diff --git accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out index 309f2f7..47e92c2 100644 --- accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out +++ accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out @@ -308,7 +308,7 @@ STAGE PLANS: filterExpr: (key >= '90') (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: ((value like '%9%') and (key = UDFToInteger(value))) (type: boolean) + predicate: ((value like '%9%') and (UDFToDouble(key) = UDFToDouble(UDFToInteger(value)))) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git common/src/java/org/apache/hadoop/hive/conf/HiveConf.java common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index c49a0f2..e610d1f 100644 --- common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -643,7 +643,7 @@ "How many rows in the joining tables (except the streaming table) should be cached in memory."), // CBO related - HIVE_CBO_ENABLED("hive.cbo.enable", false, "Flag to control enabling Cost Based Optimizations using Calcite framework."), + HIVE_CBO_ENABLED("hive.cbo.enable", true, "Flag to control enabling Cost Based Optimizations using Calcite framework."), // hive.mapjoin.bucket.cache.size has been replaced by hive.smbjoin.cache.row, // need to remove by hive .13. Also, do not change default (see SMB operator) diff --git contrib/src/test/results/clientpositive/dboutput.q.out contrib/src/test/results/clientpositive/dboutput.q.out index 554ca02..476e306 100644 --- contrib/src/test/results/clientpositive/dboutput.q.out +++ contrib/src/test/results/clientpositive/dboutput.q.out @@ -135,7 +135,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 10) (type: boolean) + predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dboutput('jdbc:derby:../build/test_dboutput_db','','','INSERT INTO app_info (kkey,vvalue) VALUES (?,?)',key,value) (type: int) diff --git contrib/src/test/results/clientpositive/udaf_example_avg.q.out contrib/src/test/results/clientpositive/udaf_example_avg.q.out index d300b0f..c282192 100644 --- contrib/src/test/results/clientpositive/udaf_example_avg.q.out +++ contrib/src/test/results/clientpositive/udaf_example_avg.q.out @@ -26,11 +26,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: value + expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) > 250.0), null, substr(value, 5)) (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: example_avg(substr(value, 5)), example_avg(if((substr(value, 5) > 250), null, substr(value, 5))) + aggregations: example_avg(_col0), example_avg(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out index 762461b..4123c5a 100644 --- contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out +++ contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out @@ -26,12 +26,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: value, key + expressions: substr(value, 5, 1) (type: string), '(' (type: string), key (type: string), ':' (type: string), value (type: string), ')' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: example_group_concat('(', key, ':', value, ')') - keys: substr(value, 5, 1) (type: string) + aggregations: example_group_concat(_col1, _col2, _col3, _col4, _col5) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git contrib/src/test/results/clientpositive/udaf_example_max.q.out contrib/src/test/results/clientpositive/udaf_example_max.q.out index 82aeca7..06fdc83 100644 --- contrib/src/test/results/clientpositive/udaf_example_max.q.out +++ contrib/src/test/results/clientpositive/udaf_example_max.q.out @@ -31,11 +31,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: value + expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) > 250.0), null, substr(value, 5)) (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: example_max(substr(value, 5)), example_max(if((substr(value, 5) > 250), null, substr(value, 5))) + aggregations: example_max(_col0), example_max(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE diff --git contrib/src/test/results/clientpositive/udaf_example_max_n.q.out contrib/src/test/results/clientpositive/udaf_example_max_n.q.out index db95fcb..4e911ed 100644 --- contrib/src/test/results/clientpositive/udaf_example_max_n.q.out +++ contrib/src/test/results/clientpositive/udaf_example_max_n.q.out @@ -26,11 +26,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: value + expressions: substr(value, 5) (type: string), 10 (type: int), if((UDFToDouble(substr(value, 5)) > 250.0), null, substr(value, 5)) (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: example_max_n(substr(value, 5), 10), example_max_n(if((substr(value, 5) > 250), null, substr(value, 5)), 10) + aggregations: example_max_n(_col0, _col1), example_max_n(_col2, _col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git contrib/src/test/results/clientpositive/udaf_example_min.q.out contrib/src/test/results/clientpositive/udaf_example_min.q.out index b62ff39..e0b2804 100644 --- contrib/src/test/results/clientpositive/udaf_example_min.q.out +++ contrib/src/test/results/clientpositive/udaf_example_min.q.out @@ -31,11 +31,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: value + expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) > 250.0), null, substr(value, 5)) (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: example_min(substr(value, 5)), example_min(if((substr(value, 5) > 250), null, substr(value, 5))) + aggregations: example_min(_col0), example_min(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE diff --git contrib/src/test/results/clientpositive/udaf_example_min_n.q.out contrib/src/test/results/clientpositive/udaf_example_min_n.q.out index 1344186..c732838 100644 --- contrib/src/test/results/clientpositive/udaf_example_min_n.q.out +++ contrib/src/test/results/clientpositive/udaf_example_min_n.q.out @@ -26,11 +26,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: value + expressions: substr(value, 5) (type: string), 10 (type: int), if((UDFToDouble(substr(value, 5)) < 250.0), null, substr(value, 5)) (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: example_min_n(substr(value, 5), 10), example_min_n(if((substr(value, 5) < 250), null, substr(value, 5)), 10) + aggregations: example_min_n(_col0, _col1), example_min_n(_col2, _col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git hbase-handler/src/test/results/positive/hbase_ppd_key_range.q.out hbase-handler/src/test/results/positive/hbase_ppd_key_range.q.out index 4e4364e..6174bfb 100644 --- hbase-handler/src/test/results/positive/hbase_ppd_key_range.q.out +++ hbase-handler/src/test/results/positive/hbase_ppd_key_range.q.out @@ -308,7 +308,7 @@ STAGE PLANS: filterExpr: (key >= '90') (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: ((value like '%9%') and (key = UDFToInteger(value))) (type: boolean) + predicate: ((value like '%9%') and (UDFToDouble(key) = UDFToDouble(UDFToInteger(value)))) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git hbase-handler/src/test/results/positive/hbase_timestamp.q.out hbase-handler/src/test/results/positive/hbase_timestamp.q.out index f70d371..3aae7d0 100644 --- hbase-handler/src/test/results/positive/hbase_timestamp.q.out +++ hbase-handler/src/test/results/positive/hbase_timestamp.q.out @@ -171,10 +171,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: hbase_table - filterExpr: (((key > 100) and (key < 400)) and (time < 200000000000)) (type: boolean) + filterExpr: (((key > 100.0) and (key < 400.0)) and (time < 200000000000)) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: (((key > 100) and (key < 400)) and (time < 200000000000)) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 400.0) and (time < 200000000000))) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), CAST( time AS TIMESTAMP) (type: timestamp) @@ -220,10 +220,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: hbase_table - filterExpr: (((key > 100) and (key < 400)) and (time > 100000000000)) (type: boolean) + filterExpr: (((key > 100.0) and (key < 400.0)) and (time > 100000000000)) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: (((key > 100) and (key < 400)) and (time > 100000000000)) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 400.0) and (time > 100000000000))) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), CAST( time AS TIMESTAMP) (type: timestamp) @@ -271,10 +271,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: hbase_table - filterExpr: (((key > 100) and (key < 400)) and (time <= 100000000000)) (type: boolean) + filterExpr: (((key > 100.0) and (key < 400.0)) and (time <= 100000000000)) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: (((key > 100) and (key < 400)) and (time <= 100000000000)) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 400.0) and (time <= 100000000000))) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), CAST( time AS TIMESTAMP) (type: timestamp) @@ -320,10 +320,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: hbase_table - filterExpr: (((key > 100) and (key < 400)) and (time >= 200000000000)) (type: boolean) + filterExpr: (((key > 100.0) and (key < 400.0)) and (time >= 200000000000)) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: (((key > 100) and (key < 400)) and (time >= 200000000000)) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 400.0) and (time >= 200000000000))) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), CAST( time AS TIMESTAMP) (type: timestamp) diff --git itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcDriver2.java itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcDriver2.java index a17ecdc..f1eb62f 100644 --- itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcDriver2.java +++ itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcDriver2.java @@ -1800,7 +1800,7 @@ public void testBuiltInUDFCol() throws SQLException { + " where c1=1"); ResultSetMetaData md = res.getMetaData(); assertEquals(md.getColumnCount(), 2); // only one result column - assertEquals(md.getColumnLabel(2), "_c1" ); // verify the system generated column name + assertEquals(md.getColumnLabel(2), "c1" ); // verify the system generated column name assertTrue(res.next()); assertEquals(res.getLong(1), 1); assertEquals(res.getString(2), "1"); diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/ASTBuilder.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/ASTBuilder.java index 276ce89..acb1edf 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/ASTBuilder.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/ASTBuilder.java @@ -167,6 +167,9 @@ static ASTNode literal(RexLiteral literal, boolean useTypeQualInLiteral) { type = HiveParser.SmallintLiteral; break; case INTEGER: + val = literal.getValue3(); + type = HiveParser.BigintLiteral; + break; case BIGINT: if (useTypeQualInLiteral) { val = literal.getValue3() + "L"; diff --git ql/src/test/queries/clientnegative/join_nonexistent_part.q ql/src/test/queries/clientnegative/join_nonexistent_part.q index b4a4757..b545a87 100644 --- ql/src/test/queries/clientnegative/join_nonexistent_part.q +++ ql/src/test/queries/clientnegative/join_nonexistent_part.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; SET hive.security.authorization.enabled = true; SELECT * FROM srcpart s1 join src s2 on s1.key == s2.key diff --git ql/src/test/queries/clientnegative/joinneg.q ql/src/test/queries/clientnegative/joinneg.q index a4967fd..9fea99e 100644 --- ql/src/test/queries/clientnegative/joinneg.q +++ ql/src/test/queries/clientnegative/joinneg.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; EXPLAIN FROM (SELECT src.* FROM src) x JOIN diff --git ql/src/test/queries/clientpositive/ambiguous_col.q ql/src/test/queries/clientpositive/ambiguous_col.q index 5ccd2c8..d1cebeb 100644 --- ql/src/test/queries/clientpositive/ambiguous_col.q +++ ql/src/test/queries/clientpositive/ambiguous_col.q @@ -1,7 +1,10 @@ set hive.support.quoted.identifiers=none; -- TOK_ALLCOLREF explain select * from (select a.key, a.* from (select * from src) a join (select * from src1) b on (a.key = b.key)) t; +select * from (select a.key, a.* from (select * from src) a join (select * from src1) b on (a.key = b.key)) t; -- DOT explain select * from (select a.key, a.`[k].*` from (select * from src) a join (select * from src1) b on (a.key = b.key)) t; +select * from (select a.key, a.`[k].*` from (select * from src) a join (select * from src1) b on (a.key = b.key)) t; -- EXPRESSION explain select * from (select a.key, a.key from (select * from src) a join (select * from src1) b on (a.key = b.key)) t; +select * from (select a.key, a.key from (select * from src) a join (select * from src1) b on (a.key = b.key)) t; diff --git ql/src/test/queries/clientpositive/annotate_stats_groupby.q ql/src/test/queries/clientpositive/annotate_stats_groupby.q index 854e401..30fc0f8 100644 --- ql/src/test/queries/clientpositive/annotate_stats_groupby.q +++ ql/src/test/queries/clientpositive/annotate_stats_groupby.q @@ -1,5 +1,7 @@ set hive.stats.fetch.column.stats=true; set hive.map.aggr.hash.percentmemory=0.0f; +set hive.cbo.enable=false; +-- Stats explain output changes with CBO, disable for now. -- hash aggregation is disabled diff --git ql/src/test/queries/clientpositive/annotate_stats_groupby2.q ql/src/test/queries/clientpositive/annotate_stats_groupby2.q index 6e65577..c5b1746 100644 --- ql/src/test/queries/clientpositive/annotate_stats_groupby2.q +++ ql/src/test/queries/clientpositive/annotate_stats_groupby2.q @@ -1,3 +1,6 @@ +set hive.cbo.enable=false; +-- Stats explain output changes with CBO, disable for now. + drop table location; -- There are different cases for Group By depending on map/reduce side, hash aggregation, diff --git ql/src/test/queries/clientpositive/constantPropagateForSubQuery.q ql/src/test/queries/clientpositive/constantPropagateForSubQuery.q index 149a290..08855cb 100644 --- ql/src/test/queries/clientpositive/constantPropagateForSubQuery.q +++ ql/src/test/queries/clientpositive/constantPropagateForSubQuery.q @@ -1,3 +1,5 @@ +-- SORT_QUERY_RESULTS + explain extended 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; diff --git ql/src/test/queries/clientpositive/constprog2.q ql/src/test/queries/clientpositive/constprog2.q index 6001668..36e6a22 100644 --- ql/src/test/queries/clientpositive/constprog2.q +++ ql/src/test/queries/clientpositive/constprog2.q @@ -1,5 +1,9 @@ set hive.fetch.task.conversion=more; set hive.optimize.constant.propagation=true; +set hive.cbo.enable=false; + +-- Some constant propagation does not work in CBO due to added casts(?), disable for now. + EXPLAIN SELECT src1.key, src1.key + 1, src2.value diff --git ql/src/test/queries/clientpositive/filter_join_breaktask2.q ql/src/test/queries/clientpositive/filter_join_breaktask2.q index 7f4258f..ae2dfba 100644 --- ql/src/test/queries/clientpositive/filter_join_breaktask2.q +++ ql/src/test/queries/clientpositive/filter_join_breaktask2.q @@ -1,6 +1,4 @@ - - - +set hive.cbo.enable=false; create table T1(c1 string, c2 string, c3 string, c4 string, c5 string, c6 string, c7 string) diff --git ql/src/test/queries/clientpositive/join_vc.q ql/src/test/queries/clientpositive/join_vc.q index 8d7dea9..3c38fa6 100644 --- ql/src/test/queries/clientpositive/join_vc.q +++ ql/src/test/queries/clientpositive/join_vc.q @@ -6,7 +6,7 @@ select t3.BLOCK__OFFSET__INSIDE__FILE,t3.key,t3.value from src t1 join src t2 on explain select t2.BLOCK__OFFSET__INSIDE__FILE -from src t1 join src t2 on t1.key = t2.key where t1.key < 100; +from src t1 join src t2 on t1.key = t2.key where t1.key < 100 order by t2.BLOCK__OFFSET__INSIDE__FILE; select t2.BLOCK__OFFSET__INSIDE__FILE -from src t1 join src t2 on t1.key = t2.key where t1.key < 100; +from src t1 join src t2 on t1.key = t2.key where t1.key < 100 order by t2.BLOCK__OFFSET__INSIDE__FILE; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_1.q ql/src/test/queries/clientpositive/list_bucket_dml_1.q index 1062e55..7a63493 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_1.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_1.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_10.q ql/src/test/queries/clientpositive/list_bucket_dml_10.q index 2fbafc2..d2848e4 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_10.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_10.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set mapred.input.dir.recursive=true; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_11.q ql/src/test/queries/clientpositive/list_bucket_dml_11.q index 8260459..ff03c9b 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_11.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_11.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set mapred.input.dir.recursive=true; set hive.merge.mapfiles=false; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_12.q ql/src/test/queries/clientpositive/list_bucket_dml_12.q index 0cab149..c8801a4 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_12.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_12.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set mapred.input.dir.recursive=true; set hive.merge.mapfiles=false; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_13.q ql/src/test/queries/clientpositive/list_bucket_dml_13.q index 5ea333f..f0c0b23 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_13.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_13.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set mapred.input.dir.recursive=true; set hive.merge.mapfiles=false; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_14.q ql/src/test/queries/clientpositive/list_bucket_dml_14.q index f60c5b0..636037b 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_14.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_14.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_2.q ql/src/test/queries/clientpositive/list_bucket_dml_2.q index 9715ff6..00978e7 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_2.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_2.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_3.q ql/src/test/queries/clientpositive/list_bucket_dml_3.q index a43613c..d6bb66a 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_3.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_3.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_4.q ql/src/test/queries/clientpositive/list_bucket_dml_4.q index 1ca54fa..5115054 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_4.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_4.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_5.q ql/src/test/queries/clientpositive/list_bucket_dml_5.q index 5278a80..98ea43f 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_5.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_5.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_6.q ql/src/test/queries/clientpositive/list_bucket_dml_6.q index 3445255..3ea6a5b 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_6.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_6.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_7.q ql/src/test/queries/clientpositive/list_bucket_dml_7.q index cacf4ea..7946c7b 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_7.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_7.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_8.q ql/src/test/queries/clientpositive/list_bucket_dml_8.q index 26103f9..5bf9472 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_8.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_8.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_dml_9.q ql/src/test/queries/clientpositive/list_bucket_dml_9.q index 4ddcddd..52e81a2 100644 --- ql/src/test/queries/clientpositive/list_bucket_dml_9.q +++ ql/src/test/queries/clientpositive/list_bucket_dml_9.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; diff --git ql/src/test/queries/clientpositive/list_bucket_query_multiskew_1.q ql/src/test/queries/clientpositive/list_bucket_query_multiskew_1.q index 48b1ff3..b6b5867 100644 --- ql/src/test/queries/clientpositive/list_bucket_query_multiskew_1.q +++ ql/src/test/queries/clientpositive/list_bucket_query_multiskew_1.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.optimize.listbucketing=true; set mapred.input.dir.recursive=true; diff --git ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q index 00410d1..5b8f995 100644 --- ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q +++ ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.optimize.listbucketing=true; set mapred.input.dir.recursive=true; diff --git ql/src/test/queries/clientpositive/list_bucket_query_multiskew_3.q ql/src/test/queries/clientpositive/list_bucket_query_multiskew_3.q index 2d1193d..21d9db7 100644 --- ql/src/test/queries/clientpositive/list_bucket_query_multiskew_3.q +++ ql/src/test/queries/clientpositive/list_bucket_query_multiskew_3.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.optimize.listbucketing=true; set mapred.input.dir.recursive=true; diff --git ql/src/test/queries/clientpositive/list_bucket_query_oneskew_1.q ql/src/test/queries/clientpositive/list_bucket_query_oneskew_1.q index 84727fe..094ab41 100644 --- ql/src/test/queries/clientpositive/list_bucket_query_oneskew_1.q +++ ql/src/test/queries/clientpositive/list_bucket_query_oneskew_1.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.optimize.listbucketing=true; set mapred.input.dir.recursive=true; diff --git ql/src/test/queries/clientpositive/list_bucket_query_oneskew_2.q ql/src/test/queries/clientpositive/list_bucket_query_oneskew_2.q index 29409e1..e9fecf9 100644 --- ql/src/test/queries/clientpositive/list_bucket_query_oneskew_2.q +++ ql/src/test/queries/clientpositive/list_bucket_query_oneskew_2.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.optimize.listbucketing=true; set mapred.input.dir.recursive=true; diff --git ql/src/test/queries/clientpositive/list_bucket_query_oneskew_3.q ql/src/test/queries/clientpositive/list_bucket_query_oneskew_3.q index 5d69906..fbab801 100644 --- ql/src/test/queries/clientpositive/list_bucket_query_oneskew_3.q +++ ql/src/test/queries/clientpositive/list_bucket_query_oneskew_3.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.optimize.listbucketing=true; set mapred.input.dir.recursive=true; set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat; diff --git ql/src/test/queries/clientpositive/partition_wise_fileformat2.q ql/src/test/queries/clientpositive/partition_wise_fileformat2.q index de51cdd..bd84ed5 100644 --- ql/src/test/queries/clientpositive/partition_wise_fileformat2.q +++ ql/src/test/queries/clientpositive/partition_wise_fileformat2.q @@ -1,3 +1,6 @@ +set hive.cbo.enable=false; +-- Disable CBO since it causes filter pruning to fail to prune in this case + -- SORT_BEFORE_DIFF create table partition_test_partitioned(key string, value string) partitioned by (dt string); diff --git ql/src/test/queries/clientpositive/ppd_gby_join.q ql/src/test/queries/clientpositive/ppd_gby_join.q index 82f358b..1e204ef 100644 --- ql/src/test/queries/clientpositive/ppd_gby_join.q +++ ql/src/test/queries/clientpositive/ppd_gby_join.q @@ -10,6 +10,14 @@ JOIN ON src1.c1 = src2.c3 AND src1.c1 < '400' WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') GROUP BY src1.c1; +SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1; set hive.ppd.remove.duplicatefilters=true; @@ -22,3 +30,11 @@ JOIN ON src1.c1 = src2.c3 AND src1.c1 < '400' WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') GROUP BY src1.c1; +SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1; diff --git ql/src/test/queries/clientpositive/subquery_exists_explain_rewrite.q ql/src/test/queries/clientpositive/subquery_exists_explain_rewrite.q index 60dfdaf..d6efd98 100644 --- ql/src/test/queries/clientpositive/subquery_exists_explain_rewrite.q +++ ql/src/test/queries/clientpositive/subquery_exists_explain_rewrite.q @@ -1,3 +1,5 @@ +set hive.cbo.enable=false; + -- no agg, corr explain rewrite select * diff --git ql/src/test/queries/clientpositive/subquery_in_explain_rewrite.q ql/src/test/queries/clientpositive/subquery_in_explain_rewrite.q index 7843680..66882aa 100644 --- ql/src/test/queries/clientpositive/subquery_in_explain_rewrite.q +++ ql/src/test/queries/clientpositive/subquery_in_explain_rewrite.q @@ -1,3 +1,5 @@ +set hive.cbo.enable=false; + DROP TABLE part; -- data setup diff --git ql/src/test/queries/clientpositive/truncate_column_list_bucket.q ql/src/test/queries/clientpositive/truncate_column_list_bucket.q index 87289f0..49e0b08 100644 --- ql/src/test/queries/clientpositive/truncate_column_list_bucket.q +++ ql/src/test/queries/clientpositive/truncate_column_list_bucket.q @@ -1,3 +1,4 @@ +set hive.cbo.enable=false; set hive.mapred.supports.subdirectories=true; set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat; set hive.merge.mapfiles=false; diff --git ql/src/test/results/clientnegative/joinneg.q.out ql/src/test/results/clientnegative/joinneg.q.out index 1d75f41..8df43d7 100644 --- ql/src/test/results/clientnegative/joinneg.q.out +++ ql/src/test/results/clientnegative/joinneg.q.out @@ -1 +1 @@ -FAILED: SemanticException [Error 10009]: Line 5:12 Invalid table alias 'b' +FAILED: SemanticException [Error 10009]: Line 6:12 Invalid table alias 'b' diff --git ql/src/test/results/clientpositive/allcolref_in_udf.q.out ql/src/test/results/clientpositive/allcolref_in_udf.q.out index 07aaae3..63319b3 100644 --- ql/src/test/results/clientpositive/allcolref_in_udf.q.out +++ ql/src/test/results/clientpositive/allcolref_in_udf.q.out @@ -16,7 +16,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + predicate: (UDFToDouble(key) < 100.0) (type: boolean) 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) diff --git ql/src/test/results/clientpositive/alter_partition_coltype.q.out ql/src/test/results/clientpositive/alter_partition_coltype.q.out index f71fa05..dfcff52 100644 --- ql/src/test/results/clientpositive/alter_partition_coltype.q.out +++ ql/src/test/results/clientpositive/alter_partition_coltype.q.out @@ -232,8 +232,8 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=3.0 [alter_coltype] - /alter_coltype/dt=100/ts=6.30 [alter_coltype] + /alter_coltype/dt=100/ts=3.0 [$hdt$_0:alter_coltype] + /alter_coltype/dt=100/ts=6.30 [$hdt$_0:alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -415,7 +415,7 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=6.30 [alter_coltype] + /alter_coltype/dt=100/ts=6.30 [$hdt$_0:alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -576,7 +576,7 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=3.0 [alter_coltype] + /alter_coltype/dt=100/ts=3.0 [$hdt$_0:$hdt$_0:alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/ambiguous_col.q.out ql/src/test/results/clientpositive/ambiguous_col.q.out index d583162..7ef2e9a 100644 --- ql/src/test/results/clientpositive/ambiguous_col.q.out +++ ql/src/test/results/clientpositive/ambiguous_col.q.out @@ -70,6 +70,53 @@ STAGE PLANS: Processor Tree: ListSink +PREHOOK: query: select * from (select a.key, a.* from (select * from src) a join (select * from src1) b on (a.key = b.key)) t +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: select * from (select a.key, a.* from (select * from src) a join (select * from src1) b on (a.key = b.key)) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +128 128 val_128 +128 128 val_128 +128 128 val_128 +146 146 val_146 +146 146 val_146 +150 150 val_150 +213 213 val_213 +213 213 val_213 +224 224 val_224 +224 224 val_224 +238 238 val_238 +238 238 val_238 +255 255 val_255 +255 255 val_255 +273 273 val_273 +273 273 val_273 +273 273 val_273 +278 278 val_278 +278 278 val_278 +311 311 val_311 +311 311 val_311 +311 311 val_311 +369 369 val_369 +369 369 val_369 +369 369 val_369 +401 401 val_401 +401 401 val_401 +401 401 val_401 +401 401 val_401 +401 401 val_401 +406 406 val_406 +406 406 val_406 +406 406 val_406 +406 406 val_406 +66 66 val_66 +98 98 val_98 +98 98 val_98 PREHOOK: query: -- DOT explain select * from (select a.key, a.`[k].*` from (select * from src) a join (select * from src1) b on (a.key = b.key)) t PREHOOK: type: QUERY @@ -141,6 +188,53 @@ STAGE PLANS: Processor Tree: ListSink +PREHOOK: query: select * from (select a.key, a.`[k].*` from (select * from src) a join (select * from src1) b on (a.key = b.key)) t +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: select * from (select a.key, a.`[k].*` from (select * from src) a join (select * from src1) b on (a.key = b.key)) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +128 128 +128 128 +128 128 +146 146 +146 146 +150 150 +213 213 +213 213 +224 224 +224 224 +238 238 +238 238 +255 255 +255 255 +273 273 +273 273 +273 273 +278 278 +278 278 +311 311 +311 311 +311 311 +369 369 +369 369 +369 369 +401 401 +401 401 +401 401 +401 401 +401 401 +406 406 +406 406 +406 406 +406 406 +66 66 +98 98 +98 98 PREHOOK: query: -- EXPRESSION explain select * from (select a.key, a.key from (select * from src) a join (select * from src1) b on (a.key = b.key)) t PREHOOK: type: QUERY @@ -212,3 +306,50 @@ STAGE PLANS: Processor Tree: ListSink +PREHOOK: query: select * from (select a.key, a.key from (select * from src) a join (select * from src1) b on (a.key = b.key)) t +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: select * from (select a.key, a.key from (select * from src) a join (select * from src1) b on (a.key = b.key)) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +128 128 +128 128 +128 128 +146 146 +146 146 +150 150 +213 213 +213 213 +224 224 +224 224 +238 238 +238 238 +255 255 +255 255 +273 273 +273 273 +273 273 +278 278 +278 278 +311 311 +311 311 +311 311 +369 369 +369 369 +369 369 +401 401 +401 401 +401 401 +401 401 +401 401 +406 406 +406 406 +406 406 +406 406 +66 66 +98 98 +98 98 diff --git ql/src/test/results/clientpositive/annotate_stats_filter.q.out ql/src/test/results/clientpositive/annotate_stats_filter.q.out index 70df189..e8cd06d 100644 --- ql/src/test/results/clientpositive/annotate_stats_filter.q.out +++ ql/src/test/results/clientpositive/annotate_stats_filter.q.out @@ -264,10 +264,10 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), null (type: void), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -417,7 +417,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- numRows: 0 rawDataSize: 0 @@ -480,7 +480,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- numRows: 8 rawDataSize: 804 @@ -541,7 +541,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- numRows: 0 rawDataSize: 0 @@ -723,10 +723,10 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), null (type: void) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/annotate_stats_groupby.q.out ql/src/test/results/clientpositive/annotate_stats_groupby.q.out index 1459b44..0a2c708 100644 --- ql/src/test/results/clientpositive/annotate_stats_groupby.q.out +++ ql/src/test/results/clientpositive/annotate_stats_groupby.q.out @@ -1,4 +1,6 @@ -PREHOOK: query: -- hash aggregation is disabled +PREHOOK: query: -- Stats explain output changes with CBO, disable for now. + +-- hash aggregation is disabled -- There are different cases for Group By depending on map/reduce side, hash aggregation, -- grouping sets and column stats. If we don't have column stats, we just assume hash @@ -27,7 +29,9 @@ create table if not exists loc_staging ( PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@loc_staging -POSTHOOK: query: -- hash aggregation is disabled +POSTHOOK: query: -- Stats explain output changes with CBO, disable for now. + +-- hash aggregation is disabled -- There are different cases for Group By depending on map/reduce side, hash aggregation, -- grouping sets and column stats. If we don't have column stats, we just assume hash diff --git ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out index f991191..07ad0c8 100644 --- ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out +++ ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out @@ -1,6 +1,10 @@ -PREHOOK: query: drop table location +PREHOOK: query: -- Stats explain output changes with CBO, disable for now. + +drop table location PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table location +POSTHOOK: query: -- Stats explain output changes with CBO, disable for now. + +drop table location POSTHOOK: type: DROPTABLE PREHOOK: query: -- There are different cases for Group By depending on map/reduce side, hash aggregation, -- grouping sets and column stats. If we don't have column stats, we just assume hash diff --git ql/src/test/results/clientpositive/annotate_stats_join.q.out ql/src/test/results/clientpositive/annotate_stats_join.q.out index c9ad41d..99a580c 100644 --- ql/src/test/results/clientpositive/annotate_stats_join.q.out +++ ql/src/test/results/clientpositive/annotate_stats_join.q.out @@ -168,24 +168,32 @@ STAGE PLANS: Filter Operator predicate: deptid is not null (type: boolean) 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) + 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 - value expressions: deptname (type: string) + 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) TableScan alias: e 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 - Reduce Output Operator - key expressions: deptid (type: int) - sort order: + - Map-reduce partition columns: deptid (type: int) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: lastname (type: string), locid (type: int) + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: int) Reduce Operator Tree: Join Operator condition map: @@ -193,15 +201,15 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col6, _col7 - Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string) + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -230,28 +238,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: 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) - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - 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 - 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) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: deptid (type: int), lastname (type: string) - sort order: ++ - Map-reduce partition columns: deptid (type: int), lastname (type: string) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: locid (type: int) + 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) + 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) + 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), _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: @@ -259,22 +275,19 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} - outputColumnNames: _col0, _col1, _col2, _col6, _col7 - Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 = _col6) and (_col0 = _col7)) (type: boolean) - Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 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 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 594 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 @@ -300,23 +313,31 @@ STAGE PLANS: Filter Operator predicate: (deptid is not null and deptname is not null) (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: deptid (type: int), deptname (type: string) - sort order: ++ - Map-reduce partition columns: deptid (type: int), deptname (type: string) + 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), _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 TableScan 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) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: deptid (type: int), lastname (type: string) - sort order: ++ - Map-reduce partition columns: deptid (type: int), lastname (type: string) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: locid (type: int) + 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) Reduce Operator Tree: Join Operator condition map: @@ -324,15 +345,15 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} - outputColumnNames: _col0, _col1, _col2, _col6, _col7 - Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string) + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -361,28 +382,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: 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) - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: deptid (type: int), deptname (type: string), deptname (type: string) - sort order: +++ - Map-reduce partition columns: deptid (type: int), deptname (type: string), deptname (type: string) - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - 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) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: deptid (type: int), lastname (type: string), lastname (type: string) - sort order: +++ - Map-reduce partition columns: deptid (type: int), lastname (type: string), lastname (type: string) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: locid (type: int) + 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) + 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) + 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), _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: @@ -390,22 +419,19 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} - outputColumnNames: _col0, _col1, _col2, _col6, _col7 - Statistics: Num rows: 11 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((_col1 = _col6) and (_col0 = _col7)) and (_col7 = _col0)) (type: boolean) - Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 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 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 11 Data size: 1089 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 11 Data size: 1089 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 11 Data size: 1089 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 @@ -422,11 +448,12 @@ POSTHOOK: query: -- 3 relations, 1 attribute explain select * from emp e join dept d on (e.deptid = d.deptid) join emp e1 on (e.deptid = e1.deptid) 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 @@ -435,54 +462,90 @@ STAGE PLANS: Filter Operator predicate: deptid is not null (type: boolean) 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) + 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 - value expressions: deptname (type: string) + 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) TableScan - alias: e1 + alias: e 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 - Reduce Output Operator - key expressions: deptid (type: int) - sort order: + - Map-reduce partition columns: deptid (type: int) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: lastname (type: string), locid (type: int) + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: int) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 41 Data size: 4059 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-1 + Map Reduce + Map Operator Tree: TableScan alias: e 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 - Reduce Output Operator - key expressions: deptid (type: int) - sort order: + - Map-reduce partition columns: deptid (type: int) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: lastname (type: string), locid (type: int) + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: int) + TableScan + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 condition expressions: - 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} - 1 {KEY.reducesinkkey0} {VALUE._col0} - 2 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13 - Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE + 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} {VALUE._col2} {VALUE._col3} + 1 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 656 Data size: 127264 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: int) + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 656 Data size: 127264 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 656 Data size: 127264 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -502,7 +565,8 @@ explain select * from emp e join dept d on (e.deptid = d.deptid) join loc l on 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 @@ -514,54 +578,90 @@ STAGE PLANS: Filter Operator predicate: deptid is not null (type: boolean) 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) + 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 - value expressions: deptname (type: string) + 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) TableScan alias: e 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 - Reduce Output Operator - key expressions: deptid (type: int) - sort order: + - Map-reduce partition columns: deptid (type: int) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: lastname (type: string), locid (type: int) + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: int) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 41 Data size: 4059 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 + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 41 Data size: 4059 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) TableScan alias: l Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: locid is not null (type: boolean) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: locid (type: int) - sort order: + - Map-reduce partition columns: locid (type: int) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: state (type: string), zip (type: bigint), year (type: int) + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 condition expressions: - 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} - 1 {KEY.reducesinkkey0} {VALUE._col0} - 2 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} {VALUE._col2} - outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13, _col14 - Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE + 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} {VALUE._col2} {VALUE._col3} + 1 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} {VALUE._col2} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 46 Data size: 8878 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: bigint), _col14 (type: int) + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: bigint), _col8 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 46 Data size: 8878 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 46 Data size: 8878 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -583,7 +683,8 @@ explain select * from emp e join dept d on (e.deptid = d.deptid and e.lastname = 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 @@ -595,53 +696,89 @@ STAGE PLANS: Filter Operator predicate: (deptid is not null and deptname is not null) (type: boolean) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: deptid (type: int), deptname (type: string) - sort order: ++ - Map-reduce partition columns: deptid (type: int), deptname (type: string) + 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), _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 TableScan 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) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: deptid (type: int), lastname (type: string) - sort order: ++ - Map-reduce partition columns: deptid (type: int), lastname (type: string) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: locid (type: int) + 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) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 6 Data size: 594 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 + key expressions: _col1 (type: int), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col0 (type: string) + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: string) 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) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: locid (type: int), state (type: string) - sort order: ++ - Map-reduce partition columns: locid (type: int), state (type: string) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: zip (type: bigint), year (type: int) + 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: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint), _col3 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 condition expressions: - 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} - 2 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} {VALUE._col2} + 1 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: bigint), _col14 (type: int) + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: bigint), _col8 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out index c91e2f3..20aa096 100644 --- ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out +++ ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out @@ -278,33 +278,41 @@ STAGE PLANS: Filter Operator predicate: s_store_sk is not null (type: boolean) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 48 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: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_store_sk is not null (type: boolean) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 964 Data size: 3716 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: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -339,33 +347,41 @@ STAGE PLANS: Filter Operator predicate: (s_store_sk > 0) (type: boolean) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 16 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: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_store_sk > 0) (type: boolean) Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 333 Data size: 1284 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: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 111 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 111 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -398,35 +414,43 @@ STAGE PLANS: alias: s Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator - predicate: (s_store_sk is not null and (s_company_id > 0)) (type: boolean) + predicate: ((s_company_id > 0) and s_store_sk is not null) (type: boolean) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_store_sk is not null and (ss_quantity > 10)) (type: boolean) + predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) - Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 321 Data size: 1236 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: 321 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col2 Statistics: Num rows: 107 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL Select Operator - expressions: _col0 (type: int) + expressions: _col2 (type: int) outputColumnNames: _col0 Statistics: Num rows: 107 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator @@ -459,35 +483,43 @@ STAGE PLANS: alias: s Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (s_store_sk is not null and (s_floor_space > 0)) (type: boolean) + predicate: ((s_floor_space > 0) and s_store_sk is not null) (type: boolean) Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) - 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: 4 Data size: 16 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: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_store_sk is not null (type: boolean) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 964 Data size: 3716 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: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -522,33 +554,41 @@ STAGE PLANS: Filter Operator predicate: s_store_sk is not null (type: boolean) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 48 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: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_store_sk is not null and (ss_quantity > 10)) (type: boolean) + predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) - Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 321 Data size: 1236 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: 321 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col2 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col2 (type: int) outputColumnNames: _col0 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -578,51 +618,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + 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 - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 48 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: 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 - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 48 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: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_store_sk is not null (type: boolean) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 964 Data size: 3716 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: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 + 0 + 1 {KEY.reducesinkkey0} 2 - outputColumnNames: _col0 + outputColumnNames: _col1 Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -652,51 +704,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: s 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 - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 16 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: 4 Data size: 16 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 > 1000) (type: boolean) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 16 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: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_store_sk > 1000) (type: boolean) Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 333 Data size: 1284 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: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 + 0 + 1 {KEY.reducesinkkey0} 2 - outputColumnNames: _col0 + outputColumnNames: _col1 Statistics: Num rows: 37 Data size: 148 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 37 Data size: 148 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -726,51 +790,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + 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 - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + 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 + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 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: 4 Data size: 16 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 and (s_floor_space > 1000)) (type: boolean) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) - 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: 12 Data size: 48 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: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_store_sk is not null (type: boolean) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 964 Data size: 3716 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: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 + 0 + 1 {KEY.reducesinkkey0} 2 - outputColumnNames: _col0 + outputColumnNames: _col1 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -800,51 +876,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + 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 - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 48 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: 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 - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 48 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: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_store_sk is not null and (ss_quantity > 10)) (type: boolean) + predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) - Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 321 Data size: 1236 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: 321 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 + 0 + 1 {KEY.reducesinkkey0} 2 - outputColumnNames: _col0 + outputColumnNames: _col2 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col2 (type: int) outputColumnNames: _col0 Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -866,46 +954,54 @@ 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-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: 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 - Reduce Output Operator - key expressions: s_store_sk (type: int) - sort order: + - Map-reduce partition columns: s_store_sk (type: int) - 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: ca_address_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_store_sk is not null and ss_addr_sk is not null) (type: boolean) + predicate: (ss_addr_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 916 Data size: 7012 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: ss_store_sk (type: int) - sort order: + - Map-reduce partition columns: ss_store_sk (type: int) + Select Operator + expressions: ss_addr_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 916 Data size: 7012 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: ss_addr_sk (type: int) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 916 Data size: 7012 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col6} - outputColumnNames: _col0, _col38 - Statistics: Num rows: 916 Data size: 7328 Basic stats: COMPLETE Column stats: COMPLETE + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 1017 Data size: 4068 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -913,43 +1009,46 @@ 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: ca - Statistics: Num rows: 20 Data size: 2114 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 - Reduce Output Operator - key expressions: ca_address_sk (type: int) - sort order: + - 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: _col38 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col38 (type: int) - Statistics: Num rows: 916 Data size: 7328 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1017 Data size: 4068 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 + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 48 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: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col0} - 1 - outputColumnNames: _col0 - Statistics: Num rows: 916 Data size: 3664 Basic stats: COMPLETE Column stats: COMPLETE + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col3 + Statistics: Num rows: 1017 Data size: 4068 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col3 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 916 Data size: 3664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1017 Data size: 4068 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 916 Data size: 3664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1017 Data size: 4068 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/annotate_stats_limit.q.out ql/src/test/results/clientpositive/annotate_stats_limit.q.out index b61a597..5f8b6f8 100644 --- ql/src/test/results/clientpositive/annotate_stats_limit.q.out +++ ql/src/test/results/clientpositive/annotate_stats_limit.q.out @@ -80,7 +80,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- numRows: 4 rawDataSize: 396 @@ -103,7 +103,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 4 Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE @@ -131,10 +131,10 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 16 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- numRows: 0 rawDataSize: 0 @@ -157,7 +157,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/annotate_stats_part.q.out ql/src/test/results/clientpositive/annotate_stats_part.q.out index b767a32..593dcff 100644 --- ql/src/test/results/clientpositive/annotate_stats_part.q.out +++ ql/src/test/results/clientpositive/annotate_stats_part.q.out @@ -102,7 +102,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- partition level analyze statistics for specific parition @@ -162,7 +162,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1656 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: NONE @@ -249,7 +249,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: NONE @@ -272,7 +272,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- both partitions will be pruned @@ -475,7 +475,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 2192 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- This is to test filter expression evaluation on partition column @@ -487,106 +487,70 @@ POSTHOOK: query: -- This is to test filter expression evaluation on partition co explain select locid from loc_orc where locid>0 and year='2001' 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: loc_orc - Statistics: Num rows: 7 Data size: 400 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) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - 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 limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc + Statistics: Num rows: 7 Data size: 400 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) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + ListSink PREHOOK: query: explain select locid,year from loc_orc where locid>0 and year='2001' PREHOOK: type: QUERY POSTHOOK: query: explain select locid,year from loc_orc where locid>0 and year='2001' 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: loc_orc - Statistics: Num rows: 7 Data size: 400 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 - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 184 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 + TableScan + alias: loc_orc + Statistics: Num rows: 7 Data size: 400 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 + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + ListSink PREHOOK: query: explain select * from (select locid,year from loc_orc) test where locid>0 and year='2001' PREHOOK: type: QUERY POSTHOOK: query: explain select * from (select locid,year from loc_orc) test where locid>0 and year='2001' 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: loc_orc - Statistics: Num rows: 7 Data size: 400 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 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - 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 limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc + Statistics: Num rows: 7 Data size: 400 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 + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + ListSink diff --git ql/src/test/results/clientpositive/annotate_stats_select.q.out ql/src/test/results/clientpositive/annotate_stats_select.q.out index 8ef4964..1e86e86 100644 --- ql/src/test/results/clientpositive/annotate_stats_select.q.out +++ ql/src/test/results/clientpositive/annotate_stats_select.q.out @@ -142,7 +142,7 @@ STAGE PLANS: 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 - Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- numRows: 2 rawDataSize: 8 @@ -305,9 +305,9 @@ STAGE PLANS: alias: alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 11 (type: int) + expressions: 11 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- numRows: 2 rawDataSize: 16 @@ -568,10 +568,10 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -603,10 +603,10 @@ STAGE PLANS: Select Operator expressions: str_to_map('a=1 b=2 c=3',' ','=') (type: map) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1840 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1840 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -762,9 +762,11 @@ STAGE PLANS: alias: alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -816,9 +818,9 @@ STAGE PLANS: alias: alltypes_orc 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) + 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: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 2 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 436 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- subquery selects @@ -832,52 +834,24 @@ POSTHOOK: query: -- subquery selects explain select i1 from (select i1 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) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - 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 - limit: -1 + limit: 10 Processor Tree: - ListSink + 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 + ListSink PREHOOK: query: -- inner select - numRows: 2 rawDataSize: 16 -- outer select - numRows: 2 rawDataSize: 8 @@ -888,52 +862,24 @@ POSTHOOK: query: -- inner select - numRows: 2 rawDataSize: 16 explain select i1 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) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - 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 - limit: -1 + limit: 10 Processor Tree: - ListSink + 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 + ListSink PREHOOK: query: -- inner select - numRows: 2 rawDataSize: 16 -- outer select - numRows: 2 rawDataSize: 186 @@ -1000,52 +946,24 @@ POSTHOOK: query: -- inner select - numRows: 2 rawDataSize: 24 explain select x from (select i1,11.0 as x 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: 11.0 (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col1 (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 16 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: alltypes_orc + Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 11.0 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + ListSink PREHOOK: query: -- inner select - numRows: 2 rawDataSize: 104 -- outer select - numRows: 2 rawDataSize: 186 @@ -1127,7 +1045,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'hello' (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 @@ -1135,17 +1053,17 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col1 (type: string) - outputColumnNames: _col1 + expressions: VALUE._col0 (type: string) + outputColumnNames: _col0 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 Select Operator - expressions: _col1 (type: string) + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Limit diff --git ql/src/test/results/clientpositive/annotate_stats_table.q.out ql/src/test/results/clientpositive/annotate_stats_table.q.out index eed5daa..c91a353 100644 --- ql/src/test/results/clientpositive/annotate_stats_table.q.out +++ ql/src/test/results/clientpositive/annotate_stats_table.q.out @@ -159,7 +159,7 @@ STAGE PLANS: Select Operator expressions: lastname (type: string), deptid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 48 Data size: 364 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 48 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- all selected columns have statistics @@ -217,7 +217,7 @@ STAGE PLANS: Select Operator expressions: lastname (type: string), deptid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 48 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE diff --git ql/src/test/results/clientpositive/annotate_stats_union.q.out ql/src/test/results/clientpositive/annotate_stats_union.q.out index e0e1504..f4dca28 100644 --- ql/src/test/results/clientpositive/annotate_stats_union.q.out +++ ql/src/test/results/clientpositive/annotate_stats_union.q.out @@ -164,7 +164,7 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: -- numRows: 16 rawDataSize: 1592 @@ -187,16 +187,16 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE + 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 @@ -207,16 +207,16 @@ STAGE PLANS: Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE + 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 diff --git ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out index 4917ac0..5e5a2f6 100644 --- ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out +++ ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out @@ -16,7 +16,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (UDFToInteger(key) / UDFToInteger(key)) (type: decimal(21,11)) + expressions: (CAST( UDFToInteger(key) AS decimal(10,0)) / CAST( UDFToInteger(key) AS decimal(10,0))) (type: decimal(21,11)) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit @@ -63,7 +63,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (UDFToInteger(key) / UDFToInteger(key)) (type: double) + expressions: (UDFToDouble(UDFToInteger(key)) / UDFToDouble(UDFToInteger(key))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/authorization_explain.q.out ql/src/test/results/clientpositive/authorization_explain.q.out index ba73021..eff0c73 100644 --- ql/src/test/results/clientpositive/authorization_explain.q.out +++ ql/src/test/results/clientpositive/authorization_explain.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[4][tables = [src, srcpart]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain authorization select * from src join srcpart PREHOOK: type: QUERY POSTHOOK: query: explain authorization select * from src join srcpart @@ -19,7 +19,7 @@ OPERATION: AUTHORIZATION_FAILURES: No privilege 'Select' found for inputs { database:default, table:srcpart, columnName:key} No privilege 'Select' found for inputs { database:default, table:src, columnName:key} -Warning: Shuffle Join JOIN[4][tables = [src, srcpart]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] 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 ql/src/test/results/clientpositive/auto_join10.q.out ql/src/test/results/clientpositive/auto_join10.q.out index 3d2bcc2..1e88034 100644 --- ql/src/test/results/clientpositive/auto_join10.q.out +++ ql/src/test/results/clientpositive/auto_join10.q.out @@ -23,11 +23,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - x:src + $hdt$_0:$hdt$_0:$hdt$_0:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - x:src + $hdt$_0:$hdt$_0:$hdt$_0:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -35,13 +35,13 @@ STAGE PLANS: 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: - 0 - 1 {_col0} {_col1} + 0 {_col1} + 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) @@ -56,26 +56,26 @@ STAGE PLANS: 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 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {_col0} {_col1} + 0 {_col0} {_col1} + 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col2, _col3 + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string) - outputColumnNames: _col2, _col3 + expressions: hash(_col0,_col1) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col2,_col3)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/auto_join11.q.out ql/src/test/results/clientpositive/auto_join11.q.out index 8dbad67..bd23f3a 100644 --- ql/src/test/results/clientpositive/auto_join11.q.out +++ ql/src/test/results/clientpositive/auto_join11.q.out @@ -23,25 +23,25 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - src1:src + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src1:src + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: - 0 - 1 {_col1} + 0 {_col1} + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) @@ -53,29 +53,29 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} - 1 {_col1} + 0 {_col1} + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 + expressions: hash(_col2,_col1) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0,_col3)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/auto_join12.q.out ql/src/test/results/clientpositive/auto_join12.q.out index 037116c..6c3d441 100644 --- ql/src/test/results/clientpositive/auto_join12.q.out +++ ql/src/test/results/clientpositive/auto_join12.q.out @@ -21,61 +21,57 @@ JOIN ON src1.c1 = src3.c5 AND src3.c5 < 80 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-6 is a root stage - Stage-2 depends on stages: Stage-6 + Stage-7 is a root stage + Stage-2 depends on stages: Stage-7 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-6 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - src1:src + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src Fetch Operator limit: -1 - src2:src + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src1:src + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 80) and (key < 100)) (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 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: - 0 - 1 {_col1} - 2 + 0 {_col1} + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - src2:src + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key < 100) and (key < 80)) 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), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: 0 - 1 {_col1} - 2 + 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -84,7 +80,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 100) and (key < 80)) (type: boolean) + 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 Select Operator expressions: key (type: string) @@ -93,30 +89,42 @@ STAGE PLANS: Map Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 condition expressions: 0 {_col0} - 1 {_col1} - 2 + 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0,_col3)) - 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: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col1} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2 + 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: 182 Data size: 1939 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) Local Work: Map Reduce Local Work Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/auto_join13.q.out ql/src/test/results/clientpositive/auto_join13.q.out index 0cb9b4f..b3778c9 100644 --- ql/src/test/results/clientpositive/auto_join13.q.out +++ ql/src/test/results/clientpositive/auto_join13.q.out @@ -29,37 +29,37 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - src1:src + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src Fetch Operator limit: -1 - src3:src + $hdt$_0:$hdt$_0:$hdt$_2:$hdt$_2:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src1:src + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: - 0 - 1 {_col0} {_col1} + 0 {_col1} + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) - src3:src + $hdt$_0:$hdt$_0:$hdt$_2:$hdt$_2:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and UDFToDouble(key) is not null) (type: boolean) + 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 Select Operator expressions: key (type: string) @@ -67,10 +67,10 @@ STAGE PLANS: Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: - 0 {_col0} {_col3} + 0 {_col1} {_col2} 1 keys: - 0 (_col0 + _col2) (type: double) + 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) 1 UDFToDouble(_col0) (type: double) Stage: Stage-3 @@ -80,43 +80,43 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} - 1 {_col0} {_col1} + 0 {_col0} {_col1} + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 + _col2) is not null (type: boolean) - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + predicate: (((UDFToDouble(_col2) + UDFToDouble(_col0)) < 200.0) and (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null) (type: boolean) + Statistics: Num rows: 30 Data size: 319 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} {_col3} + 0 {_col1} {_col2} 1 keys: - 0 (_col0 + _col2) (type: double) + 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col2 + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + expressions: hash(_col2,_col1) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0,_col3)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/auto_join16.q.out ql/src/test/results/clientpositive/auto_join16.q.out index f96bae3..eab31a9 100644 --- ql/src/test/results/clientpositive/auto_join16.q.out +++ ql/src/test/results/clientpositive/auto_join16.q.out @@ -23,62 +23,66 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - subq:a + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - subq:a + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((key > 10) and value is not null) and (key > 20)) and (value < 200)) (type: boolean) - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + 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 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: 0 - 1 {value} + 1 {_col1} keys: 0 _col0 (type: string), _col1 (type: string) - 1 key (type: string), value (type: string) + 1 _col0 (type: string), _col1 (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: tab + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((key > 20) and value is not null) and key is not null) and (value < 200)) (type: boolean) - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 key (type: string), value (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) + 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 + 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 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col1} + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0,_col3)) - mode: hash + Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash(_col0,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Statistics: Num rows: 5 Data size: 58 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 - 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: diff --git ql/src/test/results/clientpositive/auto_join18.q.out ql/src/test/results/clientpositive/auto_join18.q.out index 0de3f2a..b7db3dc 100644 --- ql/src/test/results/clientpositive/auto_join18.q.out +++ ql/src/test/results/clientpositive/auto_join18.q.out @@ -36,34 +36,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: src1 + Statistics: Num rows: 500 Data size: 5312 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 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT value) - keys: key (type: string), value (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ + key expressions: _col0 (type: string) + sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0) + aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -79,14 +80,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -98,11 +99,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(_col0,_col1,_col2,_col3) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0,_col1,_col2,_col3)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -143,35 +144,34 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: src2 + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + key expressions: _col0 (type: string), _col1 (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) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE 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 + Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out index 46559a7..383e29c 100644 --- ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out +++ ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out @@ -38,34 +38,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: src1 + Statistics: Num rows: 500 Data size: 5312 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 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT value), count(DISTINCT key) - keys: key (type: string), value (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ + key expressions: _col0 (type: string) + sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) + aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + 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: @@ -81,15 +82,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) + Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Join Operator condition map: @@ -100,11 +101,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint), _col4 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: hash(_col0,_col1,_col2,_col3,_col4) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0,_col1,_col2,_col3,_col4)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -145,35 +146,34 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: src2 + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(DISTINCT _col1), count(DISTINCT _col0) + keys: _col0 (type: string), _col1 (type: string) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + key expressions: _col0 (type: string), _col1 (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) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._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: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE 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 + expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git ql/src/test/results/clientpositive/auto_join22.q.out ql/src/test/results/clientpositive/auto_join22.q.out index c4a0084..0d50587 100644 --- ql/src/test/results/clientpositive/auto_join22.q.out +++ ql/src/test/results/clientpositive/auto_join22.q.out @@ -13,90 +13,102 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - src5:src3:src1 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src4 Fetch Operator limit: -1 - src5:src4 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:src4 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src5:src3:src1 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:src4 TableScan - alias: src1 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - src5:src4 + 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 + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:src4 TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 - 1 {_col3} - keys: - 0 key (type: string) - 1 _col2 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col2, _col3 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 {_col3} - keys: - 0 key (type: string) - 1 _col2 (type: string) - outputColumnNames: _col8 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col8 (type: string) - outputColumnNames: _col3 + 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 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col1} + 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 - Group By Operator - aggregations: sum(hash(_col3)) - mode: hash + Select Operator + expressions: hash(_col1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 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 - 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: diff --git ql/src/test/results/clientpositive/auto_join27.q.out ql/src/test/results/clientpositive/auto_join27.q.out index c16992f..943b907 100644 --- ql/src/test/results/clientpositive/auto_join27.q.out +++ ql/src/test/results/clientpositive/auto_join27.q.out @@ -37,14 +37,14 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 200) (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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -73,16 +73,16 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - src3:src + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src3:src + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 200) (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) @@ -102,34 +102,40 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 249 Data size: 2644 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE - Select Operator + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 249 Data size: 2644 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash + Select Operator + expressions: 1 (type: bigint) 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 + Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col0) + 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: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 200) (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) @@ -137,29 +143,35 @@ STAGE PLANS: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE - Select Operator + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 249 Data size: 2644 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash + Select Operator + expressions: 1 (type: bigint) 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 + Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col0) + 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 diff --git ql/src/test/results/clientpositive/auto_join_filters.q.out ql/src/test/results/clientpositive/auto_join_filters.q.out index a8c0221..a6720d9 100644 --- ql/src/test/results/clientpositive/auto_join_filters.q.out +++ 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[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] 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[10][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] 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 diff --git ql/src/test/results/clientpositive/auto_join_nulls.q.out ql/src/test/results/clientpositive/auto_join_nulls.q.out index 7abde8f..f20d5b7 100644 --- ql/src/test/results/clientpositive/auto_join_nulls.q.out +++ 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[13][bigTable=b] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[21][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[13][bigTable=a] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][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[13][bigTable=b] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][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 ql/src/test/results/clientpositive/auto_join_reordering_values.q.out ql/src/test/results/clientpositive/auto_join_reordering_values.q.out index aed67b6..d7cc279 100644 --- ql/src/test/results/clientpositive/auto_join_reordering_values.q.out +++ ql/src/test/results/clientpositive/auto_join_reordering_values.q.out @@ -319,7 +319,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -445,7 +445,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -571,7 +571,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10004 + base file name: -mr-10005 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/auto_join_without_localtask.q.out ql/src/test/results/clientpositive/auto_join_without_localtask.q.out index 318b548..6b82ee2 100644 --- ql/src/test/results/clientpositive/auto_join_without_localtask.q.out +++ ql/src/test/results/clientpositive/auto_join_without_localtask.q.out @@ -20,22 +20,25 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - b + $hdt$_0:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - b + $hdt$_0:$hdt$_1:a TableScan - alias: b + alias: a Filter Operator predicate: key is not null (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-3 Map Reduce @@ -44,78 +47,87 @@ STAGE PLANS: alias: a Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Limit - Number of rows: 40 - 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: string) + outputColumnNames: _col0, _col1 + Limit + Number of rows: 40 + 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 Local Work: Map Reduce Local Work Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - a + $hdt$_0:$hdt$_0:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - a + $hdt$_0:$hdt$_0:a TableScan alias: a Filter Operator predicate: key is not null (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Limit - Number of rows: 40 - 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: string) + outputColumnNames: _col0, _col1 + Limit + Number of rows: 40 + 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 Local Work: Map Reduce Local Work @@ -123,28 +135,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Join Operator condition map: @@ -233,93 +253,102 @@ POSTHOOK: query: explain select a.* from src a join src b on a.key=b.key join src c on a.value=c.value limit 40 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-10 is a root stage , consists of Stage-13, Stage-14, Stage-1 - Stage-13 has a backup stage: Stage-1 + Stage-9 is a root stage , consists of Stage-12, Stage-13, Stage-2 + Stage-12 has a backup stage: Stage-2 + Stage-7 depends on stages: Stage-12 + Stage-6 depends on stages: Stage-2, Stage-7, Stage-8 , consists of Stage-10, Stage-5, Stage-1 + Stage-10 has a backup stage: Stage-1 + Stage-4 depends on stages: Stage-10 + Stage-5 has a backup stage: Stage-1 + Stage-1 + Stage-13 has a backup stage: Stage-2 Stage-8 depends on stages: Stage-13 - Stage-7 depends on stages: Stage-1, Stage-8, Stage-9 , consists of Stage-11, Stage-6, Stage-2 - Stage-11 has a backup stage: Stage-2 - Stage-5 depends on stages: Stage-11 - Stage-6 has a backup stage: Stage-2 Stage-2 - Stage-14 has a backup stage: Stage-1 - Stage-9 depends on stages: Stage-14 - Stage-1 - Stage-0 depends on stages: Stage-5, Stage-6, Stage-2 + Stage-0 depends on stages: Stage-4, Stage-5, Stage-1 STAGE PLANS: - Stage: Stage-10 + Stage: Stage-9 Conditional Operator - Stage: Stage-13 + Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: - b + $hdt$_0:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - b + $hdt$_0:$hdt$_1:a TableScan - alias: b + alias: a Filter Operator - predicate: key is not null (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + predicate: value is not null (type: boolean) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) - Stage: Stage-8 + Stage: Stage-7 Map Reduce Map Operator Tree: TableScan alias: a Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + predicate: (value is not null and key is not null) (type: boolean) + Select Operator + expressions: key (type: string), value (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 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col1 (type: string) + 1 _col0 (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 Local Work: Map Reduce Local Work - Stage: Stage-7 + Stage: Stage-6 Conditional Operator - Stage: Stage-11 + Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - c + $hdt$_0:$hdt$_2:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - c + $hdt$_0:$hdt$_2:a TableScan - alias: c + alias: a Filter Operator - predicate: value is not null (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {_col0} {_col1} - 1 - keys: - 0 _col1 (type: string) - 1 value (type: string) + predicate: key is not null (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-5 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -330,8 +359,8 @@ STAGE PLANS: 0 {_col0} {_col1} 1 keys: - 0 _col1 (type: string) - 1 value (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1 Select Operator expressions: _col0 (type: string), _col1 (type: string) @@ -347,71 +376,78 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: c + alias: a Filter Operator - predicate: value is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} {_col1} - 1 - keys: - 0 _col1 (type: string) - 1 value (type: string) - outputColumnNames: _col0, _col1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) + predicate: key is not null (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Limit - Number of rows: 40 - 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: string) + outputColumnNames: _col0, _col1 + Limit + Number of rows: 40 + 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 Local Work: Map Reduce Local Work Alias -> Map Local Tables: - $INTNAME + $hdt$_0:$INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $INTNAME + $hdt$_0:$INTNAME TableScan - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - TableScan - alias: c + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - 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 - Reduce Output Operator - key expressions: value (type: string) - sort order: + - Map-reduce partition columns: value (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col0} {KEY.reducesinkkey0} + 0 {KEY.reducesinkkey0} {VALUE._col0} 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE @@ -430,84 +466,98 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-14 + Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: - a + $hdt$_0:$hdt$_0:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - a + $hdt$_0:$hdt$_0:a TableScan alias: a Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + predicate: (value is not null and key is not null) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) - Stage: Stage-9 + Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Filter Operator - predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (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 + predicate: value is not null (type: boolean) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col1 (type: string) + 1 _col0 (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 Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 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 TableScan alias: a 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) + 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 - 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator + key expressions: _col1 (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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} + 0 {VALUE._col0} {KEY.reducesinkkey0} 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE @@ -532,12 +582,12 @@ 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-10:CONDITIONAL -RUN: Stage-14:MAPREDLOCAL -RUN: Stage-9:MAPRED -RUN: Stage-7:CONDITIONAL -RUN: Stage-11:MAPREDLOCAL -RUN: Stage-5:MAPRED +RUN: Stage-9:CONDITIONAL +RUN: Stage-12:MAPREDLOCAL +RUN: Stage-7:MAPRED +RUN: Stage-6:CONDITIONAL +RUN: Stage-10:MAPREDLOCAL +RUN: Stage-4:MAPRED 238 val_238 238 val_238 238 val_238 @@ -588,10 +638,10 @@ STAGE DEPENDENCIES: Stage-10 is a root stage , consists of Stage-13, Stage-14, Stage-1 Stage-13 has a backup stage: Stage-1 Stage-8 depends on stages: Stage-13 - Stage-7 depends on stages: Stage-1, Stage-8, Stage-9 , consists of Stage-11, Stage-6, Stage-2 - Stage-11 has a backup stage: Stage-2 - Stage-5 depends on stages: Stage-11 - Stage-6 has a backup stage: Stage-2 + Stage-7 depends on stages: Stage-1, Stage-8, Stage-9 , consists of Stage-5, Stage-12, Stage-2 + Stage-5 has a backup stage: Stage-2 + Stage-12 has a backup stage: Stage-2 + Stage-6 depends on stages: Stage-12 Stage-2 Stage-14 has a backup stage: Stage-1 Stage-9 depends on stages: Stage-14 @@ -605,22 +655,25 @@ STAGE PLANS: Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: - b + $hdt$_0:$hdt$_1:$hdt$_2:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - b + $hdt$_0:$hdt$_1:$hdt$_2:a TableScan - alias: b + alias: a Filter Operator - predicate: (key > 100) (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-8 Map Reduce @@ -628,50 +681,100 @@ STAGE PLANS: TableScan alias: a Filter Operator - predicate: ((key is not null and value is not null) and (key > 100)) (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) + Select Operator + expressions: key (type: string), value (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 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (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 Local Work: Map Reduce Local Work Stage: Stage-7 Conditional Operator - Stage: Stage-11 + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + alias: a + Filter Operator + predicate: value is not null (type: boolean) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} {_col1} + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1, _col2 + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Limit + Number of rows: 40 + 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 + Local Work: + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_0:$INTNAME + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_0:$INTNAME + TableScan + + Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: - c + $hdt$_0:$hdt$_0:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - c + $hdt$_0:$hdt$_0:a TableScan - alias: c + alias: a Filter Operator predicate: value is not null (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {_col0} {_col1} - 1 - keys: - 0 _col1 (type: string) - 1 value (type: string) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + HashTable Sink Operator + condition expressions: + 0 + 1 {_col0} {_col1} + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -679,14 +782,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} {_col1} - 1 + 0 + 1 {_col0} {_col1} keys: - 0 _col1 (type: string) - 1 value (type: string) - outputColumnNames: _col0, _col1 + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1, _col2 Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 Limit Number of rows: 40 @@ -699,44 +802,6 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: c - Filter Operator - predicate: value is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} {_col1} - 1 - keys: - 0 _col1 (type: string) - 1 value (type: string) - outputColumnNames: _col0, _col1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Limit - Number of rows: 40 - 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 - Local Work: - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME - TableScan - Stage: Stage-2 Map Reduce Map Operator Tree: @@ -748,27 +813,31 @@ STAGE PLANS: Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan - alias: c + 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 - Reduce Output Operator - key expressions: value (type: string) - sort order: + - Map-reduce partition columns: value (type: string) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 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: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col0} {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {VALUE._col0} {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit @@ -785,46 +854,55 @@ STAGE PLANS: Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - a + $hdt$_0:$hdt$_1:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - a + $hdt$_0:$hdt$_1:$hdt$_1:a TableScan alias: a Filter Operator - predicate: ((key is not null and value is not null) and (key > 100)) (type: boolean) - HashTable Sink Operator - condition expressions: - 0 {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-9 Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Filter Operator - predicate: (key > 100) (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (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 + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (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 Local Work: Map Reduce Local Work @@ -832,28 +910,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 100) (type: boolean) + predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 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: _col0 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 TableScan alias: a 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) and (key > 100)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 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: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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 + 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 + 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 + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -863,12 +949,16 @@ STAGE PLANS: 1 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 + Select Operator + expressions: _col0 (type: string), _col1 (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 Stage: Stage-0 Fetch Operator @@ -888,8 +978,8 @@ RUN: Stage-10:CONDITIONAL RUN: Stage-14:MAPREDLOCAL RUN: Stage-9:MAPRED RUN: Stage-7:CONDITIONAL -RUN: Stage-11:MAPREDLOCAL -RUN: Stage-5:MAPRED +RUN: Stage-12:MAPREDLOCAL +RUN: Stage-6:MAPRED 238 val_238 238 val_238 238 val_238 @@ -948,7 +1038,7 @@ RUN: Stage-10:CONDITIONAL RUN: Stage-14:MAPREDLOCAL RUN: Stage-1:MAPRED RUN: Stage-7:CONDITIONAL -RUN: Stage-11:MAPREDLOCAL +RUN: Stage-12:MAPREDLOCAL RUN: Stage-2:MAPRED 103 val_103 103 val_103 diff --git ql/src/test/results/clientpositive/binarysortable_1.q.out ql/src/test/results/clientpositive/binarysortable_1.q.out index e486466..c4ba7e0 100644 --- ql/src/test/results/clientpositive/binarysortable_1.q.out +++ ql/src/test/results/clientpositive/binarysortable_1.q.out @@ -49,11 +49,11 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 93 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 93 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: sum(value) - keys: key (type: string) + aggregations: sum(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE diff --git ql/src/test/results/clientpositive/bucket_groupby.q.out ql/src/test/results/clientpositive/bucket_groupby.q.out index 2f04051..feb5ac8 100644 --- ql/src/test/results/clientpositive/bucket_groupby.q.out +++ 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -167,12 +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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -250,12 +250,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: length(key) (type: int), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: length(key) (type: int) + aggregations: count(_col1) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -324,12 +324,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: abs(length(key)) (type: int), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: abs(length(key)) (type: int) + aggregations: count(_col1) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -400,12 +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: key + expressions: key (type: string), 3 (type: int), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string), 3 (type: int) + aggregations: count(_col2) + keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -483,11 +483,11 @@ 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -564,12 +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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -943,12 +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: key + expressions: key (type: string), 3 (type: int), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string), 3 (type: int) + aggregations: count(_col2) + keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -1055,13 +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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1137,12 +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: value + expressions: value (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: value (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1218,13 +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: key, value + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col2) bucketGroup: true - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1352,13 +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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1434,12 +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: value, key + expressions: value (type: string), key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: value (type: string), key (type: string) + aggregations: count(_col2) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/combine2.q.out ql/src/test/results/clientpositive/combine2.q.out index 921dd90..dfff5f8 100644 --- ql/src/test/results/clientpositive/combine2.q.out +++ ql/src/test/results/clientpositive/combine2.q.out @@ -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: _col0 Statistics: Num rows: 12 Data size: 14 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -564,14 +566,14 @@ STAGE PLANS: name: default.combine2 name: default.combine2 Truncated Path -> Alias: - /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] + /combine2/value=2010-04-21 09%3A45%3A00 [$hdt$_0:$hdt$_0:combine2] + /combine2/value=val_0 [$hdt$_0:$hdt$_0:combine2] + /combine2/value=val_2 [$hdt$_0:$hdt$_0:combine2] + /combine2/value=val_4 [$hdt$_0:$hdt$_0:combine2] + /combine2/value=val_5 [$hdt$_0:$hdt$_0:combine2] + /combine2/value=val_8 [$hdt$_0:$hdt$_0:combine2] + /combine2/value=val_9 [$hdt$_0:$hdt$_0:combine2] + /combine2/value=| [$hdt$_0:$hdt$_0:combine2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -654,12 +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: ds + expressions: ds (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: ds (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out index 317a642..5586e36 100644 --- ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out +++ ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out @@ -1,8 +1,12 @@ -Warning: Shuffle Join JOIN[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain extended +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +PREHOOK: query: -- SORT_QUERY_RESULTS + +explain extended 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 -POSTHOOK: query: explain extended +POSTHOOK: query: -- SORT_QUERY_RESULTS + +explain extended 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 POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: @@ -83,22 +87,30 @@ STAGE PLANS: isSamplingPred: false predicate: (key = '429') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: value (type: string) + outputColumnNames: _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false TableScan alias: b Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator - sort order: + 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 - tag: 1 - value expressions: key (type: string), value (type: string) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col0 (type: string), _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -191,20 +203,20 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src [c:a] - /src1 [c:b] + /src [$hdt$_0:$hdt$_1:a] + /src1 [$hdt$_0:$hdt$_0:b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col1} - 1 {VALUE._col0} {VALUE._col1} - outputColumnNames: _col1, _col5, _col6 + 0 {VALUE._col0} {VALUE._col1} + 1 {VALUE._col1} + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '429' (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: '429' (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -235,7 +247,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] 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 @@ -249,50 +261,50 @@ POSTHOOK: Input: default@src1 429 val_429 429 val_429 429 val_429 -429 val_429 406 val_406 -429 val_429 146 val_146 -429 val_429 213 val_213 -429 val_429 128 -429 val_429 66 val_66 -429 val_429 369 -429 val_429 224 -429 val_429 273 val_273 -429 val_429 150 val_150 -429 val_429 401 val_401 -429 val_429 val_193 -429 val_429 val_265 -429 val_429 val_484 -429 val_429 98 val_98 -429 val_429 278 val_278 -429 val_429 255 val_255 -429 val_429 val_409 -429 val_429 val_165 -429 val_429 val_27 -429 val_429 311 val_311 429 val_429 -429 val_429 238 val_238 429 val_429 429 val_429 429 val_429 -429 val_429 406 val_406 +429 val_429 +429 val_429 val_165 +429 val_429 val_165 +429 val_429 val_193 +429 val_429 val_193 +429 val_429 val_265 +429 val_429 val_265 +429 val_429 val_27 +429 val_429 val_27 +429 val_429 val_409 +429 val_429 val_409 +429 val_429 val_484 +429 val_429 val_484 +429 val_429 128 +429 val_429 128 +429 val_429 146 val_146 429 val_429 146 val_146 +429 val_429 150 val_150 +429 val_429 150 val_150 429 val_429 213 val_213 -429 val_429 128 -429 val_429 66 val_66 -429 val_429 369 +429 val_429 213 val_213 +429 val_429 224 429 val_429 224 +429 val_429 238 val_238 +429 val_429 238 val_238 +429 val_429 255 val_255 +429 val_429 255 val_255 +429 val_429 273 val_273 429 val_429 273 val_273 -429 val_429 150 val_150 -429 val_429 401 val_401 -429 val_429 val_193 -429 val_429 val_265 -429 val_429 val_484 -429 val_429 98 val_98 429 val_429 278 val_278 -429 val_429 255 val_255 -429 val_429 val_409 -429 val_429 val_165 -429 val_429 val_27 +429 val_429 278 val_278 429 val_429 311 val_311 -429 val_429 -429 val_429 238 val_238 +429 val_429 311 val_311 +429 val_429 369 +429 val_429 369 +429 val_429 401 val_401 +429 val_429 401 val_401 +429 val_429 406 val_406 +429 val_429 406 val_406 +429 val_429 66 val_66 +429 val_429 66 val_66 +429 val_429 98 val_98 +429 val_429 98 val_98 diff --git ql/src/test/results/clientpositive/constprog2.q.out ql/src/test/results/clientpositive/constprog2.q.out index 71a44f3..245a51f 100644 --- ql/src/test/results/clientpositive/constprog2.q.out +++ ql/src/test/results/clientpositive/constprog2.q.out @@ -1,8 +1,14 @@ -PREHOOK: query: EXPLAIN +PREHOOK: query: -- Some constant propagation does not work in CBO due to added casts(?), disable for now. + + +EXPLAIN SELECT src1.key, src1.key + 1, src2.value FROM src src1 join src src2 ON src1.key = src2.key AND src1.key = 86 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN +POSTHOOK: query: -- Some constant propagation does not work in CBO due to added casts(?), disable for now. + + +EXPLAIN SELECT src1.key, src1.key + 1, src2.value FROM src src1 join src src2 ON src1.key = src2.key AND src1.key = 86 POSTHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/correlationoptimizer1.q.out ql/src/test/results/clientpositive/correlationoptimizer1.q.out index 53fd47c..454dc74 100644 --- ql/src/test/results/clientpositive/correlationoptimizer1.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer1.q.out @@ -31,42 +31,50 @@ STAGE PLANS: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -96,11 +104,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -182,27 +190,35 @@ STAGE PLANS: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 Reduce Operator Tree: Demux Operator Statistics: Num rows: 263 Data size: 2755 Basic stats: COMPLETE Column stats: NONE @@ -210,28 +226,28 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -321,24 +337,28 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - tmp:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -349,33 +369,37 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 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 + Select Operator + expressions: _col1 (type: string), 1 (type: int) 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) + Group By Operator + aggregations: count(_col1) + 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: @@ -386,11 +410,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -484,11 +508,15 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -497,10 +525,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -519,11 +547,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -553,11 +581,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -644,11 +672,15 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -657,10 +689,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -681,23 +713,23 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -786,36 +818,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -845,11 +885,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -931,50 +971,58 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1063,37 +1111,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Right Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1122,11 +1178,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1209,37 +1265,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Right Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1268,11 +1332,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1358,37 +1422,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 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: 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 - 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: _col0, _col1 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + TableScan + alias: y + 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), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey1} - outputColumnNames: _col0, _col6 + 0 {KEY.reducesinkkey1} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col6 + expressions: _col2 (type: string), _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col6 (type: string) + aggregations: count(_col2) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1484,37 +1556,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 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: 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 - 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: _col0, _col1 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + TableScan + alias: y + 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), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey1} - outputColumnNames: _col0, _col6 + 0 {KEY.reducesinkkey1} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col6 + expressions: _col2 (type: string), _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col6 (type: string) + aggregations: count(_col2) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1619,37 +1699,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Left Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1678,11 +1766,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1764,50 +1852,58 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Left Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1896,36 +1992,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Left Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1955,11 +2059,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2042,36 +2146,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 + Left Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2101,11 +2213,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2196,36 +2308,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2255,11 +2375,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2342,36 +2462,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2401,11 +2529,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2490,43 +2618,51 @@ STAGE PLANS: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 + 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: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 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: _col1 (type: string), _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2556,11 +2692,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -2643,43 +2779,51 @@ STAGE PLANS: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 + 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: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 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: _col1 (type: string), _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2709,11 +2853,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -2798,42 +2942,50 @@ STAGE PLANS: 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 and value is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 53 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: 53 Basic stats: COMPLETE Column stats: NONE - TableScan alias: 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: 125 Data size: 1328 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 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: 125 Data size: 1328 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 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: 7 Data size: 53 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: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2863,11 +3015,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2950,42 +3102,50 @@ STAGE PLANS: 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 and value is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 53 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: 53 Basic stats: COMPLETE Column stats: NONE - TableScan alias: 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: 125 Data size: 1328 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 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: 125 Data size: 1328 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 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: 7 Data size: 53 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: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -3015,11 +3175,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/correlationoptimizer10.q.out ql/src/test/results/clientpositive/correlationoptimizer10.q.out index 6e7904a..8346027 100644 --- ql/src/test/results/clientpositive/correlationoptimizer10.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer10.q.out @@ -48,22 +48,30 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 Reduce Operator Tree: Join Operator condition map: @@ -74,11 +82,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -129,10 +137,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -239,10 +247,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -257,22 +265,30 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 Reduce Operator Tree: Demux Operator Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE @@ -285,13 +301,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: bigint) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -432,24 +448,32 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and (key > 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 20) and (key < 200)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -458,16 +482,16 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} 1 outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + 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: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -483,19 +507,23 @@ STAGE PLANS: 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 + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE TableScan 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: 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) + 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 - value expressions: value (type: string) + 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: string) Reduce Operator Tree: Join Operator condition map: @@ -504,14 +532,14 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33 Data size: 358 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: 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 @@ -589,41 +617,53 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and (key > 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 20) and (key < 200)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE TableScan 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: 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) + 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 - value expressions: value (type: string) + 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: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 123 Data size: 1267 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 693 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 123 Data size: 1267 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 693 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Left Semi Join 0 to 1 @@ -656,7 +696,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator - Statistics: Num rows: 123 Data size: 1267 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 693 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Left Semi Join 0 to 1 @@ -753,27 +793,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and (key > 180)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: xx Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and (key > 180)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -782,16 +830,16 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} 1 outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + 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: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -807,19 +855,23 @@ STAGE PLANS: 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 + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE TableScan alias: xx 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Join Operator condition map: @@ -922,44 +974,56 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and (key > 180)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: xx Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and (key > 180)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE TableScan alias: xx 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: 360 Data size: 3824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 306 Data size: 3250 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 360 Data size: 3824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 306 Data size: 3250 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Left Semi Join 0 to 1 @@ -992,7 +1056,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator - Statistics: Num rows: 360 Data size: 3824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 306 Data size: 3250 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Left Semi Join 0 to 1 diff --git ql/src/test/results/clientpositive/correlationoptimizer12.q.out ql/src/test/results/clientpositive/correlationoptimizer12.q.out index 0d95e4a..a07ec03 100644 --- ql/src/test/results/clientpositive/correlationoptimizer12.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer12.q.out @@ -27,12 +27,16 @@ STAGE PLANS: TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), key (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + 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 - value expressions: key (type: string), value (type: string) + Reduce Output Operator + key expressions: _col0 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -96,12 +100,16 @@ STAGE PLANS: TableScan alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), key (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + 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 - value expressions: key (type: string), value (type: string) + Reduce Output Operator + key expressions: _col0 (type: string), _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: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/correlationoptimizer15.q.out ql/src/test/results/clientpositive/correlationoptimizer15.q.out index 5186873..96407dd 100644 --- ql/src/test/results/clientpositive/correlationoptimizer15.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer15.q.out @@ -23,14 +23,14 @@ JOIN src yy ON xx.key=yy.key ORDER BY xx.key, xx.cnt, 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-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-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-4 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan @@ -39,22 +39,30 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 Reduce Operator Tree: Join Operator condition map: @@ -65,11 +73,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -81,7 +89,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-4 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -109,38 +117,42 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: yy - 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 - 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 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 + 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 + 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) + expressions: _col1 (type: string), _col2 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -150,7 +162,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -255,41 +267,74 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: yy - 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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: yy + 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 + 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 + Mux Operator + Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col2 (type: bigint), _col0 (type: string) + 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 Join Operator condition map: Inner Join 0 to 1 @@ -299,13 +344,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -320,12 +365,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) + expressions: _col1 (type: string), _col2 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -335,27 +380,6 @@ 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 - Mux Operator - Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) - 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 Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/correlationoptimizer2.q.out ql/src/test/results/clientpositive/correlationoptimizer2.q.out index 7073a30..17ab17f 100644 --- ql/src/test/results/clientpositive/correlationoptimizer2.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer2.q.out @@ -43,11 +43,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + 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 @@ -102,11 +102,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -154,11 +154,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -242,11 +242,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + 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 @@ -264,11 +264,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -302,11 +302,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -337,11 +337,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -435,11 +435,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -494,11 +494,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -543,11 +543,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -628,11 +628,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -647,11 +647,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -685,11 +685,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -720,11 +720,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -818,11 +818,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -877,11 +877,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -926,11 +926,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1011,11 +1011,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1030,11 +1030,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1068,11 +1068,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -1103,11 +1103,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -1201,11 +1201,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1260,11 +1260,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -1309,11 +1309,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1394,11 +1394,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1413,11 +1413,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1451,11 +1451,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -1486,11 +1486,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -1584,27 +1584,24 @@ STAGE PLANS: alias: y 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 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 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 + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -1642,11 +1639,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1676,11 +1673,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1724,27 +1721,24 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 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: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -1820,48 +1814,43 @@ STAGE PLANS: alias: y 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 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 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 Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 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: bigint) Reduce Operator Tree: Demux Operator Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -1878,11 +1867,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1894,10 +1883,9 @@ STAGE PLANS: 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: _col0 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -1914,11 +1902,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1948,11 +1936,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2050,38 +2038,49 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: z + 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: key, value + outputColumnNames: _col0, _col1 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 + 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 - 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) + value expressions: _col1 (type: string) + TableScan + alias: 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 + 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: - 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 + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2097,15 +2096,15 @@ STAGE PLANS: 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 - value expressions: _col1 (type: bigint) + 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator condition map: @@ -2116,11 +2115,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + 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 Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -2166,36 +2165,33 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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 - value expressions: value (type: string) - TableScan - alias: 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 - 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 + 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: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 + Group By Operator + 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 + Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2252,18 +2248,34 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: z + 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: key, value + 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: string) + 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(value) - keys: key (type: string) + 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 @@ -2274,28 +2286,20 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 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: key is not null (type: boolean) - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 @@ -2303,12 +2307,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + 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 @@ -2322,11 +2326,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 @@ -2357,11 +2361,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)), sum(hash(_col3)) + 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 diff --git ql/src/test/results/clientpositive/correlationoptimizer3.q.out ql/src/test/results/clientpositive/correlationoptimizer3.q.out index ccd18c4..8a7cf71 100644 --- ql/src/test/results/clientpositive/correlationoptimizer3.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer3.q.out @@ -29,9 +29,9 @@ 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-3 depends on stages: Stage-2, Stage-5 Stage-4 depends on stages: Stage-3 - Stage-6 is a root stage + Stage-5 is a root stage Stage-0 depends on stages: Stage-4 STAGE PLANS: @@ -39,42 +39,50 @@ STAGE PLANS: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -141,11 +149,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -182,43 +190,51 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: 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 - 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: 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 - 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: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: string) + TableScan + alias: 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 + 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + 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 @@ -277,50 +293,66 @@ STAGE PLANS: 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 - 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: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 + 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: string) + 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 Reduce Operator Tree: Demux Operator Statistics: Num rows: 526 Data size: 5510 Basic stats: COMPLETE Column stats: NONE @@ -328,18 +360,55 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {VALUE._col0} + 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 + condition expressions: + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -359,11 +428,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -373,43 +442,6 @@ 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 - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - 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 - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_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-2 Map Reduce @@ -488,41 +520,49 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - tmp:b:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x Fetch Operator limit: -1 - tmp:d:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp:b:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) - tmp:d:x + 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 + condition expressions: + 0 + 1 {_col1} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2: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 - HashTable Sink Operator - condition expressions: - 0 {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -533,65 +573,98 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 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 + Select Operator + expressions: _col1 (type: string), 1 (type: int) 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) + Group By Operator + aggregations: count(_col1) + 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) TableScan alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1 - 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} {_col1} + 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 - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + 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 - 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Local Work: Map Reduce Local Work Reduce Operator Tree: Demux Operator Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 825 Data size: 8763 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {VALUE._col0} + 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) @@ -613,11 +686,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -627,31 +700,6 @@ 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 - Mux Operator - Statistics: Num rows: 825 Data size: 8763 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_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 @@ -720,52 +768,93 @@ FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value 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-2 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-2, Stage-5 + Stage-4 depends on stages: Stage-3 Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-4 STAGE PLANS: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), 1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + 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 + + 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: _col0, _col1 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -773,7 +862,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -781,15 +870,15 @@ 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 - value expressions: _col1 (type: string) + Statistics: Num rows: 137 Data size: 1455 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: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -800,11 +889,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: bigint), _col1 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -815,7 +904,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -845,74 +934,49 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: 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 - 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: 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 - 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: _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: string) + TableScan + alias: 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 + 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (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 - File Output Operator - compressed: false - table: - input format: 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 - 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: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -969,50 +1033,66 @@ STAGE PLANS: 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 - 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: 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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 + 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: string) + 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 Reduce Operator Tree: Demux Operator Statistics: Num rows: 526 Data size: 5510 Basic stats: COMPLETE Column stats: NONE @@ -1020,12 +1100,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + 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 @@ -1039,11 +1119,11 @@ STAGE PLANS: 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: bigint), _col1 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -1057,18 +1137,18 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -1088,11 +1168,11 @@ STAGE PLANS: 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: bigint), _col1 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -1180,41 +1260,49 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - tmp:b:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x Fetch Operator limit: -1 - tmp:d:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp:b:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1: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 - HashTable Sink Operator - condition expressions: - 0 {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - tmp:d:x + 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 + condition expressions: + 0 + 1 {_col1} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -1225,52 +1313,60 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1 - 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 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _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) + Select Operator + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Group By Operator + aggregations: count(_col1) + 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) TableScan alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} {_col1} + 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 - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash + 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 @@ -1278,7 +1374,7 @@ STAGE PLANS: 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) + value expressions: _col1 (type: string) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1295,11 +1391,11 @@ STAGE PLANS: 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: bigint), _col1 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -1330,11 +1426,11 @@ STAGE PLANS: 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: bigint), _col1 (type: string) + 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(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 diff --git ql/src/test/results/clientpositive/correlationoptimizer6.q.out ql/src/test/results/clientpositive/correlationoptimizer6.q.out index e1c46db..007b883 100644 --- ql/src/test/results/clientpositive/correlationoptimizer6.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer6.q.out @@ -38,26 +38,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 - 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 + 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: 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 Filter Operator 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: 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 + 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 Reduce Operator Tree: Join Operator condition map: @@ -66,17 +74,17 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} 1 outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -92,7 +100,7 @@ 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: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -100,11 +108,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -120,14 +128,14 @@ STAGE PLANS: 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: 7 Data size: 54 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: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -139,7 +147,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + expressions: _col2 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -155,26 +163,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + 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 - 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 + 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 + 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 TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + 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: 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 + 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 + 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: @@ -183,17 +199,17 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} 1 outputColumnNames: _col0 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -209,7 +225,7 @@ 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -217,11 +233,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE 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 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -296,48 +312,64 @@ STAGE PLANS: Map Operator Tree: 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 - 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 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 - 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 + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + 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: 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 + 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 + 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 + 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) + outputColumnNames: _col0 + 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: 526 Data size: 5510 Basic stats: COMPLETE Column stats: NONE @@ -350,13 +382,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -376,7 +408,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + expressions: _col2 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -395,13 +427,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -421,7 +453,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + expressions: _col2 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -500,111 +532,127 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - xx:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:x Fetch Operator limit: -1 - yy:x + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - xx:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:x TableScan alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + 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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) - yy:x + 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 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1:x TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) + 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 + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: 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 Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), 1 (type: int) 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) + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + 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) + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (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 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - 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) - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + 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) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -631,7 +679,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + expressions: _col2 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -662,7 +710,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + expressions: _col2 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -735,12 +783,12 @@ JOIN ON xx.key=yy.key 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 @@ -750,12 +798,12 @@ STAGE PLANS: 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 + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -783,38 +831,42 @@ 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 - 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 - value expressions: _col1 (type: bigint) - TableScan 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: 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) + 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col5, _col6 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: bigint) + expressions: _col2 (type: string), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -887,18 +939,33 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan + 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: 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: 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 + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -908,41 +975,9 @@ STAGE PLANS: 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) - TableScan - 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: 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: Demux Operator Statistics: Num rows: 263 Data size: 2755 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 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col5, _col6 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) @@ -959,12 +994,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col5, _col6 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: bigint) + expressions: _col2 (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 @@ -974,7 +1009,28 @@ 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 - + Mux Operator + Statistics: Num rows: 394 Data size: 4127 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col2 (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 + Stage: Stage-0 Fetch Operator limit: -1 @@ -1035,13 +1091,13 @@ JOIN ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 + Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -1050,22 +1106,30 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan - alias: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: @@ -1076,11 +1140,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1092,7 +1156,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -1120,38 +1184,42 @@ 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 - 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: bigint) - TableScan 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: 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) + 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: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col5, _col6 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: bigint) + expressions: _col2 (type: string), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1224,62 +1292,53 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan + 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: 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan - alias: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 - Filter Operator - predicate: key is not null (type: boolean) - 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 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: 513 Data size: 5411 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 513 Data size: 5411 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col5, _col6 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (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 Join Operator condition map: Inner Join 0 to 1 @@ -1289,13 +1348,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -1310,12 +1369,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col5, _col6 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: bigint) + expressions: _col2 (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 @@ -1325,6 +1384,27 @@ 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 + Mux Operator + Statistics: Num rows: 513 Data size: 5411 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col2 (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 Stage: Stage-0 Fetch Operator @@ -1386,13 +1466,13 @@ JOIN src yy ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-3 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan @@ -1401,22 +1481,30 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 Reduce Operator Tree: Join Operator condition map: @@ -1427,11 +1515,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1443,7 +1531,7 @@ 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 @@ -1471,38 +1559,42 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: yy - 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 - 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 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 + 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 + 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) + expressions: _col1 (type: string), _col2 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1597,41 +1689,74 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: yy - 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 - 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: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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: yy + 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 + 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 + Mux Operator + Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col2 (type: bigint), _col0 (type: string) + 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 Join Operator condition map: Inner Join 0 to 1 @@ -1641,13 +1766,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -1662,12 +1787,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) + expressions: _col1 (type: string), _col2 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -1677,27 +1802,6 @@ 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 - Mux Operator - Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) - 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 Stage: Stage-0 Fetch Operator @@ -1783,37 +1887,46 @@ JOIN ON zz.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-1 + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-2, Stage-4 + Stage-4 is a root stage + Stage-0 depends on stages: Stage-3 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan - alias: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: @@ -1824,11 +1937,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1840,7 +1953,7 @@ 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 @@ -1868,21 +1981,10 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - 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 - 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 Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -1890,38 +1992,85 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 1455 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: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + 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 + + Stage: Stage-4 + Map Reduce + Map Operator Tree: + TableScan + 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 + 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 + TableScan 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: 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) + 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 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 condition expressions: 0 {KEY.reducesinkkey0} - 1 - 2 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col10, _col11 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col10 (type: string), _col11 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + 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: 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 + input format: 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 @@ -2022,70 +2171,63 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan - alias: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan 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: 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) + 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 Reduce Operator Tree: Demux Operator Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 1526 Data size: 16134 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 - 2 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col10, _col11 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col10 (type: string), _col11 (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 Join Operator condition map: Inner Join 0 to 1 @@ -2095,13 +2237,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -2111,19 +2253,17 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator - Statistics: Num rows: 1526 Data size: 16134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - 2 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col10, _col11 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col10 (type: string), _col11 (type: bigint) + 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 @@ -2133,6 +2273,39 @@ 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 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + 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 + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col1, _col3 + 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 Stage: Stage-0 Fetch Operator @@ -2220,13 +2393,14 @@ ON xx.key=yy.key JOIN src zz ON yy.key=zz.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-1 + 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-2 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -2235,22 +2409,30 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan - alias: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: @@ -2261,11 +2443,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2277,7 +2459,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -2309,16 +2491,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: zz + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan Reduce Output Operator key expressions: _col0 (type: string) @@ -2326,35 +2512,63 @@ STAGE PLANS: 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) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + 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) TableScan 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: 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) + 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 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - 2 - outputColumnNames: _col0, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: bigint) + expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 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: 550 Data size: 5843 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 @@ -2448,75 +2662,68 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: zz + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan - alias: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan 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: 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) + 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 Reduce Operator Tree: Demux Operator Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 1526 Data size: 16134 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - 2 - outputColumnNames: _col0, _col5, _col6 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (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 Join Operator condition map: Inner Join 0 to 1 @@ -2526,13 +2733,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -2542,28 +2749,88 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator - Statistics: Num rows: 1526 Data size: 16134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - 2 - outputColumnNames: _col0, _col5, _col6 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Mux Operator + Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _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: _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 + Mux Operator + Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Mux Operator + Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col3 + 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 + Mux Operator + Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col3 + 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 Stage: Stage-0 Fetch Operator @@ -2672,11 +2939,11 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -2732,10 +2999,10 @@ STAGE PLANS: 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, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col3) + aggregations: sum(_col1), sum(_col2) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2786,28 +3053,32 @@ STAGE PLANS: Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) TableScan - alias: z + 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 1 {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col4 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), _col3 (type: string), _col4 (type: string) + 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2829,11 +3100,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -2960,11 +3231,11 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -2975,17 +3246,21 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: z + 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2994,11 +3269,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -3033,12 +3308,12 @@ STAGE PLANS: 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, _col3 + outputColumnNames: _col0, _col1, _col2 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: sum(_col1), sum(_col3) + aggregations: sum(_col1), sum(_col2) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 @@ -3054,11 +3329,11 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 1 {VALUE._col0} + 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), _col3 (type: string), _col4 (type: string) + 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 @@ -3090,12 +3365,12 @@ STAGE PLANS: 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, _col3 + outputColumnNames: _col0, _col1, _col2 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: sum(_col1), sum(_col3) + aggregations: sum(_col1), sum(_col2) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 @@ -3111,11 +3386,11 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 1 {VALUE._col0} + 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), _col3 (type: string), _col4 (type: string) + 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 @@ -3132,11 +3407,11 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 1 {VALUE._col0} + 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), _col3 (type: string), _col4 (type: string) + 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 @@ -3251,46 +3526,53 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 - 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) + 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: 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 Filter Operator 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: 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 + 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 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} + 0 {KEY.reducesinkkey0} 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col0 (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3303,22 +3585,22 @@ STAGE PLANS: Map Operator Tree: TableScan 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) + 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) 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: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE 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 + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3334,26 +3616,26 @@ STAGE PLANS: 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) + Statistics: Num rows: 7 Data size: 54 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: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + expressions: _col3 (type: string), _col4 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3389,45 +3671,54 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + 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 - 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 + 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) TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + 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: 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 + 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 + 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} + 0 {KEY.reducesinkkey0} {VALUE._col0} 1 - outputColumnNames: _col0 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + expressions: _col0 (type: string), _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 + 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(_col2) + keys: _col0 (type: string), _col1 (type: string) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3440,22 +3731,22 @@ STAGE PLANS: 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) + 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) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE 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 + 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 File Output Operator compressed: false table: @@ -3521,13 +3812,13 @@ JOIN ON xx.key=yy.key 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-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -3536,23 +3827,31 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 - value expressions: value (type: string) + 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) TableScan - alias: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: @@ -3563,11 +3862,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 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: _col0 (type: string), _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -3579,7 +3878,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -3607,41 +3906,70 @@ 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 - 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) - 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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: y + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 + Mux Operator + Statistics: Num rows: 163 Data size: 1653 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col3 (type: string), _col4 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + 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 Join Operator condition map: Inner Join 0 to 1 @@ -3651,13 +3979,13 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) + aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -3672,12 +4000,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3, _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: string), _col3 (type: string), _col4 (type: bigint) + expressions: _col3 (type: string), _col4 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -3687,27 +4015,6 @@ 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 - Mux Operator - Statistics: Num rows: 163 Data size: 1653 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col2, _col3, _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: string), _col3 (type: string), _col4 (type: bigint) - 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 @@ -3768,70 +4075,78 @@ ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-10 is a root stage - Stage-2 depends on stages: Stage-10 - Stage-9 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-9 - Stage-0 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-10 + Stage-9 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-9 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - yy:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - yy:x + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:x 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 - HashTable Sink Operator - condition expressions: - 0 {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + 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 + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-2 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: y + 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 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 - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 1 (type: int) outputColumnNames: _col0, _col1, _col2 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(_col2) + keys: _col0 (type: string), _col1 (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: @@ -3855,26 +4170,30 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - xx:x + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - xx:x + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -3885,43 +4204,68 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: bigint) TableScan - alias: y + 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (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 + Select Operator + expressions: _col0 (type: string), 1 (type: int) outputColumnNames: _col0, _col1 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(_col1) + keys: _col0 (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: Demux Operator Statistics: Num rows: 151 Data size: 1563 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 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col3 (type: string), _col4 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + 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 Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) @@ -3938,12 +4282,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3, _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: string), _col3 (type: string), _col4 (type: bigint) + expressions: _col3 (type: string), _col4 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -3953,27 +4297,6 @@ 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 - Mux Operator - Statistics: Num rows: 226 Data size: 2339 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col2, _col3, _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: string), _col3 (type: string), _col4 (type: bigint) - 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 diff --git ql/src/test/results/clientpositive/correlationoptimizer7.q.out ql/src/test/results/clientpositive/correlationoptimizer7.q.out index 17649e6..508b67f 100644 --- ql/src/test/results/clientpositive/correlationoptimizer7.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer7.q.out @@ -19,36 +19,40 @@ JOIN src1 yy ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-3 depends on stages: Stage-8 - Stage-7 depends on stages: Stage-3 - Stage-5 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-5 + Stage-9 is a root stage + Stage-2 depends on stages: Stage-9 + Stage-8 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-8 + Stage-0 depends on stages: Stage-6 STAGE PLANS: - Stage: Stage-8 + Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -57,33 +61,37 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), 1 (type: int) 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) + Group By Operator + aggregations: count(_col1) + 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: @@ -104,29 +112,33 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-7 + Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - yy + $hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - yy + $hdt$_0:$hdt$_1:y TableScan - alias: yy + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {_col0} {_col1} - 1 {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) + 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 + condition expressions: + 0 {_col0} {_col1} + 1 {_col1} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -135,10 +147,10 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {_col0} {_col1} - 1 {key} {value} + 1 {_col0} {_col1} keys: 0 _col0 (type: string) - 1 key (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -213,81 +225,93 @@ JOIN src1 yy ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-5 is a root stage - Stage-1 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-1 + Stage-6 is a root stage + Stage-2 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-5 + Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: yy + alias: 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 - 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: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: string) 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), 1 (type: int) 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) + Group By Operator + aggregations: count(_col1) + 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: @@ -416,36 +440,40 @@ JOIN src1 yy ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-3 depends on stages: Stage-8 - Stage-7 depends on stages: Stage-3 - Stage-5 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-5 + Stage-9 is a root stage + Stage-2 depends on stages: Stage-9 + Stage-8 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-8 + Stage-0 depends on stages: Stage-6 STAGE PLANS: - Stage: Stage-8 + Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -454,33 +482,37 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), 1 (type: int) 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) + Group By Operator + aggregations: count(_col1) + 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: @@ -501,29 +533,33 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-7 + Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - yy + $hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - yy + $hdt$_0:$hdt$_1:y TableScan - alias: yy + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {_col0} {_col1} - 1 {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) + 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 + condition expressions: + 0 {_col0} {_col1} + 1 {_col1} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -532,10 +568,10 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {_col0} {_col1} - 1 {key} {value} + 1 {_col0} {_col1} keys: 0 _col0 (type: string) - 1 key (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -610,81 +646,93 @@ JOIN src1 yy ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-5 is a root stage - Stage-1 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-1 + Stage-6 is a root stage + Stage-2 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-5 + Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - xx:y + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: yy + alias: 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 - 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: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: string) 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), 1 (type: int) 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) + Group By Operator + aggregations: count(_col1) + 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 ql/src/test/results/clientpositive/count.q.out ql/src/test/results/clientpositive/count.q.out index 9618367..f69ed72 100644 --- ql/src/test/results/clientpositive/count.q.out +++ ql/src/test/results/clientpositive/count.q.out @@ -46,11 +46,11 @@ 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: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) - keys: a (type: int), b (type: int), c (type: int) + aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) + keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -113,12 +113,12 @@ 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: a, b, c, d + expressions: 1 (type: int), a (type: int), b (type: int), c (type: int), d (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: 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) - keys: a (type: int), b (type: int), c (type: int), d (type: int) + aggregations: count(_col0), 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) 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 @@ -177,14 +177,14 @@ 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: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: a (type: int), b (type: int), c (type: int) + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ - Map-reduce partition columns: a (type: int) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: d (type: int) + value expressions: _col3 (type: int) Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col0) @@ -238,16 +238,17 @@ 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: a, b, c, d + expressions: 1 (type: int), a (type: int), b (type: int), c (type: int), d (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: a (type: int), b (type: int), c (type: int), d (type: int) + key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) 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(VALUE._col0), 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) mode: complete 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: 168 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/create_genericudaf.q.out ql/src/test/results/clientpositive/create_genericudaf.q.out index 0d4fa83..774e64f 100644 --- ql/src/test/results/clientpositive/create_genericudaf.q.out +++ 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: value (type: string) - outputColumnNames: value + expressions: 1 (type: int), substr(value, 5) (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: test_avg(1), test_avg(substr(value, 5)) + aggregations: test_avg(_col0), test_avg(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git ql/src/test/results/clientpositive/create_view.q.out ql/src/test/results/clientpositive/create_view.q.out index a028c62..2d8a3d2 100644 --- ql/src/test/results/clientpositive/create_view.q.out +++ ql/src/test/results/clientpositive/create_view.q.out @@ -192,7 +192,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 18) (type: boolean) + 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) diff --git ql/src/test/results/clientpositive/cross_join.q.out ql/src/test/results/clientpositive/cross_join.q.out index 654e105..af6c82c 100644 --- ql/src/test/results/clientpositive/cross_join.q.out +++ ql/src/test/results/clientpositive/cross_join.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[4][tables = [src, src2]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- current explain select src.key from src join src src2 PREHOOK: type: QUERY @@ -14,18 +14,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -53,7 +59,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[4][tables = [src, src2]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] 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 @@ -69,18 +75,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -123,27 +135,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 TableScan alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: diff --git ql/src/test/results/clientpositive/cross_product_check_1.q.out ql/src/test/results/clientpositive/cross_product_check_1.q.out index 87e356d..7f90dc2 100644 --- ql/src/test/results/clientpositive/cross_product_check_1.q.out +++ ql/src/test/results/clientpositive/cross_product_check_1.q.out @@ -24,7 +24,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Shuffle Join JOIN[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] 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 @@ -40,17 +40,25 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 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 - value expressions: key (type: string), value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -58,10 +66,10 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/cross_product_check_2.q.out ql/src/test/results/clientpositive/cross_product_check_2.q.out index 32d94a6..24c7812 100644 --- ql/src/test/results/clientpositive/cross_product_check_2.q.out +++ ql/src/test/results/clientpositive/cross_product_check_2.q.out @@ -24,7 +24,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Map Join MAPJOIN[7][bigTable=a] 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: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -38,21 +38,25 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - b + $hdt$_0:$hdt$_1:b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - b + $hdt$_0:$hdt$_1:b TableScan alias: b Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 {key} {value} - keys: - 0 - 1 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} {_col1} + keys: + 0 + 1 Stage: Stage-3 Map Reduce @@ -60,28 +64,32 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 {key} {value} - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + 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 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} {_col1} + keys: + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3 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), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 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 diff --git ql/src/test/results/clientpositive/decimal_precision.q.out ql/src/test/results/clientpositive/decimal_precision.q.out index 94c63cb..32b4e7a 100644 --- ql/src/test/results/clientpositive/decimal_precision.q.out +++ 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: dec + outputColumnNames: _col0 Statistics: Num rows: 23 Data size: 2661 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(dec), sum(dec) + aggregations: avg(_col0), sum(_col0) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/decimal_udf.q.out ql/src/test/results/clientpositive/decimal_udf.q.out index 6bd876a..859942a 100644 --- ql/src/test/results/clientpositive/decimal_udf.q.out +++ ql/src/test/results/clientpositive/decimal_udf.q.out @@ -109,7 +109,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key + value) (type: decimal(21,10)) + expressions: (key + CAST( value AS decimal(10,0))) (type: decimal(21,10)) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -176,7 +176,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key + (value / 2)) (type: double) + expressions: (UDFToDouble(key) + (UDFToDouble(value) / 2.0)) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -243,7 +243,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key + '1.0') (type: double) + expressions: (UDFToDouble(key) + 1.0) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -379,7 +379,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key - value) (type: decimal(21,10)) + expressions: (key - CAST( value AS decimal(10,0))) (type: decimal(21,10)) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -446,7 +446,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key - (value / 2)) (type: double) + expressions: (UDFToDouble(key) - (UDFToDouble(value) / 2.0)) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -513,7 +513,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key - '1.0') (type: double) + expressions: (UDFToDouble(key) - 1.0) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -649,7 +649,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key * value) > 0) (type: boolean) + predicate: ((key * CAST( value AS decimal(10,0))) > CAST( 0 AS decimal(31,10))) (type: boolean) Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)), value (type: int) @@ -704,7 +704,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key * value) (type: decimal(31,10)) + expressions: (key * CAST( value AS decimal(10,0))) (type: decimal(31,10)) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -771,7 +771,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key * (value / 2)) (type: double) + expressions: (UDFToDouble(key) * (UDFToDouble(value) / 2.0)) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -838,7 +838,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key * '2.0') (type: double) + expressions: (UDFToDouble(key) * 2.0) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -907,7 +907,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key / 0) (type: decimal(22,12)) + expressions: (key / CAST( 0 AS decimal(10,0))) (type: decimal(22,12)) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Limit @@ -940,7 +940,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key / null) (type: double) + expressions: (UDFToDouble(key) / UDFToDouble(null)) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Limit @@ -973,8 +973,13 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Filter Operator +<<<<<<< HEAD + predicate: (key is not null and (key <> CAST( 0 AS decimal(20,10)))) (type: boolean) + Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE +======= predicate: (key <> 0) (type: boolean) Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE +>>>>>>> trunk Select Operator expressions: (key / key) (type: decimal(38,24)) outputColumnNames: _col0 @@ -1042,7 +1047,7 @@ STAGE PLANS: predicate: (value <> 0) (type: boolean) Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key / value) (type: decimal(31,21)) + expressions: (key / CAST( value AS decimal(10,0))) (type: decimal(31,21)) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1098,7 +1103,7 @@ STAGE PLANS: predicate: (value <> 0) (type: boolean) Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key / (value / 2)) (type: double) + expressions: (UDFToDouble(key) / (UDFToDouble(value) / 2.0)) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1151,7 +1156,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (1 + (key / '2.0')) (type: double) + expressions: (1.0 + (UDFToDouble(key) / 2.0)) (type: double) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1291,11 +1296,11 @@ 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: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(key), count(key), avg(key) - keys: value (type: int) + aggregations: sum(_col1), count(_col1), avg(_col1) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -1313,7 +1318,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(38,23)), _col3 (type: decimal(24,14)), _col1 (type: decimal(30,10)) + 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 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1808,7 +1813,7 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ((key + 1) % (key / 2)) (type: decimal(22,12)) + expressions: ((key + CAST( 1 AS decimal(10,0))) % (key / CAST( 2 AS decimal(10,0)))) (type: decimal(22,12)) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1878,11 +1883,11 @@ 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: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev(key), variance(key) - keys: value (type: int) + aggregations: stddev(_col1), variance(_col1) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -1961,11 +1966,11 @@ 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: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(key), var_samp(key) - keys: value (type: int) + aggregations: stddev_samp(_col1), var_samp(_col1) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -2043,11 +2048,11 @@ 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: key + expressions: key (type: decimal(20,10)), 3 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: histogram_numeric(key, 3) + aggregations: histogram_numeric(_col0, _col1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -2107,10 +2112,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(key) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2170,10 +2175,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(key) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2233,10 +2238,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/decimal_udf2.q.out ql/src/test/results/clientpositive/decimal_udf2.q.out index d8511d6..3d0f5db 100644 --- ql/src/test/results/clientpositive/decimal_udf2.q.out +++ ql/src/test/results/clientpositive/decimal_udf2.q.out @@ -44,7 +44,7 @@ STAGE PLANS: alias: decimal_udf2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 10) (type: boolean) + predicate: (key = CAST( 10 AS decimal(20,10))) (type: boolean) Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: acos(key) (type: double), asin(key) (type: double), atan(key) (type: double), cos(key) (type: double), sin(key) (type: double), tan(key) (type: double), radians(key) (type: double) @@ -101,7 +101,7 @@ STAGE PLANS: alias: decimal_udf2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 10) (type: boolean) + predicate: (key = CAST( 10 AS decimal(20,10))) (type: boolean) Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: exp(key) (type: double), ln(key) (type: double), log(key) (type: double), log(key, key) (type: double), log(key, value) (type: double), log(value, key) (type: double), log10(key) (type: double), sqrt(key) (type: double) diff --git ql/src/test/results/clientpositive/distinct_stats.q.out ql/src/test/results/clientpositive/distinct_stats.q.out index be46e25..8612598 100644 --- ql/src/test/results/clientpositive/distinct_stats.q.out +++ 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: a, b + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT b) - keys: a (type: string), b (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -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: b + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: b (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -155,11 +155,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string) - outputColumnNames: a + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: a (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/explain_dependency.q.out ql/src/test/results/clientpositive/explain_dependency.q.out index b9a8ed8..9365bc9 100644 --- ql/src/test/results/clientpositive/explain_dependency.q.out +++ 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":[{"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]"}]} +{"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]"}]} PREHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V3 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V3 POSTHOOK: type: QUERY -{"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@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v3]"},{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v3]"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} +{"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@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v3]"},{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW","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":[{"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@v2","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"tablename":"default@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v4, default@v1]"},{"tablename":"default@v1","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} +{"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@v2","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"tablename":"default@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v4, default@v1]"},{"tablename":"default@v1","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"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 ql/src/test/results/clientpositive/explain_logical.q.out ql/src/test/results/clientpositive/explain_logical.q.out index 5a9cc2a..9931c4d 100644 --- ql/src/test/results/clientpositive/explain_logical.q.out +++ ql/src/test/results/clientpositive/explain_logical.q.out @@ -100,37 +100,37 @@ TOK_QUERY LOGICAL PLAN: -srcpart +$hdt$_0:$hdt$_0: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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_3) - aggregations: count(1) - keys: key (type: string) + Group By Operator (GBY_5) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_4) + Reduce Output Operator (RS_6) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Group By Operator (GBY_5) + Group By Operator (GBY_7) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_6) + Select Operator (SEL_8) expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_7) + File Output Operator (FS_9) compressed: false Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE table: @@ -184,37 +184,37 @@ TOK_QUERY LOGICAL PLAN: -subq1:src +$hdt$_0:$hdt$_0:src TableScan (TS_0) alias: 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_3) - aggregations: count(1) + Group By Operator (GBY_4) + aggregations: count(_col1) 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 (RS_4) + Reduce Output Operator (RS_5) 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_6) aggregations: count(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 - Select Operator (SEL_6) + Select Operator (SEL_7) 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 (FS_7) + File Output Operator (FS_8) compressed: false Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: @@ -286,7 +286,7 @@ TOK_QUERY LOGICAL PLAN: -null-subquery1:s1-subquery1:src +null-subquery1:$hdt$_0-subquery1:src TableScan (TS_0) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -294,20 +294,20 @@ null-subquery1:s1-subquery1:src expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Union (UNION_5) + Union (UNION_6) Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_6) + Select Operator (SEL_7) expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_7) + File Output Operator (FS_8) 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 +null-subquery2:$hdt$_0-subquery2:$hdt$_0:srcpart TableScan (TS_2) alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -315,7 +315,7 @@ null-subquery2:s1-subquery2:srcpart expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Union (UNION_5) + Union (UNION_6) Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: EXPLAIN LOGICAL @@ -369,58 +369,66 @@ TOK_QUERY LOGICAL PLAN: -s1 - TableScan (TS_1) - alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_11) - predicate: key is not null (type: boolean) - 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 - Join Operator (JOIN_6) - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col6 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_8) - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_9) - 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 -s2 +$hdt$_0:$hdt$_0:s2 TableScan (TS_0) alias: s2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_10) + Filter Operator (FIL_14) predicate: key is not null (type: boolean) 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: key (type: string) + 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 - value expressions: value (type: string) - Join Operator (JOIN_6) - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col6 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_6) + key expressions: _col0 (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_9) + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col3 + 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 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 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 +$hdt$_0:$hdt$_1:s1 + TableScan (TS_3) + alias: s1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator (FIL_13) + 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) + 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_9) + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: -- With views EXPLAIN LOGICAL SELECT * FROM V1 @@ -445,7 +453,7 @@ TOK_QUERY LOGICAL PLAN: -v1:src +src TableScan (TS_0) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -453,7 +461,7 @@ v1:src expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - ListSink (OP_4) + ListSink (OP_3) PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V2 PREHOOK: type: QUERY @@ -476,7 +484,7 @@ TOK_QUERY LOGICAL PLAN: -v2:srcpart +$hdt$_0:srcpart TableScan (TS_0) alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -507,62 +515,66 @@ TOK_QUERY LOGICAL PLAN: -v3:src1:srcpart +$hdt$_0:$hdt$_0:$hdt$_0:srcpart TableScan (TS_0) alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_14) + Filter Operator (FIL_15) 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) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_5) - key expressions: _col1 (type: string) + Reduce Output Operator (RS_7) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Join Operator (JOIN_8) + Join Operator (JOIN_10) condition map: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} 1 {VALUE._col0} - outputColumnNames: _col1, _col4 + outputColumnNames: _col0, _col2 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_10) - expressions: _col1 (type: string), _col4 (type: string) + Select Operator (SEL_11) + expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_12) + File Output Operator (FS_13) 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 -v3:src2 - TableScan (TS_3) +$hdt$_0:$hdt$_1:src2 + TableScan (TS_4) alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_13) + Filter Operator (FIL_14) predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_7) - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator (SEL_5) + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) - Join Operator (JOIN_8) - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col1, _col4 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_9) + 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_10) + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V4 PREHOOK: type: QUERY @@ -585,18 +597,68 @@ TOK_QUERY LOGICAL PLAN: -v4:src1:src - TableScan (TS_3) +$hdt$_0:$hdt$_0:$hdt$_0:srcpart + TableScan (TS_0) + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator (FIL_23) + 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_9) + key expressions: _col0 (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_12) + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_14) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string) + Join Operator (JOIN_17) + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {VALUE._col1} + 1 {VALUE._col0} + outputColumnNames: _col1, _col2, _col4 + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_18) + expressions: _col2 (type: string), _col1 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + File Output Operator (FS_20) + compressed: false + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +$hdt$_0:$hdt$_1:src + TableScan (TS_6) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_16) + Filter Operator (FIL_21) predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_4) + Select Operator (SEL_7) expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_7) + Reduce Output Operator (RS_11) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) @@ -604,74 +666,36 @@ v4:src1:src Join Operator (JOIN_12) condition map: Inner Join 0 to 1 - Inner Join 1 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col1} - 2 {VALUE._col0} - outputColumnNames: _col0, _col4, _col6 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_13) - expressions: _col0 (type: string), _col4 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_15) - 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 -v4:src2:srcpart - TableScan (TS_0) - alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_18) + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE +$hdt$_0:$hdt$_2:src + TableScan (TS_4) + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator (FIL_22) predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_2) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_5) expressions: key (type: string), value (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_9) - key expressions: _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_16) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) - Join Operator (JOIN_12) + 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_17) condition map: Inner Join 0 to 1 - Inner Join 1 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col1} - 2 {VALUE._col0} - outputColumnNames: _col0, _col4, _col6 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE -v4:src3 - TableScan (TS_5) - alias: src3 - 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 - Reduce Output Operator (RS_11) - 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_12) - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col1} - 2 {VALUE._col0} - outputColumnNames: _col0, _col4, _col6 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + 0 {VALUE._col0} {VALUE._col1} + 1 {VALUE._col0} + outputColumnNames: _col1, _col2, _col4 + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: -- The table should show up in the explain logical even if none -- of the partitions are selected. @@ -708,18 +732,18 @@ TOK_QUERY LOGICAL PLAN: -v5:srcpart +srcpart TableScan (TS_0) alias: srcpart Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Filter Operator (FIL_5) + Filter Operator (FIL_4) predicate: (ds = '10') (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator (SEL_2) expressions: key (type: string), value (type: string), '10' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - ListSink (OP_6) + ListSink (OP_5) 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 @@ -796,46 +820,91 @@ TOK_QUERY LOGICAL PLAN: -s1:src +$hdt$_0:$hdt$_0:src TableScan (TS_0) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_17) + Filter Operator (FIL_21) 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_2) - aggregations: count(value) - keys: key (type: string) + Reduce Output Operator (RS_11) + 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_14) + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_15) + 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_17) + 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_18) + 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_19) + 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 +$hdt$_0:$hdt$_1:$hdt$_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_20) + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_3) + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator (GBY_6) + aggregations: count(_col1) + 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 (RS_3) + Reduce Output Operator (RS_7) 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_4) + Group By Operator (GBY_8) aggregations: count(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 - Select Operator (SEL_5) + Select Operator (SEL_9) expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_8) + Reduce Output Operator (RS_13) 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 value expressions: _col1 (type: bigint) - Join Operator (JOIN_11) + Join Operator (JOIN_14) condition map: Inner Join 0 to 1 condition expressions: @@ -843,45 +912,4 @@ s1:src 1 {VALUE._col0} outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_12) - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_13) - 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_14) - 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_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_6) - alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_16) - predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_10) - 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 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/fetch_aggregation.q.out ql/src/test/results/clientpositive/fetch_aggregation.q.out index f0a73f5..1995b43 100644 --- ql/src/test/results/clientpositive/fetch_aggregation.q.out +++ 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: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key), sum(key), avg(key), min(key), max(key), std(key), variance(key) + aggregations: count(_col0), sum(_col0), avg(_col0), min(_col0), max(_col0), std(_col0), variance(_col0) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/filter_join_breaktask.q.out ql/src/test/results/clientpositive/filter_join_breaktask.q.out index c540c4a..87d28f0 100644 --- ql/src/test/results/clientpositive/filter_join_breaktask.q.out +++ ql/src/test/results/clientpositive/filter_join_breaktask.q.out @@ -281,7 +281,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/groupby2_limit.q.out ql/src/test/results/clientpositive/groupby2_limit.q.out index 855bd63..265bb65 100644 --- ql/src/test/results/clientpositive/groupby2_limit.q.out +++ ql/src/test/results/clientpositive/groupby2_limit.q.out @@ -17,12 +17,12 @@ 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: key, value + expressions: key (type: string), substr(value, 5) (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(substr(value, 5)) - keys: key (type: string) + aggregations: sum(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out index 3871381..e94d3ba 100644 --- ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out +++ ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out @@ -119,11 +119,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: int1 (type: int) - outputColumnNames: int1 + outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT int1) - keys: int1 (type: int) + aggregations: sum(DISTINCT _col0) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_position.q.out ql/src/test/results/clientpositive/groupby_position.q.out index 70eb661..bbdcc90 100644 --- ql/src/test/results/clientpositive/groupby_position.q.out +++ ql/src/test/results/clientpositive/groupby_position.q.out @@ -441,15 +441,15 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key <= 20) (type: boolean) + 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -577,34 +577,32 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 10) and (key < 20)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 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)) and key is not null) (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: key, value - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 31 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) + keys: _col0 (type: string), _col1 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 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) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -620,14 +618,14 @@ STAGE PLANS: 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 + Statistics: Num rows: 1 Data size: 10 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: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -636,12 +634,12 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -656,15 +654,15 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: --++ - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + 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 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + 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 @@ -674,35 +672,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 15) and (key < 25)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 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)) and key is not null) (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: key, value - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 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: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git ql/src/test/results/clientpositive/groupby_ppd.q.out ql/src/test/results/clientpositive/groupby_ppd.q.out index a086527..0fc0ddb 100644 --- ql/src/test/results/clientpositive/groupby_ppd.q.out +++ ql/src/test/results/clientpositive/groupby_ppd.q.out @@ -21,7 +21,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: d + alias: c Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator predicate: (bar = 1) (type: boolean) @@ -33,11 +33,11 @@ STAGE PLANS: Union Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col1 (type: int), 1 (type: int) + expressions: 1 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - keys: _col1 (type: int), _col0 (type: int) + keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -59,11 +59,11 @@ STAGE PLANS: Union Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col1 (type: int), 1 (type: int) + expressions: 1 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - keys: _col1 (type: int), _col0 (type: int) + keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_resolution.q.out ql/src/test/results/clientpositive/groupby_resolution.q.out index 1d1856f..9414dab 100644 --- ql/src/test/results/clientpositive/groupby_resolution.q.out +++ ql/src/test/results/clientpositive/groupby_resolution.q.out @@ -15,12 +15,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: key (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -64,12 +64,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: key (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -114,10 +114,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -188,10 +188,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -261,11 +261,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -317,11 +317,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -374,11 +374,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -455,11 +455,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -641,11 +641,11 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_10.q.out ql/src/test/results/clientpositive/groupby_sort_10.q.out index 6a2f91e..5b57154 100644 --- ql/src/test/results/clientpositive/groupby_sort_10.q.out +++ ql/src/test/results/clientpositive/groupby_sort_10.q.out @@ -41,10 +41,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: final outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE @@ -113,11 +113,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE Group By Operator bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_11.q.out ql/src/test/results/clientpositive/groupby_sort_11.q.out index a175852..7becc5f 100644 --- ql/src/test/results/clientpositive/groupby_sort_11.q.out +++ 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: key + outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key) + aggregations: count(DISTINCT _col0) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -108,13 +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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key), count(1), count(key), sum(DISTINCT key) + aggregations: count(DISTINCT _col0), count(_col1), count(_col0), sum(DISTINCT _col0) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -176,13 +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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key), count(1), count(key), sum(DISTINCT key) + aggregations: count(DISTINCT _col0), count(_col1), count(_col0), sum(DISTINCT _col0) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -251,13 +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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key), count(1), count(key), sum(DISTINCT key) + aggregations: count(DISTINCT _col0), count(_col1), count(_col0), sum(DISTINCT _col0) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -326,12 +326,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double) + outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT (key + key)) - keys: (key + key) (type: double) + aggregations: count(DISTINCT _col0) + keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -390,10 +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: _col0 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 _col0) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -455,10 +457,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/groupby_sort_1_23.q.out ql/src/test/results/clientpositive/groupby_sort_1_23.q.out index a74cb2b..42949f6 100644 --- ql/src/test/results/clientpositive/groupby_sort_1_23.q.out +++ ql/src/test/results/clientpositive/groupby_sort_1_23.q.out @@ -4243,7 +4243,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/groupby_sort_8.q.out ql/src/test/results/clientpositive/groupby_sort_8.q.out index e70abeb..304a5ff 100644 --- ql/src/test/results/clientpositive/groupby_sort_8.q.out +++ 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: key + outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key) + aggregations: count(DISTINCT _col0) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -126,11 +126,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key) - keys: key (type: string) + aggregations: count(DISTINCT _col0) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_9.q.out ql/src/test/results/clientpositive/groupby_sort_9.q.out index 0969c8d..db5a291 100644 --- ql/src/test/results/clientpositive/groupby_sort_9.q.out +++ 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) bucketGroup: true - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out index df9d51e..cafe68a 100644 --- ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out +++ ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out @@ -4535,7 +4535,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -4633,7 +4633,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/having.q.out ql/src/test/results/clientpositive/having.q.out index 4cda72f..58fed5e 100644 --- ql/src/test/results/clientpositive/having.q.out +++ ql/src/test/results/clientpositive/having.q.out @@ -93,15 +93,15 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key <> 302) (type: boolean) + predicate: (UDFToDouble(key) <> 302.0) (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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -469,11 +469,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -734,15 +734,15 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 300) (type: boolean) + predicate: (UDFToDouble(key) > 300.0) (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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -930,11 +930,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1196,11 +1196,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/having2.q.out ql/src/test/results/clientpositive/having2.q.out index 7a22550..9539394 100644 --- ql/src/test/results/clientpositive/having2.q.out +++ ql/src/test/results/clientpositive/having2.q.out @@ -133,11 +133,11 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: customer_name (type: string), customer_balance (type: double), order_quantity (type: double), discount (type: double) - outputColumnNames: customer_name, customer_balance, order_quantity, discount + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(customer_balance), sum(order_quantity), count(discount) - keys: customer_name (type: string) + aggregations: sum(_col1), sum(_col2), count(_col3) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -200,11 +200,11 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: customer_name (type: string), customer_balance (type: double), order_quantity (type: double), discount (type: double) - outputColumnNames: customer_name, customer_balance, order_quantity, discount + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(customer_balance), sum(order_quantity), count(discount) - keys: customer_name (type: string) + aggregations: sum(_col1), sum(_col2), count(_col3) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE diff --git ql/src/test/results/clientpositive/index_auto.q.out ql/src/test/results/clientpositive/index_auto.q.out index 124a9d2..d44fccc 100644 --- ql/src/test/results/clientpositive/index_auto.q.out +++ ql/src/test/results/clientpositive/index_auto.q.out @@ -77,7 +77,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 80) and (key < 100)) (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), value (type: string) @@ -147,9 +147,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((key > 80.0) and (key < 100.0)) (type: boolean) Filter Operator - predicate: ((key > 80) and (key < 100)) (type: boolean) + predicate: ((key > 80.0) and (key < 100.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -180,10 +180,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((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: ((key > 80) and (key < 100)) (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), value (type: string) diff --git ql/src/test/results/clientpositive/index_auto_empty.q.out ql/src/test/results/clientpositive/index_auto_empty.q.out index 5039024..55136f4 100644 --- ql/src/test/results/clientpositive/index_auto_empty.q.out +++ ql/src/test/results/clientpositive/index_auto_empty.q.out @@ -62,13 +62,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: temp - filterExpr: (key = 86) (type: boolean) + filterExpr: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: '86' (type: string), val (type: string) + expressions: '86.0' (type: string), val (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/index_auto_file_format.q.out ql/src/test/results/clientpositive/index_auto_file_format.q.out index 85a57f3..b6a4fe1 100644 --- ql/src/test/results/clientpositive/index_auto_file_format.q.out +++ ql/src/test/results/clientpositive/index_auto_file_format.q.out @@ -41,9 +41,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: (key = 86) (type: boolean) + filterExpr: (key = 86.0) (type: boolean) Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (key = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -74,10 +74,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: (key = 86) (type: boolean) + filterExpr: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) @@ -157,9 +157,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: (key = 86) (type: boolean) + filterExpr: (key = 86.0) (type: boolean) Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (key = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -190,10 +190,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: (key = 86) (type: boolean) + filterExpr: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/index_auto_mult_tables.q.out ql/src/test/results/clientpositive/index_auto_mult_tables.q.out index 47fed0c..208affb 100644 --- ql/src/test/results/clientpositive/index_auto_mult_tables.q.out +++ ql/src/test/results/clientpositive/index_auto_mult_tables.q.out @@ -22,41 +22,49 @@ STAGE PLANS: alias: b Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 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: 24 Data size: 254 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)) and key is not null) (type: boolean) + Statistics: Num rows: 12 Data size: 127 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 127 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: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (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) + 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 + 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 + Reduce Output Operator + key expressions: _col0 (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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -204,9 +212,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__srcpart_srcpart_index__ - filterExpr: (((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + filterExpr: (((((key > 70.0) and (key < 90.0)) and (key > 80.0)) and (key < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: (((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: (((((key > 70.0) and (key < 90.0)) and (key > 80.0)) and (key < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) outputColumnNames: _col0, _col1 @@ -247,45 +255,53 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - filterExpr: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) + 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 Filter Operator - predicate: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 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: 24 Data size: 254 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)) and key is not null) (type: boolean) + Statistics: Num rows: 12 Data size: 127 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE TableScan alias: a - filterExpr: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (type: boolean) + 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 Filter Operator - predicate: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (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) + 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 + 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 + Reduce Output Operator + key expressions: _col0 (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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -296,9 +312,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: (((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + filterExpr: (((((key > 80.0) and (key < 100.0)) and (key > 70.0)) and (key < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: (((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: (((((key > 80.0) and (key < 100.0)) and (key > 70.0)) and (key < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out index 1e344fa..e0f36c4 100644 --- ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out +++ ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out @@ -22,41 +22,49 @@ STAGE PLANS: alias: b Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 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: 24 Data size: 254 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)) and key is not null) (type: boolean) + Statistics: Num rows: 12 Data size: 127 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 127 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: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (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) + 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 + 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 + Reduce Output Operator + key expressions: _col0 (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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -214,9 +222,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__srcpart_srcpart_index__ - filterExpr: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) + filterExpr: ((((key > 70.0) and (key < 90.0)) and (key > 80.0)) and (key < 100.0)) (type: boolean) Filter Operator - predicate: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) + predicate: ((((key > 70.0) and (key < 90.0)) and (key > 80.0)) and (key < 100.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -247,45 +255,53 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - filterExpr: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) + 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 Filter Operator - predicate: ((((key > 70) and (key < 90)) and (key > 80)) and (key < 100)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 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: 24 Data size: 254 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)) and key is not null) (type: boolean) + Statistics: Num rows: 12 Data size: 127 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE TableScan alias: a - filterExpr: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (type: boolean) + 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 Filter Operator - predicate: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (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) + 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 + 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 + Reduce Output Operator + key expressions: _col0 (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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -324,9 +340,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (type: boolean) + filterExpr: ((((key > 80.0) and (key < 100.0)) and (key > 70.0)) and (key < 90.0)) (type: boolean) Filter Operator - predicate: ((((key > 80) and (key < 100)) and (key > 70)) and (key < 90)) (type: boolean) + predicate: ((((key > 80.0) and (key < 100.0)) and (key > 70.0)) and (key < 90.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/index_auto_multiple.q.out ql/src/test/results/clientpositive/index_auto_multiple.q.out index 722ee6e..ac65483 100644 --- ql/src/test/results/clientpositive/index_auto_multiple.q.out +++ ql/src/test/results/clientpositive/index_auto_multiple.q.out @@ -61,9 +61,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_key_index__ - filterExpr: (key = 86) (type: boolean) + filterExpr: (key = 86.0) (type: boolean) Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (key = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -94,10 +94,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: (key = 86) (type: boolean) + filterExpr: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/index_auto_partitioned.q.out ql/src/test/results/clientpositive/index_auto_partitioned.q.out index 4777c53..cf71e4c 100644 --- ql/src/test/results/clientpositive/index_auto_partitioned.q.out +++ ql/src/test/results/clientpositive/index_auto_partitioned.q.out @@ -55,9 +55,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__srcpart_src_part_index__ - filterExpr: ((key = 86) and (ds = '2008-04-09')) (type: boolean) + filterExpr: ((key = 86.0) and (ds = '2008-04-09')) (type: boolean) Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (key = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -88,10 +88,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((key = 86) and (ds = '2008-04-09')) (type: boolean) + filterExpr: ((UDFToDouble(key) = 86.0) and (ds = '2008-04-09')) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/index_auto_self_join.q.out ql/src/test/results/clientpositive/index_auto_self_join.q.out index 2bc80f4..abcf5fa 100644 --- ql/src/test/results/clientpositive/index_auto_self_join.q.out +++ ql/src/test/results/clientpositive/index_auto_self_join.q.out @@ -17,29 +17,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (key > 70)) and (key < 90)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + 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 + 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 + Reduce Output Operator + key expressions: _col1 (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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (key > 80)) and (key < 100)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + 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 + 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 + Reduce Output Operator + key expressions: _col1 (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) Reduce Operator Tree: Join Operator condition map: @@ -47,15 +55,15 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} 1 {VALUE._col0} - outputColumnNames: _col0, _col5 - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col2 + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col5 (type: string) + expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -124,9 +132,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: (((key > 70) and (key < 90)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + filterExpr: (((key > 70.0) and (key < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: (((key > 70) and (key < 90)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: (((key > 70.0) and (key < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) outputColumnNames: _col0, _col1 @@ -166,31 +174,39 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - filterExpr: ((value is not null and (key > 70)) and (key < 90)) (type: boolean) + alias: a + filterExpr: (((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (key > 70)) and (key < 90)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + 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 + 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 + Reduce Output Operator + key expressions: _col1 (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) TableScan alias: a - filterExpr: ((value is not null and (key > 80)) and (key < 100)) (type: boolean) + filterExpr: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (key > 80)) and (key < 100)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + 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 + 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 + Reduce Output Operator + key expressions: _col1 (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) Reduce Operator Tree: Join Operator condition map: @@ -198,15 +214,15 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} 1 {VALUE._col0} - outputColumnNames: _col0, _col5 - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col2 + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col5 (type: string) + expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -217,9 +233,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: (((key > 80) and (key < 100)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + filterExpr: (((key > 80.0) and (key < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: (((key > 80) and (key < 100)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: (((key > 80.0) and (key < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/index_auto_unused.q.out ql/src/test/results/clientpositive/index_auto_unused.q.out index ad799e8..e86a795 100644 --- ql/src/test/results/clientpositive/index_auto_unused.q.out +++ ql/src/test/results/clientpositive/index_auto_unused.q.out @@ -38,10 +38,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((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: ((key > 80) and (key < 100)) (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), value (type: string) @@ -104,10 +104,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((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: ((key > 80) and (key < 100)) (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), value (type: string) @@ -170,10 +170,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: ((key < 10) or (key > 480)) (type: boolean) + filterExpr: ((UDFToDouble(key) < 10.0) or (UDFToDouble(key) > 480.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 10) or (key > 480)) (type: boolean) + predicate: ((UDFToDouble(key) < 10.0) or (UDFToDouble(key) > 480.0)) (type: boolean) Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -273,10 +273,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((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: ((key > 80) and (key < 100)) (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), value (type: string) @@ -365,10 +365,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (((ds = '2008-04-09') and (hr = 12)) and (key < 10)) (type: boolean) + filterExpr: ((12.0 = 12.0) and (UDFToDouble(key) < 10.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 10) (type: boolean) + predicate: ((12.0 = 12.0) and (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), '2008-04-09' (type: string), '12' (type: string) diff --git ql/src/test/results/clientpositive/index_auto_update.q.out ql/src/test/results/clientpositive/index_auto_update.q.out index 0f996b5..791f95a 100644 --- ql/src/test/results/clientpositive/index_auto_update.q.out +++ ql/src/test/results/clientpositive/index_auto_update.q.out @@ -223,9 +223,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__temp_temp_index__ - filterExpr: (key = 86) (type: boolean) + filterExpr: (key = 86.0) (type: boolean) Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (key = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -256,10 +256,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: temp - filterExpr: (key = 86) (type: boolean) + filterExpr: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out index 052acbb..1b56899 100644 --- ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out +++ ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out @@ -53,9 +53,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__srcpart_src_part_index__ - filterExpr: ((key = 86) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + filterExpr: ((key = 86.0) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: ((key = 86) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: ((key = 86.0) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) outputColumnNames: _col0, _col1 @@ -96,10 +96,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((key = 86) and (ds = '2008-04-09')) (type: boolean) + filterExpr: ((UDFToDouble(key) = 86.0) and (ds = '2008-04-09')) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/index_bitmap_compression.q.out ql/src/test/results/clientpositive/index_bitmap_compression.q.out index f136259..6772bc0 100644 --- ql/src/test/results/clientpositive/index_bitmap_compression.q.out +++ ql/src/test/results/clientpositive/index_bitmap_compression.q.out @@ -39,9 +39,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: (((key > 80) and (key < 100)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + filterExpr: (((key > 80.0) and (key < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: (((key > 80) and (key < 100)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: (((key > 80.0) and (key < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) outputColumnNames: _col0, _col1 @@ -82,10 +82,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((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: ((key > 80) and (key < 100)) (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), value (type: string) diff --git ql/src/test/results/clientpositive/index_compression.q.out ql/src/test/results/clientpositive/index_compression.q.out index b44bce8..418a993 100644 --- ql/src/test/results/clientpositive/index_compression.q.out +++ ql/src/test/results/clientpositive/index_compression.q.out @@ -43,9 +43,9 @@ STAGE PLANS: Map Operator Tree: TableScan alias: default.default__src_src_index__ - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((key > 80.0) and (key < 100.0)) (type: boolean) Filter Operator - predicate: ((key > 80) and (key < 100)) (type: boolean) + predicate: ((key > 80.0) and (key < 100.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 @@ -76,10 +76,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - filterExpr: ((key > 80) and (key < 100)) (type: boolean) + filterExpr: ((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: ((key > 80) and (key < 100)) (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), value (type: string) diff --git ql/src/test/results/clientpositive/index_stale.q.out ql/src/test/results/clientpositive/index_stale.q.out index 951bcf2..b8bcfd7 100644 --- ql/src/test/results/clientpositive/index_stale.q.out +++ ql/src/test/results/clientpositive/index_stale.q.out @@ -68,10 +68,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: temp - filterExpr: (key = 86) (type: boolean) + filterExpr: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/index_stale_partitioned.q.out ql/src/test/results/clientpositive/index_stale_partitioned.q.out index edd9746..9a37a56 100644 --- ql/src/test/results/clientpositive/index_stale_partitioned.q.out +++ ql/src/test/results/clientpositive/index_stale_partitioned.q.out @@ -89,10 +89,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: temp - filterExpr: ((key = 86) and (foo = 'bar')) (type: boolean) + filterExpr: ((UDFToDouble(key) = 86.0) and (foo = 'bar')) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) 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) diff --git ql/src/test/results/clientpositive/infer_const_type.q.out ql/src/test/results/clientpositive/infer_const_type.q.out index 4f4fe1c..d345afa 100644 --- ql/src/test/results/clientpositive/infer_const_type.q.out +++ ql/src/test/results/clientpositive/infer_const_type.q.out @@ -59,7 +59,7 @@ STAGE PLANS: alias: infertypes Statistics: Num rows: 3 Data size: 117 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((ti = 127) and (si = 32767)) and (i = 12345)) and (bi = -12345)) and (fl = 906.0)) and (db = -307.0)) and (str = 1234)) (type: boolean) + predicate: (((((((ti = 127) and (si = 32767)) and (i = 12345)) and (bi = -12345)) and (fl = 906.0)) and (db = -307.0)) and (UDFToDouble(str) = 1234.0)) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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) @@ -256,7 +256,7 @@ STAGE PLANS: alias: infertypes Statistics: Num rows: 3 Data size: 117 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ti < 127.0) and (i > 100.0)) and (str = 1.57)) (type: boolean) + predicate: (((UDFToDouble(ti) < 127) and (UDFToDouble(i) > 100)) and (UDFToDouble(str) = 1.57)) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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) diff --git ql/src/test/results/clientpositive/innerjoin.q.out ql/src/test/results/clientpositive/innerjoin.q.out index f058d37..2a18d6b 100644 --- ql/src/test/results/clientpositive/innerjoin.q.out +++ ql/src/test/results/clientpositive/innerjoin.q.out @@ -1184,12 +1184,16 @@ STAGE PLANS: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/input23.q.out ql/src/test/results/clientpositive/input23.q.out index 51a2329..5a568a3 100644 --- ql/src/test/results/clientpositive/input23.q.out +++ ql/src/test/results/clientpositive/input23.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[4][tables = [a]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[9][tables = [$hdt$_0]] 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 @@ -69,12 +69,16 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator - sort order: + 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 - tag: 0 - value expressions: key (type: string), value (type: string) - auto parallelism: false + 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) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -125,7 +129,7 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:a] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -134,10 +138,10 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col7, _col8 + outputColumnNames: _col0, _col1, _col4, _col5 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), _col7 (type: string), _col8 (type: string), '2008-04-08' (type: string), '14' (type: string) + 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 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Limit @@ -171,7 +175,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[4][tables = [a]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[9][tables = [$hdt$_0]] 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 ql/src/test/results/clientpositive/input24.q.out ql/src/test/results/clientpositive/input24.q.out index 75689b3..a579ba6 100644 --- ql/src/test/results/clientpositive/input24.q.out +++ ql/src/test/results/clientpositive/input24.q.out @@ -31,9 +31,11 @@ STAGE PLANS: alias: x Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/input25.q.out ql/src/test/results/clientpositive/input25.q.out index 6d8cb15..141a576 100644 --- ql/src/test/results/clientpositive/input25.q.out +++ ql/src/test/results/clientpositive/input25.q.out @@ -60,18 +60,22 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), '2009-01-01' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - input format: 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), '2009-01-01' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 @@ -124,18 +128,22 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), '2009-02-02' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - input format: 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), '2009-02-02' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 ql/src/test/results/clientpositive/input26.q.out ql/src/test/results/clientpositive/input26.q.out index 443c1c5..66d3bd2 100644 --- ql/src/test/results/clientpositive/input26.q.out +++ ql/src/test/results/clientpositive/input26.q.out @@ -36,18 +36,22 @@ STAGE PLANS: value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col3 + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 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 - File Output Operator - compressed: false - table: - input format: 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), '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 Stage: Stage-2 Map Reduce @@ -85,18 +89,22 @@ STAGE PLANS: Map Reduce Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), '14' (type: string) - outputColumnNames: _col0, _col1, _col3 + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Limit Number of rows: 5 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - input format: 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), '14' (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 ql/src/test/results/clientpositive/input2_limit.q.out ql/src/test/results/clientpositive/input2_limit.q.out index cffde07..76d1102 100644 --- ql/src/test/results/clientpositive/input2_limit.q.out +++ ql/src/test/results/clientpositive/input2_limit.q.out @@ -16,7 +16,7 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 300) (type: boolean) + predicate: (UDFToDouble(key) < 300.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/input42.q.out ql/src/test/results/clientpositive/input42.q.out index 8ecb492..deed5dc 100644 --- ql/src/test/results/clientpositive/input42.q.out +++ ql/src/test/results/clientpositive/input42.q.out @@ -1187,52 +1187,14 @@ TOK_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: a - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key < 200) (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 - 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 _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 - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + 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: @@ -1276,9 +1238,7 @@ 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=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1322,15 +1282,20 @@ STAGE PLANS: 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] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: a + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (UDFToDouble(key) < 200.0) (type: boolean) + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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 key < 200 PREHOOK: type: QUERY @@ -1759,52 +1724,14 @@ TOK_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: a - Statistics: Num rows: 1000 Data size: 10624 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 - 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 _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 - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + 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: @@ -1848,9 +1775,7 @@ 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=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1894,15 +1819,20 @@ STAGE PLANS: 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] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: a + Statistics: Num rows: 1000 Data size: 10624 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 + 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 diff --git ql/src/test/results/clientpositive/input_part4.q.out ql/src/test/results/clientpositive/input_part4.q.out index 85e9aa9..1ebf36b 100644 --- ql/src/test/results/clientpositive/input_part4.q.out +++ ql/src/test/results/clientpositive/input_part4.q.out @@ -16,7 +16,7 @@ STAGE PLANS: alias: x Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: ((ds = '2008-04-08') and (hr = 15)) (type: boolean) + predicate: ((ds = '2008-04-08') and (UDFToDouble(hr) = 15.0)) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '15' (type: string) diff --git ql/src/test/results/clientpositive/input_part6.q.out ql/src/test/results/clientpositive/input_part6.q.out index e094741..fa51cdf 100644 --- ql/src/test/results/clientpositive/input_part6.q.out +++ ql/src/test/results/clientpositive/input_part6.q.out @@ -16,12 +16,12 @@ STAGE PLANS: alias: x Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ds = 1996) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(ds) = 1996.0) (type: boolean) + 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 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/input_part9.q.out ql/src/test/results/clientpositive/input_part9.q.out index 8586a67..cc998f4 100644 --- ql/src/test/results/clientpositive/input_part9.q.out +++ ql/src/test/results/clientpositive/input_part9.q.out @@ -38,52 +38,14 @@ TOK_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: x - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: 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), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 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.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: -#### A masked pattern was here #### + Stage: Stage-0 + 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: @@ -127,9 +89,7 @@ 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=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -173,15 +133,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [x] - /srcpart/ds=2008-04-08/hr=12 [x] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: x + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: 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), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: SELECT x.* FROM SRCPART x WHERE key IS NOT NULL AND ds = '2008-04-08' PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/join10.q.out ql/src/test/results/clientpositive/join10.q.out index 1749768..0120c9b 100644 --- ql/src/test/results/clientpositive/join10.q.out +++ ql/src/test/results/clientpositive/join10.q.out @@ -27,14 +27,15 @@ STAGE PLANS: 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: _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) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -42,26 +43,25 @@ STAGE PLANS: 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 + expressions: key (type: string) + outputColumnNames: _col0 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: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col2, _col3 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string) + 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 diff --git ql/src/test/results/clientpositive/join11.q.out ql/src/test/results/clientpositive/join11.q.out index 9e77bb7..ad03b6d 100644 --- ql/src/test/results/clientpositive/join11.q.out +++ ql/src/test/results/clientpositive/join11.q.out @@ -26,7 +26,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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) @@ -42,7 +42,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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) @@ -58,12 +58,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col3 + 0 {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) + expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/join13.q.out ql/src/test/results/clientpositive/join13.q.out index f5f3e08..94f1d44 100644 --- ql/src/test/results/clientpositive/join13.q.out +++ ql/src/test/results/clientpositive/join13.q.out @@ -21,19 +21,19 @@ JOIN ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 200 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: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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) @@ -49,7 +49,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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) @@ -65,13 +65,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col2, _col3 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 + _col2) is not null (type: boolean) - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + predicate: (((UDFToDouble(_col2) + UDFToDouble(_col0)) < 200.0) and (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null) (type: boolean) + Statistics: Num rows: 30 Data size: 319 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -79,21 +79,14 @@ 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 - key expressions: (_col0 + _col2) (type: double) - sort order: + - Map-reduce partition columns: (_col0 + _col2) (type: double) - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col3 (type: string) - TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and UDFToDouble(key) is not null) (type: boolean) + 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 Select Operator expressions: key (type: string) @@ -104,22 +97,29 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator + key expressions: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) + Statistics: Num rows: 30 Data size: 319 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col0} {VALUE._col3} + 0 {VALUE._col1} {VALUE._col2} 1 - outputColumnNames: _col0, _col3 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col2 + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) + expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 91 Data size: 969 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: 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 diff --git ql/src/test/results/clientpositive/join16.q.out ql/src/test/results/clientpositive/join16.q.out index 4573cb6..a0c2f7d 100644 --- ql/src/test/results/clientpositive/join16.q.out +++ ql/src/test/results/clientpositive/join16.q.out @@ -14,28 +14,32 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((key > 10) and value is not null) and (key > 20)) and (value < 200)) (type: boolean) - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + 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 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 53 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: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE TableScan - alias: tab + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((key > 20) and value is not null) and key is not null) and (value < 200)) (type: boolean) - Statistics: Num rows: 14 Data size: 148 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: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + 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 + 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 + 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: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -44,14 +48,14 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey1} outputColumnNames: _col0, _col3 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 58 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 ql/src/test/results/clientpositive/join18.q.out ql/src/test/results/clientpositive/join18.q.out index 5550ff6..e2dd0af 100644 --- ql/src/test/results/clientpositive/join18.q.out +++ ql/src/test/results/clientpositive/join18.q.out @@ -39,11 +39,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT value) - keys: key (type: string), value (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -116,11 +116,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/join18_multi_distinct.q.out ql/src/test/results/clientpositive/join18_multi_distinct.q.out index 5d4a738..59042a3 100644 --- ql/src/test/results/clientpositive/join18_multi_distinct.q.out +++ ql/src/test/results/clientpositive/join18_multi_distinct.q.out @@ -45,11 +45,11 @@ STAGE PLANS: 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 + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT value), count(DISTINCT key) - keys: key (type: string), value (type: string) + aggregations: count(DISTINCT _col1), count(DISTINCT _col0) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -122,11 +122,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/join22.q.out ql/src/test/results/clientpositive/join22.q.out index 4c1a690..16e1d87 100644 --- ql/src/test/results/clientpositive/join22.q.out +++ ql/src/test/results/clientpositive/join22.q.out @@ -5,37 +5,45 @@ POSTHOOK: query: explain SELECT 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-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: src2 + alias: 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 - 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: _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) TableScan - alias: src1 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: @@ -47,7 +55,7 @@ STAGE PLANS: Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col2, _col3 + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -56,38 +64,42 @@ 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 - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string) - TableScan alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 + 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) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {VALUE._col2} - outputColumnNames: _col8 + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col8 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/join40.q.out ql/src/test/results/clientpositive/join40.q.out index d99be84..93117a0 100644 --- ql/src/test/results/clientpositive/join40.q.out +++ ql/src/test/results/clientpositive/join40.q.out @@ -15,17 +15,21 @@ STAGE PLANS: TableScan alias: x Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan - alias: src + alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key <= 100) (type: boolean) + 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) @@ -44,10 +48,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -655,39 +659,47 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 + 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col6 + 0 {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col6 (type: string) + expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3733,27 +3745,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: @@ -3763,9 +3783,11 @@ STAGE PLANS: 1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/join_alt_syntax.q.out ql/src/test/results/clientpositive/join_alt_syntax.q.out index 590e4d1..38dc661 100644 --- ql/src/test/results/clientpositive/join_alt_syntax.q.out +++ ql/src/test/results/clientpositive/join_alt_syntax.q.out @@ -40,7 +40,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwri POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@part -Warning: Shuffle Join JOIN[4][tables = [p1, p2]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] 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 @@ -56,30 +56,38 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p2 + alias: p1 Statistics: Num rows: 31 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: p_name (type: string) + outputColumnNames: _col0 Statistics: Num rows: 31 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 31 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) TableScan alias: p1 Statistics: Num rows: 31 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: p_name (type: string) + outputColumnNames: _col0 Statistics: Num rows: 31 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 31 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col1} - 1 {VALUE._col1} - outputColumnNames: _col1, _col13 + 0 {VALUE._col0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col1 Statistics: Num rows: 34 Data size: 3490 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col13 (type: string) + expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 34 Data size: 3490 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/join_filters.q.out ql/src/test/results/clientpositive/join_filters.q.out index 8a4e2a2..4f112bd 100644 --- ql/src/test/results/clientpositive/join_filters.q.out +++ 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[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] 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[10][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] 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 diff --git ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out index b3f1e09..88103e8 100644 --- ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out +++ ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out @@ -14,38 +14,50 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a 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 - Reduce Output Operator - key expressions: key (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), hr (type: string) + Select Operator + expressions: key (type: string), hr (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: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan - alias: c + alias: a 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 - Reduce Output Operator - key expressions: key (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), hr (type: string) + Select Operator + expressions: key (type: string), hr (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: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan alias: a 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 - Reduce Output Operator - key expressions: key (type: string), hr (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), hr (type: string) + Select Operator + expressions: key (type: string), hr (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: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/join_nulls.q.out ql/src/test/results/clientpositive/join_nulls.q.out index d5f20b7..46e0170 100644 --- ql/src/test/results/clientpositive/join_nulls.q.out +++ 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[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] 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[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] 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[4][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] 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 ql/src/test/results/clientpositive/join_vc.q.out ql/src/test/results/clientpositive/join_vc.q.out index 45652ff..a3550c9 100644 --- ql/src/test/results/clientpositive/join_vc.q.out +++ ql/src/test/results/clientpositive/join_vc.q.out @@ -139,63 +139,92 @@ POSTHOOK: Input: default@src 0 238 val_238 PREHOOK: query: explain select t2.BLOCK__OFFSET__INSIDE__FILE -from src t1 join src t2 on t1.key = t2.key where t1.key < 100 +from src t1 join src t2 on t1.key = t2.key where t1.key < 100 order by t2.BLOCK__OFFSET__INSIDE__FILE PREHOOK: type: QUERY POSTHOOK: query: explain select t2.BLOCK__OFFSET__INSIDE__FILE -from src t1 join src t2 on t1.key = t2.key where t1.key < 100 +from src t1 join src t2 on t1.key = t2.key where t1.key < 100 order by t2.BLOCK__OFFSET__INSIDE__FILE 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: t2 + alias: t1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 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), BLOCK__OFFSET__INSIDE__FILE (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: BLOCK__OFFSET__INSIDE__FILE (type: bigint) + 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 + value expressions: _col1 (type: bigint) TableScan alias: t1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 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: _col0 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: Inner Join 0 to 1 condition expressions: - 0 - 1 {VALUE._col1} - outputColumnNames: _col7 + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col7 (type: bigint) + expressions: _col1 (type: bigint) outputColumnNames: _col0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE 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 + input format: 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) + 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 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + 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 @@ -204,160 +233,160 @@ STAGE PLANS: ListSink PREHOOK: query: select t2.BLOCK__OFFSET__INSIDE__FILE -from src t1 join src t2 on t1.key = t2.key where t1.key < 100 +from src t1 join src t2 on t1.key = t2.key where t1.key < 100 order by t2.BLOCK__OFFSET__INSIDE__FILE PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: select t2.BLOCK__OFFSET__INSIDE__FILE -from src t1 join src t2 on t1.key = t2.key where t1.key < 100 +from src t1 join src t2 on t1.key = t2.key where t1.key < 100 order by t2.BLOCK__OFFSET__INSIDE__FILE POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -2088 -2632 -968 -2088 -2632 -968 -2088 -2632 -968 -2846 -3170 -1720 -4362 -1720 -4362 +12 +34 +92 +92 +198 +328 +328 386 -2770 386 -2770 +396 910 -5340 -5514 -5340 -5514 -2824 -4004 +968 +968 +968 +1024 1118 -4594 -1972 -4594 -1972 -2226 -5284 -2226 -5284 -34 -5616 -3494 -3592 -3192 -3138 -4012 +1176 +1198 +1208 +1208 +1218 1238 -3138 -4012 1238 -3138 -4012 1238 -5626 -328 -5626 -328 -1218 -3388 +1440 +1462 +1462 +1592 +1674 +1674 +1720 +1720 +1754 +1754 +1872 +1872 +1906 +1906 +1916 +1972 +1972 2030 -3298 2030 -3298 +2088 +2088 +2088 +2216 +2226 +2226 +2308 +2308 2330 -4068 -1198 +2400 +2400 +2458 +2458 +2612 +2622 +2632 +2632 +2632 +2652 +2770 +2770 +2792 +2792 +2802 +2802 +2802 +2824 +2846 3060 -4540 -3864 3060 -4540 -3864 3060 -4540 -3864 -2308 -1462 -2308 -1462 -4186 -1440 -1024 -1906 3128 -1906 3128 +3138 +3138 +3138 +3160 +3160 +3170 +3192 +3298 +3298 +3368 +3378 +3378 +3388 +3494 3516 -1592 -198 -1754 -5306 -1754 -5306 +3538 +3538 +3548 3570 +3592 3794 -4640 -4548 3794 -4640 -4548 3794 -4640 -4548 -2792 -1208 -2792 -1208 -3548 -3378 -3538 -3378 -3538 -2622 -3368 -1916 +3864 +3864 +3864 +4004 +4012 +4012 +4012 4058 -396 +4068 +4186 +4304 +4304 +4304 +4362 +4362 +4540 +4540 +4540 +4548 +4548 +4548 +4594 +4594 +4640 +4640 +4640 5070 -1674 5070 -1674 -1872 +5284 +5284 +5306 +5306 +5340 +5340 +5398 +5514 +5514 +5572 +5572 5606 -1872 5606 -2612 -12 -2652 -5398 -2802 +5616 +5626 +5626 5744 -4304 -2802 5744 -4304 -2802 5744 -4304 -1176 -3160 -2400 -3160 -2400 -2216 -5572 5802 -5572 5802 -92 -2458 -92 -2458 diff --git ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out index 7513886..5086797 100644 --- ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out +++ ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out @@ -546,10 +546,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) - outputColumnNames: hr + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: hr (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/limit_pushdown.q.out ql/src/test/results/clientpositive/limit_pushdown.q.out index 4abef8c..e972a79 100644 --- ql/src/test/results/clientpositive/limit_pushdown.q.out +++ ql/src/test/results/clientpositive/limit_pushdown.q.out @@ -178,12 +178,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: value, key + expressions: value (type: string), (UDFToDouble(key) + 1.0) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum((key + 1)) - keys: value (type: string) + aggregations: sum(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -270,12 +270,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: value, key + expressions: value (type: string), (UDFToDouble(key) + 1.0) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg((key + 1)) - keys: value (type: string) + aggregations: avg(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -363,10 +363,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) - outputColumnNames: cdouble + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: cdouble (type: double) + keys: _col0 (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -450,11 +450,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: ctinyint, cdouble + outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT cdouble) - keys: ctinyint (type: tinyint), cdouble (type: double) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -541,11 +541,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: ctinyint, cstring1, cstring2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) - keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) + aggregations: count(DISTINCT _col1), count(DISTINCT _col2) + keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -659,11 +659,11 @@ 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: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(key) - keys: value (type: string) + aggregations: sum(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -769,10 +769,10 @@ 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-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-2 + Stage-2 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-2, Stage-4 + Stage-4 is a root stage + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 @@ -782,12 +782,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -810,11 +810,39 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit - Number of rows: 2 + 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-2 + 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) 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -822,7 +850,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -830,14 +858,14 @@ STAGE PLANS: 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 + Statistics: Num rows: 2 Data size: 20 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: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -845,11 +873,11 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3 + 1 {VALUE._col0} + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + expressions: _col0 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Limit @@ -863,19 +891,19 @@ STAGE PLANS: 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 alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -898,41 +926,21 @@ STAGE PLANS: outputColumnNames: _col0, _col1 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) + Number of rows: 2 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 + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + 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 + File Output Operator + compressed: false + table: + input format: 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 @@ -960,16 +968,16 @@ 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: key, value + expressions: value (type: string), key (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: value (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: value (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: key (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) @@ -1205,16 +1213,16 @@ 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: key, value + expressions: concat(key, value, value, value, value, value, value, value, value, value) (type: string), key (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: concat(key, value, value, value, value, value, value, value, value, value) (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: concat(key, value, value, value, value, value, value, value, value, value) (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 2.0E-5 - value expressions: key (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) diff --git ql/src/test/results/clientpositive/limit_pushdown_negative.q.out ql/src/test/results/clientpositive/limit_pushdown_negative.q.out index b27e049..042b6f1 100644 --- ql/src/test/results/clientpositive/limit_pushdown_negative.q.out +++ ql/src/test/results/clientpositive/limit_pushdown_negative.q.out @@ -13,29 +13,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Join Operator condition map: @@ -43,10 +51,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + 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 diff --git ql/src/test/results/clientpositive/literal_ints.q.out ql/src/test/results/clientpositive/literal_ints.q.out index 9a56ebd..94d1a7e 100644 --- ql/src/test/results/clientpositive/literal_ints.q.out +++ ql/src/test/results/clientpositive/literal_ints.q.out @@ -14,12 +14,12 @@ STAGE PLANS: alias: src 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) + expressions: 100 (type: int), 100 (type: int), 100 (type: int), 100 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 10000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT 100, 100Y, 100S, 100L FROM src LIMIT 1 diff --git ql/src/test/results/clientpositive/louter_join_ppr.q.out ql/src/test/results/clientpositive/louter_join_ppr.q.out index 1e60985..342d8c3 100644 --- ql/src/test/results/clientpositive/louter_join_ppr.q.out +++ ql/src/test/results/clientpositive/louter_join_ppr.q.out @@ -109,37 +109,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false - TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + TableScan + alias: b + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + 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 + Statistics: Num rows: 111 Data size: 1179 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -280,25 +288,25 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [a] - /srcpart/ds=2008-04-08/hr=11 [b] - /srcpart/ds=2008-04-08/hr=12 [b] + /src [$hdt$_0:$hdt$_1:a] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:$hdt$_0:b] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:$hdt$_0:b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col5 > 15) and (_col5 < 25)) (type: boolean) + predicate: ((UDFToDouble(_col0) > 15.0) and (UDFToDouble(_col0) < 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), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -483,32 +491,40 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false TableScan alias: a Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 222 Data size: 2358 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), ds (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string), ds (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (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) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -741,11 +757,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /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] + /src [$hdt$_0:$hdt$_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] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:$hdt$_0:a] + /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:$hdt$_0:a] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -759,14 +775,14 @@ STAGE PLANS: filter predicates: 0 {(VALUE._col1 = '2008-04-08')} 1 - outputColumnNames: _col0, _col1, _col7, _col8 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col7 > 15) and (_col7 < 25)) (type: boolean) + predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 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), _col7 (type: string), _col8 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -950,37 +966,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 222 Data size: 2358 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string), ds (type: string) - auto parallelism: false - TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + TableScan + alias: b + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + 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 + Statistics: Num rows: 111 Data size: 1179 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1120,120 +1144,26 @@ 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 defaultdefault - 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 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 true - bucket_count -1 - columns key,value - columns.comments defaultdefault - 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 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: - /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] + /src [$hdt$_0:$hdt$_1:a] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:$hdt$_0:b] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:$hdt$_0:b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col5, _col6, _col7 - Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (((_col5 > 15) and (_col5 < 25)) and (_col7 = '2008-04-08')) (type: boolean) + predicate: ((UDFToDouble(_col0) > 15.0) and (UDFToDouble(_col0) < 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), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1276,8 +1206,6 @@ PREHOOK: Input: default@src 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: FROM src a @@ -1291,8 +1219,6 @@ 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: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 17 val_17 17 val_17 17 val_17 17 val_17 @@ -1422,32 +1348,40 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false TableScan alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 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: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1588,9 +1522,9 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [b] - /srcpart/ds=2008-04-08/hr=11 [a] - /srcpart/ds=2008-04-08/hr=12 [a] + /src [$hdt$_0:$hdt$_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] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -1599,14 +1533,14 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col7, _col8 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col7 > 15) and (_col7 < 25)) (type: boolean) + predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 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), _col7 (type: string), _col8 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out index 7da7122..7c510a9 100644 --- ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out +++ ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out @@ -60,14 +60,14 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - src + $hdt$_0:$hdt$_0:src Fetch Operator limit: -1 - src1 + $hdt$_0:$hdt$_1:$hdt$_2:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src + $hdt$_0:$hdt$_0:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -76,15 +76,19 @@ STAGE PLANS: isSamplingPred: false predicate: value is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 value (type: string) - 1 value (type: string) - Position of Big Table: 0 - src1 + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + Position of Big Table: 1 + $hdt$_0:$hdt$_1:$hdt$_2:src1 TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -93,14 +97,18 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 - keys: - 0 _col0 (type: string) - 1 key (type: string) - Position of Big Table: 0 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + Position of Big Table: 0 Stage: Stage-5 Map Reduce @@ -111,57 +119,65 @@ STAGE PLANS: 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 value (type: string) - 1 value (type: string) - outputColumnNames: _col0 - Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 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 Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} + 0 {_col0} {_col1} 1 keys: 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0 + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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 + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1 + Position of Big Table: 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.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: _col1 (type: string) + outputColumnNames: _col0 + 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.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 +456,10 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /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] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_1:$hdt$_1:srcpart] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_1:$hdt$_1:srcpart] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:$hdt$_1:$hdt$_1:srcpart] + /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:$hdt$_1:$hdt$_1:srcpart] Stage: Stage-0 Fetch Operator @@ -466,41 +482,49 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - src + $hdt$_0:$hdt$_0:src Fetch Operator limit: -1 - src1 + $hdt$_0:$hdt$_1:$hdt$_2:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src + $hdt$_0:$hdt$_0:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value > 'val_450') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 value (type: string) - 1 value (type: string) - src1 + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + $hdt$_0:$hdt$_1:$hdt$_2:src1 TableScan alias: src1 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 - HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 - keys: - 0 _col0 (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-5 Map Reduce @@ -509,41 +533,49 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 value (type: string) - 1 value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + 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 + 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 Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} + 0 {_col0} {_col1} 1 keys: 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - table: - 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: _col0 (type: string), _col1 (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 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (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 Local Work: Map Reduce Local Work @@ -570,24 +602,28 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - src + $hdt$_0:$hdt$_0:$hdt$_1:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src + $hdt$_0:$hdt$_0:$hdt$_1:src TableScan alias: src 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 - HashTable Sink Operator - condition expressions: - 0 {key} {ds} - 1 - keys: - 0 value (type: string) - 1 value (type: string) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} {_col2} + 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) Stage: Stage-7 Map Reduce @@ -598,47 +634,55 @@ STAGE PLANS: Filter Operator 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {ds} - 1 - keys: - 0 value (type: string) - 1 value (type: string) - outputColumnNames: _col0, _col2 - 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 + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col2} + 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + 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 Local Work: Map Reduce Local Work Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - src1 + $hdt$_0:$hdt$_0:$hdt$_2:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - src1 + $hdt$_0:$hdt$_0:$hdt$_2:src TableScan - alias: src1 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {_col2} - 1 - keys: - 0 _col0 (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col2} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-3 Map Reduce @@ -652,16 +696,16 @@ STAGE PLANS: 1 keys: 0 _col0 (type: string) - 1 key (type: string) + 1 _col0 (type: string) outputColumnNames: _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string) - outputColumnNames: _col2 + outputColumnNames: _col0 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col2 (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/mapjoin_subquery.q.out ql/src/test/results/clientpositive/mapjoin_subquery.q.out index 4084764..f8206b5 100644 --- ql/src/test/results/clientpositive/mapjoin_subquery.q.out +++ ql/src/test/results/clientpositive/mapjoin_subquery.q.out @@ -27,41 +27,49 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - subq:x + $hdt$_0:$hdt$_0:z Fetch Operator limit: -1 - z + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - subq:x + $hdt$_0:$hdt$_0:z + TableScan + alias: z + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((11.0 = 11.0) and 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 + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) - z - 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 - HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-5 Map Reduce @@ -72,43 +80,47 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col5 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1 + 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 + condition expressions: + 0 {_col1} + 1 {_col0} + 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 - File Output Operator - compressed: false + 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 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 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 Local Work: Map Reduce Local Work @@ -270,41 +282,49 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - subq:x + $hdt$_0:$hdt$_0:z Fetch Operator limit: -1 - z + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - subq:x + $hdt$_0:$hdt$_0:z + TableScan + alias: z + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((11.0 = 11.0) and 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 + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) - z - 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 - HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-5 Map Reduce @@ -315,43 +335,47 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col5 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1 + 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 + condition expressions: + 0 {_col1} + 1 {_col0} + 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 - File Output Operator - compressed: false + 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 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 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 Local Work: Map Reduce Local Work diff --git ql/src/test/results/clientpositive/mergejoins.q.out ql/src/test/results/clientpositive/mergejoins.q.out index d5f5bb4..dc16a89 100644 --- ql/src/test/results/clientpositive/mergejoins.q.out +++ ql/src/test/results/clientpositive/mergejoins.q.out @@ -183,32 +183,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan - alias: c + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -220,12 +232,12 @@ STAGE PLANS: 2 {KEY.reducesinkkey0} {VALUE._col0} filter predicates: 0 - 1 {(KEY.reducesinkkey0 < 10)} + 1 {(UDFToDouble(KEY.reducesinkkey0) < UDFToDouble(10))} 2 - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1100 Data size: 11686 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) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (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 diff --git ql/src/test/results/clientpositive/metadata_only_queries.q.out ql/src/test/results/clientpositive/metadata_only_queries.q.out index f5b9bd8..c04c98e 100644 --- ql/src/test/results/clientpositive/metadata_only_queries.q.out +++ 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: s, bo, bin, si, i, b + 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: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 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(s), count(bo), count(bin), count(si), max(i), min(b) + aggregations: count(), sum(_col0), sum(_col1), count(_col0), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) 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 @@ -248,11 +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: s, bo, bin, si, i, b + 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: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 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(s), count(bo), count(bin), count(si), max(i), min(b) + aggregations: count(), sum(_col0), sum(_col1), count(_col0), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) 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 @@ -439,10 +439,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: ts + outputColumnNames: _col0 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(ts) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/metadataonly1.q.out ql/src/test/results/clientpositive/metadataonly1.q.out index a7dc080..66a7ee8 100644 --- ql/src/test/results/clientpositive/metadataonly1.q.out +++ ql/src/test/results/clientpositive/metadataonly1.q.out @@ -128,10 +128,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -142,9 +142,9 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [$hdt$_0:$hdt$_0:test1] Path -> Partition: - -mr-10002default.test1{ds=1} + -mr-10003default.test1{ds=1} Partition base file name: ds=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -185,7 +185,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [$hdt$_0:$hdt$_0:test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -273,11 +273,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(DISTINCT ds) - keys: ds (type: string) + aggregations: count(DISTINCT _col0) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -288,9 +288,9 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [$hdt$_0:$hdt$_0:test1] Path -> Partition: - -mr-10002default.test1{ds=1} + -mr-10003default.test1{ds=1} Partition base file name: ds=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -331,7 +331,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [$hdt$_0:$hdt$_0:test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -419,10 +419,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(ds) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -476,7 +476,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - /test1/ds=1 [test1] + /test1/ds=1 [$hdt$_0:$hdt$_0:test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -597,15 +597,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: test1 + alias: a2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -616,10 +616,10 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10004default.test1{ds=1} [b:test1] - -mr-10005default.test1{ds=2} [b:test1] + -mr-10005default.test1{ds=1} [$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a2] + -mr-10006default.test1{ds=2} [$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a2] Path -> Partition: - -mr-10004default.test1{ds=1} + -mr-10005default.test1{ds=1} Partition base file name: ds=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -659,7 +659,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 - -mr-10005default.test1{ds=2} + -mr-10006default.test1{ds=2} Partition base file name: ds=2 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -700,8 +700,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10004default.test1{ds=1} [b:test1] - -mr-10005default.test1{ds=2} [b:test1] + -mr-10005default.test1{ds=1} [$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a2] + -mr-10006default.test1{ds=2} [$hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -751,19 +751,23 @@ STAGE PLANS: alias: a2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE GatherStats: false - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 0 - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + tag: 0 + 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-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -862,8 +866,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - /test1/ds=1 [a2] - /test1/ds=2 [a2] + /test1/ds=1 [$hdt$_0:$hdt$_0:$hdt$_0:a2] + /test1/ds=2 [$hdt$_0:$hdt$_0:$hdt$_0:a2] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -915,7 +919,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -1059,11 +1063,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: ds, hr + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(DISTINCT hr) - keys: ds (type: string), hr (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -1075,11 +1079,11 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10002default.test2{ds=1, hr=1} [test2] - -mr-10003default.test2{ds=1, hr=2} [test2] - -mr-10004default.test2{ds=1, hr=3} [test2] + -mr-10003default.test2{ds=1, hr=1} [$hdt$_0:$hdt$_0:test2] + -mr-10004default.test2{ds=1, hr=2} [$hdt$_0:$hdt$_0:test2] + -mr-10005default.test2{ds=1, hr=3} [$hdt$_0:$hdt$_0:test2] Path -> Partition: - -mr-10002default.test2{ds=1, hr=1} + -mr-10003default.test2{ds=1, hr=1} Partition base file name: hr=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1120,7 +1124,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10003default.test2{ds=1, hr=2} + -mr-10004default.test2{ds=1, hr=2} Partition base file name: hr=2 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1161,7 +1165,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10004default.test2{ds=1, hr=3} + -mr-10005default.test2{ds=1, hr=3} Partition base file name: hr=3 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1203,9 +1207,9 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -mr-10002default.test2{ds=1, hr=1} [test2] - -mr-10003default.test2{ds=1, hr=2} [test2] - -mr-10004default.test2{ds=1, hr=3} [test2] + -mr-10003default.test2{ds=1, hr=1} [$hdt$_0:$hdt$_0:test2] + -mr-10004default.test2{ds=1, hr=2} [$hdt$_0:$hdt$_0:test2] + -mr-10005default.test2{ds=1, hr=3} [$hdt$_0:$hdt$_0:test2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1304,11 +1308,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: ds, hr + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(hr) - keys: ds (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -1447,9 +1451,9 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - /test2/ds=1/hr=1 [test2] - /test2/ds=1/hr=2 [test2] - /test2/ds=1/hr=3 [test2] + /test2/ds=1/hr=1 [$hdt$_0:$hdt$_0:test2] + /test2/ds=1/hr=2 [$hdt$_0:$hdt$_0:test2] + /test2/ds=1/hr=3 [$hdt$_0:$hdt$_0:test2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1541,10 +1545,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1555,10 +1559,10 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10002default.test1{ds=1} [test1] - -mr-10003default.test1{ds=2} [test1] + -mr-10003default.test1{ds=1} [$hdt$_0:$hdt$_0:test1] + -mr-10004default.test1{ds=2} [$hdt$_0:$hdt$_0:test1] Path -> Partition: - -mr-10002default.test1{ds=1} + -mr-10003default.test1{ds=1} Partition base file name: ds=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1598,7 +1602,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 - -mr-10003default.test1{ds=2} + -mr-10004default.test1{ds=2} Partition base file name: ds=2 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1639,8 +1643,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10002default.test1{ds=1} [test1] - -mr-10003default.test1{ds=2} [test1] + -mr-10003default.test1{ds=1} [$hdt$_0:$hdt$_0:test1] + -mr-10004default.test1{ds=2} [$hdt$_0:$hdt$_0:test1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1787,11 +1791,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: ds, hr + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(DISTINCT hr) - keys: ds (type: string), hr (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -1803,13 +1807,13 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -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] + -mr-10003default.test2{ds=01_10_10, hr=01} [$hdt$_0:$hdt$_0:test2] + -mr-10004default.test2{ds=01_10_20, hr=02} [$hdt$_0:$hdt$_0:test2] + -mr-10005default.test2{ds=1, hr=1} [$hdt$_0:$hdt$_0:test2] + -mr-10006default.test2{ds=1, hr=2} [$hdt$_0:$hdt$_0:test2] + -mr-10007default.test2{ds=1, hr=3} [$hdt$_0:$hdt$_0:test2] Path -> Partition: - -mr-10002default.test2{ds=01_10_10, hr=01} + -mr-10003default.test2{ds=01_10_10, hr=01} Partition base file name: hr=01 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1850,7 +1854,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10003default.test2{ds=01_10_20, hr=02} + -mr-10004default.test2{ds=01_10_20, hr=02} Partition base file name: hr=02 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1891,7 +1895,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10004default.test2{ds=1, hr=1} + -mr-10005default.test2{ds=1, hr=1} Partition base file name: hr=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1932,7 +1936,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10005default.test2{ds=1, hr=2} + -mr-10006default.test2{ds=1, hr=2} Partition base file name: hr=2 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1973,7 +1977,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10006default.test2{ds=1, hr=3} + -mr-10007default.test2{ds=1, hr=3} Partition base file name: hr=3 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -2015,11 +2019,11 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -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] + -mr-10003default.test2{ds=01_10_10, hr=01} [$hdt$_0:$hdt$_0:test2] + -mr-10004default.test2{ds=01_10_20, hr=02} [$hdt$_0:$hdt$_0:test2] + -mr-10005default.test2{ds=1, hr=1} [$hdt$_0:$hdt$_0:test2] + -mr-10006default.test2{ds=1, hr=2} [$hdt$_0:$hdt$_0:test2] + -mr-10007default.test2{ds=1, hr=3} [$hdt$_0:$hdt$_0:test2] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/multiMapJoin2.q.out ql/src/test/results/clientpositive/multiMapJoin2.q.out index ac3cd1e..9a7fa43 100644 --- ql/src/test/results/clientpositive/multiMapJoin2.q.out +++ ql/src/test/results/clientpositive/multiMapJoin2.q.out @@ -23,107 +23,123 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:tmp-subquery1:y1 + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 - null-subquery2:tmp-subquery2:y2 + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:tmp-subquery1:y1 + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_1:y1 TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - null-subquery2:tmp-subquery2:y2 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:y1 TableScan - alias: y2 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x2 + alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE TableScan alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (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: @@ -278,24 +294,28 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:tmp-subquery1:y1 + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:tmp-subquery1:y1 + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:y1 TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-7 Map Reduce @@ -306,51 +326,59 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - File Output Operator - compressed: false - table: - input format: 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 Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery2:tmp-subquery2:y2 + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery2:tmp-subquery2:y2 + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_1:y1 TableScan - alias: y2 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -367,36 +395,40 @@ STAGE PLANS: sort order: + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x2 + alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (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: @@ -537,13 +569,13 @@ FROM (SELECT x1.key AS key FROM src1 x1 GROUP BY x1.key ORDER BY tmp.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-6 depends on stages: Stage-4 + Stage-1 is a root stage + Stage-6 depends on stages: Stage-1 Stage-2 depends on stages: Stage-6 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-4 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan @@ -551,10 +583,10 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -583,24 +615,28 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery2:tmp-subquery2:y2 + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:x1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery2:tmp-subquery2:y2 + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:x1 TableScan - alias: y2 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -622,31 +658,35 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (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: @@ -686,7 +726,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 #### A masked pattern was here #### -RUN: Stage-4:MAPRED +RUN: Stage-1:MAPRED RUN: Stage-6:MAPREDLOCAL RUN: Stage-2:MAPRED @@ -783,7 +823,7 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-17 is a root stage Stage-2 depends on stages: Stage-17 - Stage-12 depends on stages: Stage-2, Stage-8 , consists of Stage-15, Stage-16, Stage-3 + Stage-12 depends on stages: Stage-2, Stage-7 , consists of Stage-15, Stage-16, Stage-3 Stage-15 has a backup stage: Stage-3 Stage-10 depends on stages: Stage-15 Stage-4 depends on stages: Stage-3, Stage-10, Stage-11 @@ -792,66 +832,74 @@ STAGE DEPENDENCIES: Stage-11 depends on stages: Stage-16 Stage-3 Stage-18 is a root stage - Stage-8 depends on stages: Stage-18 + Stage-7 depends on stages: Stage-18 Stage-0 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-17 Map Reduce Local Work Alias -> Map Local Tables: - tmp2:y2 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp2:y2 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 TableScan - alias: y2 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x2 + alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -877,11 +925,11 @@ STAGE PLANS: Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: - $INTNAME + $hdt$_0:$hdt$_0:$INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $INTNAME + $hdt$_0:$hdt$_0:$INTNAME1 TableScan HashTable Sink Operator condition expressions: @@ -974,11 +1022,11 @@ STAGE PLANS: Stage: Stage-16 Map Reduce Local Work Alias -> Map Local Tables: - $INTNAME1 + $hdt$_0:$hdt$_0:$INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $INTNAME1 + $hdt$_0:$hdt$_0:$INTNAME TableScan HashTable Sink Operator condition expressions: @@ -1063,26 +1111,30 @@ STAGE PLANS: Stage: Stage-18 Map Reduce Local Work Alias -> Map Local Tables: - tmp1:y1 + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp1:y1 + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2:y1 TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-8 + Stage: Stage-7 Map Reduce Map Operator Tree: TableScan @@ -1091,31 +1143,35 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1172,7 +1228,7 @@ POSTHOOK: Input: default@src1 RUN: Stage-17:MAPREDLOCAL RUN: Stage-18:MAPREDLOCAL RUN: Stage-2:MAPRED -RUN: Stage-8:MAPRED +RUN: Stage-7:MAPRED RUN: Stage-12:CONDITIONAL RUN: Stage-16:MAPREDLOCAL RUN: Stage-11:MAPRED @@ -1235,107 +1291,123 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - tmp1:y1 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 Fetch Operator limit: -1 - tmp2:y2 + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp1:y1 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 TableScan alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - tmp2:y2 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + $hdt$_0:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_2:y1 TableScan - alias: y2 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x2 + alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 TableScan alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1561,10 +1633,10 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -1596,15 +1668,15 @@ STAGE PLANS: Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: - $INTNAME + $hdt$_0:$hdt$_0:$INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $INTNAME + $hdt$_0:$hdt$_0:$INTNAME1 TableScan HashTable Sink Operator condition expressions: - 0 {_col0} + 0 1 keys: 0 _col0 (type: string) @@ -1618,14 +1690,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} - 1 + 0 + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0 + outputColumnNames: _col1 Select Operator - expressions: _col0 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Group By Operator aggregations: count() @@ -1693,16 +1765,16 @@ STAGE PLANS: Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: - $INTNAME1 + $hdt$_0:$hdt$_0:$INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $INTNAME1 + $hdt$_0:$hdt$_0:$INTNAME TableScan HashTable Sink Operator condition expressions: 0 - 1 + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) @@ -1715,14 +1787,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} - 1 + 0 + 1 {_col0} keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0 + outputColumnNames: _col1 Select Operator - expressions: _col0 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Group By Operator aggregations: count() @@ -1758,12 +1830,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1782,24 +1854,28 @@ STAGE PLANS: Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - tmp2:y2 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp2:y2 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 TableScan - alias: y2 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -1810,31 +1886,35 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1892,8 +1972,8 @@ RUN: Stage-7:MAPRED RUN: Stage-14:MAPREDLOCAL RUN: Stage-2:MAPRED RUN: Stage-10:CONDITIONAL -RUN: Stage-12:MAPREDLOCAL -RUN: Stage-8:MAPRED +RUN: Stage-13:MAPREDLOCAL +RUN: Stage-9:MAPRED RUN: Stage-4:MAPRED RUN: Stage-5:MAPRED 128 1 @@ -1953,24 +2033,28 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - tmp2:y2 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp2:y2 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 TableScan - alias: y2 + alias: 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 - HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -1983,10 +2067,10 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -2001,31 +2085,35 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2046,12 +2134,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator @@ -2087,12 +2175,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Mux Operator @@ -2368,69 +2456,77 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-17 is a root stage Stage-2 depends on stages: Stage-17 - Stage-16 depends on stages: Stage-2, Stage-7 + Stage-16 depends on stages: Stage-2, Stage-6 Stage-4 depends on stages: Stage-16 Stage-18 is a root stage - Stage-7 depends on stages: Stage-18 + Stage-6 depends on stages: Stage-18 Stage-0 depends on stages: Stage-4 STAGE PLANS: Stage: Stage-17 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery2:x-subquery2:tmp:a + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery2:x-subquery2:tmp:a + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: b + 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2453,41 +2549,49 @@ STAGE PLANS: Stage: Stage-16 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:x-subquery1:c + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_0:a Fetch Operator limit: -1 - null-subquery2:x-subquery2:c + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:x-subquery1:c + null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_0:a TableScan - alias: c + 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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 _col0 (type: string) - 1 key (type: string) - null-subquery2:x-subquery2:c + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:a TableScan - alias: c + 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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 _col0 (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-4 Map Reduce @@ -2497,15 +2601,15 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {key} + 0 {_col0} + 1 keys: 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col1 + 1 _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Union @@ -2526,15 +2630,15 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {key} + 0 {_col0} + 1 keys: 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col1 + 1 _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Union @@ -2556,59 +2660,67 @@ STAGE PLANS: Stage: Stage-18 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:x-subquery1:tmp:a + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:x-subquery1:tmp:a + null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:$hdt$_1: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 - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) - Stage: Stage-7 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: b + 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 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 - Group By Operator - keys: _col0 (type: string) - mode: hash + 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 + 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 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2661,7 +2773,7 @@ POSTHOOK: Input: default@src RUN: Stage-17:MAPREDLOCAL RUN: Stage-18:MAPREDLOCAL RUN: Stage-2:MAPRED -RUN: Stage-7:MAPRED +RUN: Stage-6:MAPRED RUN: Stage-16:MAPREDLOCAL RUN: Stage-4:MAPRED 0 diff --git ql/src/test/results/clientpositive/noalias_subq1.q.out ql/src/test/results/clientpositive/noalias_subq1.q.out index 9f618b2..91c0138 100644 --- ql/src/test/results/clientpositive/noalias_subq1.q.out +++ ql/src/test/results/clientpositive/noalias_subq1.q.out @@ -16,7 +16,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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) diff --git ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out index b69e1ae..43358be 100644 --- ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out +++ ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out @@ -20,11 +20,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (key + 1) (type: double) + expressions: (UDFToDouble(key) + 1.0) (type: double) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (_col0 + 1) (type: double) + expressions: _col0 (type: double), (_col0 + 1.0) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -41,7 +41,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [tmp2, tmp3]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2: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 @@ -152,7 +152,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [tmp2, tmp3]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2: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 * @@ -200,7 +200,7 @@ POSTHOOK: Input: default@src1 406 val_406 25 66 val_66 25 98 val_98 25 -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-4:MAPRED' is a cross product +Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-4: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 @@ -267,11 +267,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - tmp4:tmp2:tmp1:src1 + $hdt$_0:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - tmp4:tmp2:tmp1:src1 + $hdt$_0:src1 TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -322,7 +322,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-4:MAPRED' is a cross product +Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-4: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 ql/src/test/results/clientpositive/nonmr_fetch.q.out ql/src/test/results/clientpositive/nonmr_fetch.q.out index c6a4318..09c518a 100644 --- ql/src/test/results/clientpositive/nonmr_fetch.q.out +++ ql/src/test/results/clientpositive/nonmr_fetch.q.out @@ -137,39 +137,27 @@ POSTHOOK: query: -- negative, filter on non-partition column explain select * from srcpart where key > 100 limit 10 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: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key > 100) (type: boolean) - 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 - Statistics: Num rows: 666 Data size: 7075 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 - 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 limit: 10 Processor Tree: - ListSink + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + 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 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: select * from srcpart where key > 100 limit 10 PREHOOK: type: QUERY @@ -403,7 +391,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) + 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) @@ -496,7 +484,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 10) (type: boolean) + 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), BLOCK__OFFSET__INSIDE__FILE (type: bigint) @@ -543,7 +531,7 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 10) (type: boolean) + predicate: (UDFToDouble(key) < 10.0) (type: boolean) 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) @@ -805,7 +793,7 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rand() > 1) (type: boolean) + 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) @@ -844,11 +832,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -902,10 +890,10 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1067,29 +1055,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Join Operator condition map: @@ -1097,10 +1093,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + 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 File Output Operator diff --git ql/src/test/results/clientpositive/nullgroup.q.out ql/src/test/results/clientpositive/nullgroup.q.out index ffc2347..25a0275 100644 --- ql/src/test/results/clientpositive/nullgroup.q.out +++ ql/src/test/results/clientpositive/nullgroup.q.out @@ -16,12 +16,14 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -80,12 +82,14 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -145,17 +149,20 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: _col0 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: _col0 (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 @@ -225,16 +232,19 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: _col0 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: int) Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count(VALUE._col0) mode: complete outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/nullgroup2.q.out ql/src/test/results/clientpositive/nullgroup2.q.out index cb92904..c4df10e 100644 --- ql/src/test/results/clientpositive/nullgroup2.q.out +++ ql/src/test/results/clientpositive/nullgroup2.q.out @@ -17,15 +17,15 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -110,15 +110,15 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -180,20 +180,21 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (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: _col1 (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 @@ -266,20 +267,21 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 9999) (type: boolean) + 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: key (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (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 diff --git ql/src/test/results/clientpositive/nullgroup3.q.out ql/src/test/results/clientpositive/nullgroup3.q.out index 54657a8..5b96d62 100644 --- ql/src/test/results/clientpositive/nullgroup3.q.out +++ ql/src/test/results/clientpositive/nullgroup3.q.out @@ -42,9 +42,11 @@ STAGE PLANS: alias: tstparttbl Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -133,9 +135,11 @@ STAGE PLANS: alias: tstparttbl2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -232,9 +236,11 @@ STAGE PLANS: alias: tstparttbl Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -331,9 +337,11 @@ STAGE PLANS: alias: tstparttbl2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/nullgroup4.q.out ql/src/test/results/clientpositive/nullgroup4.q.out index a4ec2cd..b2ba216 100644 --- ql/src/test/results/clientpositive/nullgroup4.q.out +++ ql/src/test/results/clientpositive/nullgroup4.q.out @@ -17,15 +17,15 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 9999) (type: boolean) + 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: value + expressions: 1 (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT value) - keys: value (type: string) + aggregations: count(_col0), count(DISTINCT _col1) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -107,15 +107,15 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 9999) (type: boolean) + 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: value + expressions: 1 (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT value) - keys: value (type: string) + aggregations: count(_col0), count(DISTINCT _col1) + keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -176,20 +176,21 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 9999) (type: boolean) + 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: value + expressions: 1 (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: value (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: value (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(VALUE._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 @@ -259,19 +260,20 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 9999) (type: boolean) + 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: value + expressions: 1 (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: value (type: string) + key expressions: _col1 (type: string) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out index ef8f54d..89f7340 100644 --- ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out +++ ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out @@ -16,15 +16,15 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 9999) (type: boolean) + 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: value + expressions: 1 (type: int), value (type: string), substr(value, 5) (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT value), count(DISTINCT substr(value, 5)) - keys: value (type: string), substr(value, 5) (type: string) + aggregations: count(_col0), count(DISTINCT _col1), count(DISTINCT _col2) + keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -84,19 +84,20 @@ STAGE PLANS: alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 9999) (type: boolean) + 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: value + expressions: 1 (type: int), value (type: string), substr(value, 5) (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: value (type: string), substr(value, 5) (type: string) + key expressions: _col1 (type: string), _col2 (type: string) sort order: ++ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) + aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/num_op_type_conv.q.out ql/src/test/results/clientpositive/num_op_type_conv.q.out index f22d957..708fb51 100644 --- ql/src/test/results/clientpositive/num_op_type_conv.q.out +++ ql/src/test/results/clientpositive/num_op_type_conv.q.out @@ -20,7 +20,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: (null + 7) (type: double), (1.0 - null) (type: double), (null + null) (type: double), 1 (type: bigint), 0 (type: bigint), 0.0 (type: double) + expressions: (UDFToDouble(null) + 7.0) (type: double), (1.0 - UDFToDouble(null)) (type: double), (UDFToDouble(null) + UDFToDouble(null)) (type: double), 1 (type: bigint), 0 (type: bigint), 0.0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 500 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE Limit diff --git ql/src/test/results/clientpositive/optimize_nullscan.q.out ql/src/test/results/clientpositive/optimize_nullscan.q.out index fd77ad2..fd9e702 100644 --- ql/src/test/results/clientpositive/optimize_nullscan.q.out +++ ql/src/test/results/clientpositive/optimize_nullscan.q.out @@ -69,9 +69,9 @@ STAGE PLANS: GatherStats: false MultiFileSpray: false Path -> Alias: - -mr-10002default.src{} [src] + -mr-10003default.src{} [src] Path -> Partition: - -mr-10002default.src{} + -mr-10003default.src{} Partition base file name: src input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -116,7 +116,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - -mr-10002default.src{} [src] + -mr-10003default.src{} [src] Stage: Stage-0 Fetch Operator @@ -309,12 +309,12 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10004default.srcpart{ds=2008-04-08, hr=11} [b:srcpart] - -mr-10005default.srcpart{ds=2008-04-08, hr=12} [b:srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=11} [b:srcpart] - -mr-10007default.srcpart{ds=2008-04-09, hr=12} [b:srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=11} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] + -mr-10006default.srcpart{ds=2008-04-08, hr=12} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=11} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] + -mr-10008default.srcpart{ds=2008-04-09, hr=12} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] Path -> Partition: - -mr-10004default.srcpart{ds=2008-04-08, hr=11} + -mr-10005default.srcpart{ds=2008-04-08, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -360,7 +360,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10005default.srcpart{ds=2008-04-08, hr=12} + -mr-10006default.srcpart{ds=2008-04-08, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -406,7 +406,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10006default.srcpart{ds=2008-04-09, hr=11} + -mr-10007default.srcpart{ds=2008-04-09, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -452,7 +452,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10007default.srcpart{ds=2008-04-09, hr=12} + -mr-10008default.srcpart{ds=2008-04-09, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -499,10 +499,10 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - -mr-10004default.srcpart{ds=2008-04-08, hr=11} [b:srcpart] - -mr-10005default.srcpart{ds=2008-04-08, hr=12} [b:srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=11} [b:srcpart] - -mr-10007default.srcpart{ds=2008-04-09, hr=12} [b:srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=11} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] + -mr-10006default.srcpart{ds=2008-04-08, hr=12} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=11} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] + -mr-10008default.srcpart{ds=2008-04-09, hr=12} [$hdt$_0:$hdt$_0:$hdt$_0:srcpart] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -512,23 +512,27 @@ STAGE PLANS: Limit Number of rows: 0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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 - 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 + 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-1 Map Reduce @@ -540,7 +544,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 1 + tag: 0 auto parallelism: false TableScan alias: src @@ -559,13 +563,13 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 0 + tag: 1 auto parallelism: false Path -> Alias: - -mr-10003default.src{} [a:src] + -mr-10004default.src{} [$hdt$_0:$hdt$_1:src] #### A masked pattern was here #### Path -> Partition: - -mr-10003default.src{} + -mr-10004default.src{} Partition base file name: src input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -611,7 +615,7 @@ STAGE PLANS: name: default.src #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -630,20 +634,20 @@ STAGE PLANS: serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: - -mr-10003default.src{} [a:src] + -mr-10004default.src{} [$hdt$_0:$hdt$_1:src] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -757,35 +761,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(key) - mode: hash + Filter Operator + isSamplingPred: false + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count(_col0) + 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: -#### A masked pattern was here #### + -mr-10005default.src{} [null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_0:src] Path -> Partition: -#### A masked pattern was here #### + -mr-10005default.src{} Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat + base file name: src + input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat 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 @@ -793,90 +798,208 @@ STAGE PLANS: columns.comments defaultdefault columns.types string:string #### A masked pattern was here #### - name default.srcpart + name default.src numFiles 1 numRows 500 - partition_columns ds/hr - partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} + serialization.ddl struct src { string key, string value} serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe totalSize 5812 #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.NullStructSerDe 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 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} + 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.srcpart - name: default.srcpart + name: default.src + name: default.src + Truncated Path -> Alias: + -mr-10005default.src{} [null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_0:src] + 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 + 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 + Map Operator Tree: + TableScan + GatherStats: false + Union + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + 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 #### + 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.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 + 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 #### + 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.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: #### 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 + base file name: -mr-10003 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments defaultdefault - 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 + columns _col0 + columns.types bigint + 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 _col0 + columns.types bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Partition + base file name: -mr-10004 + 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 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - bucket_count -1 - columns key,value - columns.comments defaultdefault - columns.types string:string + columns _col0 + columns.types bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Truncated Path -> Alias: #### 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 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_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 + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false + Path -> Alias: #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + 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 2008-04-09 + ds 2008-04-08 hr 11 properties: COLUMN_STATS_ACCURATE true @@ -922,7 +1045,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: - ds 2008-04-09 + ds 2008-04-08 hr 12 properties: COLUMN_STATS_ACCURATE true @@ -960,183 +1083,62 @@ STAGE PLANS: 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 [null-subquery2:_u1-subquery2:srcpart] - /srcpart/ds=2008-04-08/hr=12 [null-subquery2:_u1-subquery2:srcpart] - /srcpart/ds=2008-04-09/hr=11 [null-subquery2:_u1-subquery2:srcpart] - /srcpart/ds=2008-04-09/hr=12 [null-subquery2:_u1-subquery2:srcpart] - 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 - 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 - Map Operator Tree: - TableScan - GatherStats: false - Union - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE - 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 #### - 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.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 - 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 #### - 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.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: + name: default.srcpart + name: default.srcpart #### A masked pattern was here #### Partition - base file name: -mr-10002 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + 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: - columns _col0 - columns.types bigint - 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 _col0 - columns.types bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string #### A masked pattern was here #### - Partition - 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.types bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 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 - Truncated Path -> Alias: + 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 #### - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: - 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: - -mr-10004default.src{} Partition - base file name: src - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat + 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 @@ -1144,40 +1146,42 @@ STAGE PLANS: columns.comments defaultdefault 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.NullStructSerDe + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe + 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 defaultdefault 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: - -mr-10004default.src{} [null-subquery1:_u1-subquery1:src] + /srcpart/ds=2008-04-08/hr=11 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=11 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=12 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1233,7 +1237,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 2000 0 -Warning: Shuffle Join JOIN[11][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain extended select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b PREHOOK: type: QUERY @@ -1315,12 +1319,12 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10004default.srcpart{ds=2008-04-08, hr=11} [b:srcpart] - -mr-10005default.srcpart{ds=2008-04-08, hr=12} [b:srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=11} [b:srcpart] - -mr-10007default.srcpart{ds=2008-04-09, hr=12} [b:srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=11} [$hdt$_0:$hdt$_0:srcpart] + -mr-10006default.srcpart{ds=2008-04-08, hr=12} [$hdt$_0:$hdt$_0:srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=11} [$hdt$_0:$hdt$_0:srcpart] + -mr-10008default.srcpart{ds=2008-04-09, hr=12} [$hdt$_0:$hdt$_0:srcpart] Path -> Partition: - -mr-10004default.srcpart{ds=2008-04-08, hr=11} + -mr-10005default.srcpart{ds=2008-04-08, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1366,7 +1370,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10005default.srcpart{ds=2008-04-08, hr=12} + -mr-10006default.srcpart{ds=2008-04-08, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1412,7 +1416,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10006default.srcpart{ds=2008-04-09, hr=11} + -mr-10007default.srcpart{ds=2008-04-09, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1458,7 +1462,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10007default.srcpart{ds=2008-04-09, hr=12} + -mr-10008default.srcpart{ds=2008-04-09, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1505,10 +1509,10 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - -mr-10004default.srcpart{ds=2008-04-08, hr=11} [b:srcpart] - -mr-10005default.srcpart{ds=2008-04-08, hr=12} [b:srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=11} [b:srcpart] - -mr-10007default.srcpart{ds=2008-04-09, hr=12} [b:srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=11} [$hdt$_0:$hdt$_0:srcpart] + -mr-10006default.srcpart{ds=2008-04-08, hr=12} [$hdt$_0:$hdt$_0:srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=11} [$hdt$_0:$hdt$_0:srcpart] + -mr-10008default.srcpart{ds=2008-04-09, hr=12} [$hdt$_0:$hdt$_0:srcpart] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -1518,23 +1522,27 @@ STAGE PLANS: Limit Number of rows: 0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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 - 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 + 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-1 Map Reduce @@ -1544,7 +1552,7 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 1 + tag: 0 value expressions: _col0 (type: string) auto parallelism: false TableScan @@ -1562,14 +1570,14 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 0 + tag: 1 value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10003default.src{} [a:src] + -mr-10004default.src{} [$hdt$_1:src] #### A masked pattern was here #### Path -> Partition: - -mr-10003default.src{} + -mr-10004default.src{} Partition base file name: src input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1615,7 +1623,7 @@ STAGE PLANS: name: default.src #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -1634,20 +1642,25 @@ STAGE PLANS: serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: - -mr-10003default.src{} [a:src] + -mr-10004default.src{} [$hdt$_1:src] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: 0 {VALUE._col0} 1 {VALUE._col0} + filter mappings: + 1 [0, 1] + filter predicates: + 0 + 1 {true} outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -1678,7 +1691,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -1775,31 +1788,44 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: 1 - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + tag: 0 + auto parallelism: false TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + Filter Operator + isSamplingPred: false + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + tag: 1 + auto parallelism: false Path -> Alias: + -mr-10005default.src{} [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:src] #### A masked pattern was here #### Path -> Partition: -#### A masked pattern was here #### + -mr-10005default.src{} Partition base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat + input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: COLUMN_STATS_ACCURATE true @@ -1814,10 +1840,10 @@ STAGE PLANS: rawDataSize 5312 serialization.ddl struct src { string key, string value} serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe totalSize 5812 #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.NullStructSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2025,46 +2051,42 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [null-subquery2:a-subquery2:src] - /srcpart/ds=2008-04-08/hr=11 [null-subquery2:a-subquery2:srcpart] - /srcpart/ds=2008-04-08/hr=12 [null-subquery2:a-subquery2:srcpart] - /srcpart/ds=2008-04-09/hr=11 [null-subquery2:a-subquery2:srcpart] - /srcpart/ds=2008-04-09/hr=12 [null-subquery2:a-subquery2:srcpart] + -mr-10005default.src{} [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:src] + /srcpart/ds=2008-04-08/hr=11 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=11 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=12 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:srcpart] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2200 Data size: 23372 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 + 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 @@ -2072,17 +2094,17 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE 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 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2111,17 +2133,17 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Union - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE 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 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2138,10 +2160,10 @@ STAGE PLANS: GatherStats: false MultiFileSpray: false Path -> Alias: - -mr-10003default.src{} [null-subquery1:a-subquery1:src] + -mr-10004default.src{} [null-subquery1:$hdt$_0-subquery1:src] #### A masked pattern was here #### Path -> Partition: - -mr-10003default.src{} + -mr-10004default.src{} Partition base file name: src input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -2187,7 +2209,7 @@ STAGE PLANS: name: default.src #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -2206,7 +2228,7 @@ STAGE PLANS: serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: - -mr-10003default.src{} [null-subquery1:a-subquery1:src] + -mr-10004default.src{} [null-subquery1:$hdt$_0-subquery1:src] #### A masked pattern was here #### Stage: Stage-0 diff --git ql/src/test/results/clientpositive/optional_outer.q.out ql/src/test/results/clientpositive/optional_outer.q.out index f1b4aff..e5eea4d 100644 --- ql/src/test/results/clientpositive/optional_outer.q.out +++ ql/src/test/results/clientpositive/optional_outer.q.out @@ -11,23 +11,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -35,10 +43,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -68,23 +76,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -92,10 +108,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -125,34 +141,42 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -182,34 +206,42 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -239,23 +271,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -263,10 +303,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -296,23 +336,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -320,10 +368,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out index 359d4ac..b770c6d 100644 --- ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out +++ ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out @@ -137,11 +137,11 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: t (type: tinyint) - outputColumnNames: t + expressions: hash(t) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(t)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -189,11 +189,11 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: t (type: tinyint) - outputColumnNames: t + expressions: hash(t) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(t)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -321,14 +321,14 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((t < 0) and (t > -2)) (type: boolean) + predicate: ((t < 0) and (UDFToInteger(t) > -2)) (type: boolean) Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: t (type: tinyint) - outputColumnNames: t + expressions: hash(t) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(t)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -380,17 +380,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - filterExpr: ((t < 0) and (t > -2)) (type: boolean) + filterExpr: ((t < 0) and (UDFToInteger(t) > -2)) (type: boolean) Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((t < 0) and (t > -2)) (type: boolean) + predicate: ((t < 0) and (UDFToInteger(t) > -2)) (type: boolean) Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: t (type: tinyint) - outputColumnNames: t + expressions: hash(t) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(t)) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/order2.q.out ql/src/test/results/clientpositive/order2.q.out index 3423a76..b86e9a7 100644 --- ql/src/test/results/clientpositive/order2.q.out +++ ql/src/test/results/clientpositive/order2.q.out @@ -37,7 +37,7 @@ STAGE PLANS: Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < 10) (type: boolean) + predicate: (UDFToDouble(_col0) < 10.0) (type: boolean) Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) diff --git ql/src/test/results/clientpositive/outer_join_ppr.q.out ql/src/test/results/clientpositive/outer_join_ppr.q.out index bd735a1..7498251 100644 --- ql/src/test/results/clientpositive/outer_join_ppr.q.out +++ ql/src/test/results/clientpositive/outer_join_ppr.q.out @@ -109,29 +109,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string), ds (type: string) - auto parallelism: false - TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false - 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + 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 + TableScan + alias: b + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -364,11 +372,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /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] + /src [$hdt$_0:$hdt$_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] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:$hdt$_0:b] + /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:$hdt$_0:b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -378,18 +386,18 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} filter mappings: - 1 [0, 1] + 0 [1, 1] filter predicates: - 0 - 1 {(VALUE._col1 = '2008-04-08')} - outputColumnNames: _col0, _col1, _col5, _col6 + 0 {(VALUE._col1 = '2008-04-08')} + 1 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((_col5 > 15) and (_col5 < 25)) and (_col0 > 10)) and (_col0 < 20)) (type: boolean) + predicate: ((((UDFToDouble(_col0) > 15.0) and (UDFToDouble(_col0) < 25.0)) and (UDFToDouble(_col3) > 10.0)) and (UDFToDouble(_col3) < 20.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -573,29 +581,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string), ds (type: string) - auto parallelism: false - TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false - 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + 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 + TableScan + alias: b + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -828,11 +844,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /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] + /src [$hdt$_0:$hdt$_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] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:$hdt$_0:b] + /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:$hdt$_0:b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -840,23 +856,28 @@ STAGE PLANS: Outer Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col5, _col6, _col7 + 1 {KEY.reducesinkkey0} {VALUE._col0} + filter mappings: + 0 [1, 1] + filter predicates: + 0 {(VALUE._col1 = '2008-04-08')} + 1 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (((((_col5 > 15) and (_col5 < 25)) and (_col7 = '2008-04-08')) and (_col0 > 10)) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(_col0) > 15.0) and (UDFToDouble(_col0) < 25.0)) and (UDFToDouble(_col3) > 10.0)) and (UDFToDouble(_col3) < 20.0)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE + 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 - Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE + 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 diff --git ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out index b9cdde1..99d944b 100644 --- ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out +++ ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out @@ -1,10 +1,14 @@ -PREHOOK: query: -- SORT_BEFORE_DIFF +PREHOOK: query: -- Disable CBO since it causes filter pruning to fail to prune in this case + +-- SORT_BEFORE_DIFF create table partition_test_partitioned(key string, value string) partitioned by (dt string) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@partition_test_partitioned -POSTHOOK: query: -- SORT_BEFORE_DIFF +POSTHOOK: query: -- Disable CBO since it causes filter pruning to fail to prune in this case + +-- SORT_BEFORE_DIFF create table partition_test_partitioned(key string, value string) partitioned by (dt string) POSTHOOK: type: CREATETABLE diff --git ql/src/test/results/clientpositive/pcr.q.out ql/src/test/results/clientpositive/pcr.q.out index 568417a..d8d0998 100644 --- ql/src/test/results/clientpositive/pcr.q.out +++ ql/src/test/results/clientpositive/pcr.q.out @@ -475,9 +475,9 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] + /pcr_t1/ds=2000-04-08 [$hdt$_0:pcr_t1] + /pcr_t1/ds=2000-04-09 [$hdt$_0:pcr_t1] + /pcr_t1/ds=2000-04-10 [$hdt$_0:pcr_t1] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -1798,8 +1798,8 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-08 [$hdt$_0:pcr_t1] + /pcr_t1/ds=2000-04-09 [$hdt$_0:pcr_t1] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -2003,8 +2003,8 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-08 [$hdt$_0:pcr_t1] + /pcr_t1/ds=2000-04-09 [$hdt$_0:pcr_t1] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -2293,9 +2293,9 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] + /pcr_t1/ds=2000-04-08 [$hdt$_0:pcr_t1] + /pcr_t1/ds=2000-04-09 [$hdt$_0:pcr_t1] + /pcr_t1/ds=2000-04-10 [$hdt$_0:pcr_t1] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -2825,7 +2825,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -3168,7 +3168,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -5325,7 +5325,7 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -5445,7 +5445,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (key = 11) (type: boolean) + 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) @@ -5668,7 +5668,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (key = 11) (type: boolean) + 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) diff --git ql/src/test/results/clientpositive/plan_json.q.out ql/src/test/results/clientpositive/plan_json.q.out index 9a57bc2..5dc714b 100644 --- ql/src/test/results/clientpositive/plan_json.q.out +++ ql/src/test/results/clientpositive/plan_json.q.out @@ -6,4 +6,4 @@ 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":{"Select Operator":{"expressions:":"_col0 (type: bigint)","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"}},"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:":["_col0"],"children":{"Select Operator":{"expressions:":"_col0 (type: bigint)","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"}},"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:":["_col0"],"children":{"Group By Operator":{"mode:":"hash","aggregations:":["count(_col0)"],"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"}}} diff --git ql/src/test/results/clientpositive/ppd2.q.out ql/src/test/results/clientpositive/ppd2.q.out index 618a545..98a2ffd 100644 --- ql/src/test/results/clientpositive/ppd2.q.out +++ ql/src/test/results/clientpositive/ppd2.q.out @@ -306,24 +306,20 @@ STAGE PLANS: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(key) (type: int), CASE WHEN (((value like 'aaa%') or (value like 'vvv%'))) THEN (1) ELSE (0) END (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col1 > 0) (type: boolean) + 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 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 + File Output Operator + compressed: false Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - 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 diff --git ql/src/test/results/clientpositive/ppd_gby.q.out ql/src/test/results/clientpositive/ppd_gby.q.out index 3a6543b..523842e 100644 --- ql/src/test/results/clientpositive/ppd_gby.q.out +++ ql/src/test/results/clientpositive/ppd_gby.q.out @@ -26,11 +26,11 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key) - keys: value (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE @@ -47,24 +47,20 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 > 'val_200') and ((_col1 > 30) or (_col0 < 'val_400'))) (type: boolean) - Statistics: Num rows: 6 Data size: 63 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 - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - table: - 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: ((_col1 > 30) or (_col0 < '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 + Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -243,11 +239,11 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key) - keys: value (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/ppd_gby2.q.out ql/src/test/results/clientpositive/ppd_gby2.q.out index fd3866b..1ee4b49 100644 --- ql/src/test/results/clientpositive/ppd_gby2.q.out +++ ql/src/test/results/clientpositive/ppd_gby2.q.out @@ -29,11 +29,11 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key) - keys: value (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE @@ -50,29 +50,25 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 > 'val_200') and ((_col1 > 30) or (_col0 < 'val_400'))) (type: boolean) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + Filter Operator + predicate: ((_col1 > 30) or (_col0 < '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 + Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: max(_col1) + keys: _col0 (type: bigint) + mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col0) - keys: _col1 (type: bigint) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - 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: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 @@ -82,7 +78,7 @@ 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: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Group By Operator @@ -90,14 +86,14 @@ STAGE PLANS: keys: KEY._col0 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + 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 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 95 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: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -161,11 +157,11 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key) - keys: value (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE @@ -186,12 +182,12 @@ STAGE PLANS: predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean) Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: _col1 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) - keys: _col1 (type: bigint) + aggregations: max(_col1) + keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/ppd_gby_join.q.out ql/src/test/results/clientpositive/ppd_gby_join.q.out index 01e9466..16b3526 100644 --- ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -31,67 +31,84 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean) - Statistics: Num rows: 9 Data size: 95 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')) and key is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < '400') (type: boolean) - Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + 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 Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < '400') (type: boolean) - Statistics: Num rows: 4 Data size: 42 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: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} + 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Filter Operator + predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) 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 + Select Operator + expressions: _col0 (type: string), 1 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - 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(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 @@ -128,6 +145,157 @@ STAGE PLANS: Processor Tree: ListSink +PREHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +200 4 +201 1 +202 1 +203 4 +205 4 +207 4 +208 9 +209 4 +213 4 +214 1 +216 4 +217 4 +218 1 +219 4 +221 4 +222 1 +223 4 +224 4 +226 1 +228 1 +229 4 +230 25 +233 4 +235 1 +237 4 +238 4 +239 4 +24 4 +241 1 +242 4 +244 1 +247 1 +248 1 +249 1 +252 1 +255 4 +256 4 +257 1 +258 1 +26 4 +260 1 +262 1 +263 1 +265 4 +266 1 +27 1 +272 4 +273 9 +274 1 +275 1 +277 16 +278 4 +28 1 +280 4 +281 4 +282 4 +283 1 +284 1 +285 1 +286 1 +287 1 +288 4 +289 1 +291 1 +292 1 +296 1 +298 9 +30 1 +302 1 +305 1 +306 1 +307 4 +308 1 +309 4 +310 1 +311 9 +315 1 +316 9 +317 4 +318 9 +321 4 +322 4 +323 1 +325 4 +327 9 +33 1 +331 4 +332 1 +333 4 +335 1 +336 1 +338 1 +339 1 +34 1 +341 1 +342 4 +344 4 +345 1 +348 25 +35 9 +351 1 +353 4 +356 1 +360 1 +362 1 +364 1 +365 1 +366 1 +367 4 +368 1 +369 9 +37 4 +373 1 +374 1 +375 1 +377 1 +378 1 +379 1 +382 4 +384 9 +386 1 +389 1 +392 1 +393 1 +394 1 +395 4 +396 9 +397 4 +399 4 PREHOOK: query: EXPLAIN SELECT src1.c1, count(1) FROM @@ -161,55 +329,54 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean) - Statistics: Num rows: 9 Data size: 95 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')) and key is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 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: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + 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 Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 31 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} + 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + expressions: _col0 (type: string), 1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -225,7 +392,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -233,14 +400,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 @@ -252,3 +419,154 @@ STAGE PLANS: Processor Tree: ListSink +PREHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +200 4 +201 1 +202 1 +203 4 +205 4 +207 4 +208 9 +209 4 +213 4 +214 1 +216 4 +217 4 +218 1 +219 4 +221 4 +222 1 +223 4 +224 4 +226 1 +228 1 +229 4 +230 25 +233 4 +235 1 +237 4 +238 4 +239 4 +24 4 +241 1 +242 4 +244 1 +247 1 +248 1 +249 1 +252 1 +255 4 +256 4 +257 1 +258 1 +26 4 +260 1 +262 1 +263 1 +265 4 +266 1 +27 1 +272 4 +273 9 +274 1 +275 1 +277 16 +278 4 +28 1 +280 4 +281 4 +282 4 +283 1 +284 1 +285 1 +286 1 +287 1 +288 4 +289 1 +291 1 +292 1 +296 1 +298 9 +30 1 +302 1 +305 1 +306 1 +307 4 +308 1 +309 4 +310 1 +311 9 +315 1 +316 9 +317 4 +318 9 +321 4 +322 4 +323 1 +325 4 +327 9 +33 1 +331 4 +332 1 +333 4 +335 1 +336 1 +338 1 +339 1 +34 1 +341 1 +342 4 +344 4 +345 1 +348 25 +35 9 +351 1 +353 4 +356 1 +360 1 +362 1 +364 1 +365 1 +366 1 +367 4 +368 1 +369 9 +37 4 +373 1 +374 1 +375 1 +377 1 +378 1 +379 1 +382 4 +384 9 +386 1 +389 1 +392 1 +393 1 +394 1 +395 4 +396 9 +397 4 +399 4 diff --git ql/src/test/results/clientpositive/ppd_join.q.out ql/src/test/results/clientpositive/ppd_join.q.out index dd2531a..2e22615 100644 --- ql/src/test/results/clientpositive/ppd_join.q.out +++ ql/src/test/results/clientpositive/ppd_join.q.out @@ -28,63 +28,80 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean) - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + 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 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < '400') (type: boolean) - Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean) - Statistics: Num rows: 12 Data size: 127 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')) and key is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < '400') (type: boolean) - Statistics: Num rows: 4 Data size: 42 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: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE 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, _col2, _col3 - Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean) + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col2 (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 + 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 @@ -560,53 +577,52 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean) - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + 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 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 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: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 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 Filter Operator - predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean) - Statistics: Num rows: 12 Data size: 127 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')) and key is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 21 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (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 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + predicate: ((_col0 > '50') or (_col2 < '50')) (type: boolean) + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) + expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + 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 diff --git ql/src/test/results/clientpositive/ppd_join2.q.out ql/src/test/results/clientpositive/ppd_join2.q.out index 4e8a803..848008d 100644 --- ql/src/test/results/clientpositive/ppd_join2.q.out +++ ql/src/test/results/clientpositive/ppd_join2.q.out @@ -35,40 +35,54 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key <> '305') and (key < '400')) and key is not null) and (key <> '14')) and (key <> '311')) (type: boolean) + predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) 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 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < '400') (type: boolean) + predicate: ((_col0 <> '302') and ((_col0 <> '311') and (_col0 < '400'))) (type: boolean) Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + 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) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key <> '302') and (key < '400')) and value is not null) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '14')) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + 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: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < '400') (type: boolean) - Statistics: Num rows: 36 Data size: 382 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: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean) + Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col0 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) + 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) Reduce Operator Tree: Join Operator condition map: @@ -77,16 +91,27 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 39 Data size: 420 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 20 Data size: 215 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - 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: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean) + Statistics: Num rows: 30 Data size: 326 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: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col1 is not null (type: boolean) + Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 @@ -96,50 +121,46 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 20 Data size: 215 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) + Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col3 (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13)) (type: boolean) + predicate: (((key <> '306') and (sqrt(key) <> 13.0)) and 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: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + 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: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} {VALUE._col2} - 1 {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 {VALUE._col0} {VALUE._col2} + 1 + outputColumnNames: _col0, _col3 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((((_col0 <> '311') and ((_col1 <> 'val_50') or (_col0 > '1'))) and ((_col2 <> '10') or (_col0 <> '10'))) and (_col2 <> '14')) and (sqrt(_col4) <> 13)) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - 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 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1728,7 +1749,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key <> '305') and (key < '400')) and key is not null) and (key <> '14')) and (key <> '311')) (type: boolean) + predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) 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) @@ -1744,17 +1765,17 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key <> '302') and (key < '400')) and value is not null) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '14')) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + 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: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 594 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: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1764,13 +1785,20 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - 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: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <> '10') or (_col0 <> '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 Stage: Stage-2 Map Reduce @@ -1780,47 +1808,43 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col3 (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13)) (type: boolean) + predicate: (((key <> '306') and (sqrt(key) <> 13.0)) and 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: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} {VALUE._col2} - 1 {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 {VALUE._col0} {VALUE._col2} + 1 + outputColumnNames: _col0, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((((_col0 <> '311') and ((_col1 <> 'val_50') or (_col0 > '1'))) and ((_col2 <> '10') or (_col0 <> '10'))) and (_col2 <> '14')) and (sqrt(_col4) <> 13)) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false 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 + table: + input format: org.apache.hadoop.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 ql/src/test/results/clientpositive/ppd_join_filter.q.out ql/src/test/results/clientpositive/ppd_join_filter.q.out index 15a8a54..dd44aab 100644 --- ql/src/test/results/clientpositive/ppd_join_filter.q.out +++ ql/src/test/results/clientpositive/ppd_join_filter.q.out @@ -129,7 +129,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -138,11 +138,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(key) - keys: key (type: string) + 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 @@ -202,7 +202,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [b:src] + /src [$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -212,12 +212,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double) - outputColumnNames: _col0, _col2, _col3, _col4 + expressions: _col0 (type: string), (UDFToDouble(_col1) + 1.0) (type: double), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col2 < 5.0) and _col0 is not null) (type: boolean) + predicate: ((_col1 < 5.0) and _col0 is not null) (type: boolean) Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -228,7 +228,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -248,13 +248,21 @@ STAGE PLANS: isSamplingPred: false 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + Filter Operator + isSamplingPred: false + 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 + tag: 0 + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -263,18 +271,18 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col3 (type: double), _col4 (type: double) + value expressions: _col2 (type: double), _col3 (type: double) 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-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -283,7 +291,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -333,7 +341,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [a] + /src [$hdt$_0:$hdt$_0:a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -342,19 +350,19 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} - 1 {VALUE._col2} {VALUE._col3} - outputColumnNames: _col0, _col8, _col9 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 1 {VALUE._col1} {VALUE._col2} + outputColumnNames: _col0, _col3, _col4 + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double) + expressions: _col0 (type: string), _col3 (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -542,7 +550,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -551,11 +559,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(key) - keys: key (type: string) + 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 @@ -615,7 +623,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [b:src] + /src [$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -625,12 +633,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double) - outputColumnNames: _col0, _col2, _col3, _col4 + expressions: _col0 (type: string), (UDFToDouble(_col1) + 1.0) (type: double), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (_col2 < 5.0) (type: boolean) + predicate: (_col1 < 5.0) (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -641,7 +649,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -661,13 +669,17 @@ STAGE PLANS: isSamplingPred: false 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + 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: 0 + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -676,18 +688,18 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col3 (type: double), _col4 (type: double) + value expressions: _col2 (type: double), _col3 (type: double) 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-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -696,7 +708,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -746,7 +758,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [a] + /src [$hdt$_0:$hdt$_0:a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -755,11 +767,11 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} - 1 {VALUE._col2} {VALUE._col3} - outputColumnNames: _col0, _col8, _col9 + 1 {VALUE._col1} {VALUE._col2} + outputColumnNames: _col0, _col3, _col4 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double) + expressions: _col0 (type: string), _col3 (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -955,16 +967,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(key) - keys: key (type: string) + 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 @@ -1024,7 +1036,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [b:src] + /src [$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1034,12 +1046,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double) - outputColumnNames: _col0, _col2, _col3, _col4 + expressions: _col0 (type: string), (UDFToDouble(_col1) + 1.0) (type: double), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col2 < 5.0) and _col0 is not null) (type: boolean) + predicate: ((_col1 < 5.0) and _col0 is not null) (type: boolean) Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1050,7 +1062,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1066,17 +1078,21 @@ STAGE PLANS: alias: a 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: _col0 is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + 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: 0 + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -1085,18 +1101,18 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col3 (type: double), _col4 (type: double) + value expressions: _col2 (type: double), _col3 (type: double) 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-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1105,7 +1121,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1155,7 +1171,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [a] + /src [$hdt$_0:$hdt$_0:a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -1164,11 +1180,11 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} - 1 {VALUE._col2} {VALUE._col3} - outputColumnNames: _col0, _col8, _col9 + 1 {VALUE._col1} {VALUE._col2} + outputColumnNames: _col0, _col3, _col4 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double) + expressions: _col0 (type: string), _col3 (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1364,7 +1380,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -1373,11 +1389,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(key) - keys: key (type: string) + 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 @@ -1437,7 +1453,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [b:src] + /src [$hdt$_0:$hdt$_1:$hdt$_1:$hdt$_1:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1447,12 +1463,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double) - outputColumnNames: _col0, _col2, _col3, _col4 + expressions: _col0 (type: string), (UDFToDouble(_col1) + 1.0) (type: double), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (_col2 < 5.0) (type: boolean) + predicate: (_col1 < 5.0) (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1463,7 +1479,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1483,13 +1499,17 @@ STAGE PLANS: isSamplingPred: false 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + 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: 0 + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -1498,18 +1518,18 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col3 (type: double), _col4 (type: double) + value expressions: _col2 (type: double), _col3 (type: double) 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-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1518,7 +1538,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col2,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types string,double,double,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1568,7 +1588,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [a] + /src [$hdt$_0:$hdt$_0:a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -1577,11 +1597,11 @@ STAGE PLANS: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} - 1 {VALUE._col2} {VALUE._col3} - outputColumnNames: _col0, _col8, _col9 + 1 {VALUE._col1} {VALUE._col2} + outputColumnNames: _col0, _col3, _col4 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double) + expressions: _col0 (type: string), _col3 (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/ppd_outer_join1.q.out ql/src/test/results/clientpositive/ppd_outer_join1.q.out index fc314ca..65f6921 100644 --- ql/src/test/results/clientpositive/ppd_outer_join1.q.out +++ ql/src/test/results/clientpositive/ppd_outer_join1.q.out @@ -25,29 +25,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -55,22 +63,26 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col0 > 10) and (_col0 < 20)) and (_col5 > 15)) and (_col5 < 25)) (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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 Stage: Stage-0 Fetch Operator @@ -131,29 +143,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -161,13 +181,13 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col5 > 15) and (_col5 < 25)) (type: boolean) + 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 Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/ppd_outer_join2.q.out ql/src/test/results/clientpositive/ppd_outer_join2.q.out index 9ea48d4..cbe5433 100644 --- ql/src/test/results/clientpositive/ppd_outer_join2.q.out +++ ql/src/test/results/clientpositive/ppd_outer_join2.q.out @@ -25,52 +25,64 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '15') and (key < '25')) (type: boolean) Statistics: Num rows: 55 Data size: 584 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '15') and (key < '25')) (type: boolean) Statistics: Num rows: 55 Data size: 584 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col0 > '10') and (_col0 < '20')) and (_col5 > '15')) and (_col5 < '25')) (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 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 + Select Operator + expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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 Stage: Stage-0 Fetch Operator @@ -251,43 +263,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '15') and (key < '25')) (type: boolean) Statistics: Num rows: 55 Data size: 584 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '15') and (key < '25')) (type: boolean) Statistics: Num rows: 55 Data size: 584 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean) + predicate: ((_col2 > '10') and (_col2 < '20')) (type: boolean) Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/ppd_outer_join3.q.out ql/src/test/results/clientpositive/ppd_outer_join3.q.out index 04f0f12..6c614ee 100644 --- ql/src/test/results/clientpositive/ppd_outer_join3.q.out +++ ql/src/test/results/clientpositive/ppd_outer_join3.q.out @@ -25,23 +25,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -49,22 +57,26 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col0 > '10') and (_col0 < '20')) and (_col5 > '15')) and (_col5 < '25')) (type: boolean) - Statistics: Num rows: 6 Data size: 63 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col0 > '10') and ((_col0 < '20') and ((_col2 > '15') and (_col2 < '25')))) (type: boolean) Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output 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: 63 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -245,23 +257,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: @@ -269,13 +289,13 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((_col5 > '15') and (_col5 < '25')) and (_col0 > '10')) and (_col0 < '20')) (type: boolean) + predicate: ((((_col0 > '10') and (_col0 < '20')) and (_col2 > '15')) and (_col2 < '25')) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/ppd_random.q.out ql/src/test/results/clientpositive/ppd_random.q.out index f21054a..41b53df 100644 --- ql/src/test/results/clientpositive/ppd_random.q.out +++ ql/src/test/results/clientpositive/ppd_random.q.out @@ -28,6 +28,31 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator + predicate: ((key > '2') and (rand() > 0.5)) (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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 > '2') (type: boolean) + Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 9 Data size: 95 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: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + TableScan + alias: 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 @@ -43,47 +68,26 @@ STAGE PLANS: 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) - TableScan - alias: 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 - 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 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col3 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rand() > 0.5) (type: boolean) - Statistics: Num rows: 45 Data size: 479 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 45 Data size: 479 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 45 Data size: 479 Basic stats: COMPLETE Column stats: NONE - table: - 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._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (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 Stage: Stage-0 Fetch Operator @@ -121,56 +125,53 @@ STAGE PLANS: alias: 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 + predicate: ((key > '2') and (rand() > 0.5)) (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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan alias: 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 + 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 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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 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 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rand() > 0.5) (type: boolean) - Statistics: Num rows: 91 Data size: 966 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 966 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 91 Data size: 966 Basic stats: COMPLETE Column stats: NONE - table: - 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._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 + 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: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + 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 diff --git ql/src/test/results/clientpositive/ppd_udf_case.q.out ql/src/test/results/clientpositive/ppd_udf_case.q.out index 1826993..c069d81 100644 --- ql/src/test/results/clientpositive/ppd_udf_case.q.out +++ ql/src/test/results/clientpositive/ppd_udf_case.q.out @@ -34,29 +34,50 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) + predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (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), hr (type: string) + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string), hr (type: string) + 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 + value expressions: _col1 (type: string), _col3 (type: string) TableScan alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) + predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (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), hr (type: string) + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string), hr (type: string) + 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col3 + 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) Reduce Operator Tree: Join Operator condition map: @@ -64,38 +85,35 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col2} 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col2} - outputColumnNames: _col0, _col1, _col3, _col7, _col8, _col10 - Statistics: Num rows: 275 Data size: 2921 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: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col7 (type: string), _col8 (type: string), _col10 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 - 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: _col0, _col1, _col3, _col4, _col5, _col7 + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Select Operator + 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) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _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 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: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) sort order: ++++++++ - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1460 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) + 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: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + 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 @@ -179,29 +197,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) + predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (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), hr (type: string) + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string), hr (type: string) + 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), _col3 (type: string) TableScan alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) + predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (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), hr (type: string) + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string), hr (type: string) + 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), _col3 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -209,11 +235,11 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col2} 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col2} - outputColumnNames: _col0, _col1, _col3, _col7, _col8, _col10 + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col7 (type: string), _col8 (type: string), _col10 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 + 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) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -227,12 +253,12 @@ STAGE PLANS: 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: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (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) + 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: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/ppd_udf_col.q.out ql/src/test/results/clientpositive/ppd_udf_col.q.out index 5c38154..9ea61ce 100644 --- ql/src/test/results/clientpositive/ppd_udf_col.q.out +++ ql/src/test/results/clientpositive/ppd_udf_col.q.out @@ -20,26 +20,19 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) = 100.0) and (rand() <= 0.1)) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: rand() (type: double) - outputColumnNames: _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 <= 0.1) (type: boolean) + expressions: '100' (type: string), rand() (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - 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 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -73,36 +66,22 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) = 100.0) and ((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: rand() (type: double) - outputColumnNames: _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 <= 0.1) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col1 > 0.1) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 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 + 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 + 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 Stage: Stage-0 Fetch Operator @@ -130,28 +109,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator - expressions: rand() (type: double), '4' (type: string) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col3 <= 3) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col2 (type: double), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - 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 + expressions: '100' (type: string), rand() (type: double), '4' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 @@ -181,26 +153,19 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (((UDFToDouble(value) * 10.0) <= 200) and (UDFToDouble(key) = 100.0)) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: rand() (type: double), (value * 10) (type: double) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col3 <= 200.0) (type: boolean) + expressions: '100' (type: string), rand() (type: double), (UDFToDouble(value) * 10.0) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - 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 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -230,26 +195,19 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) = 100.0) and (rand() <= 0.1)) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: rand() (type: double) - outputColumnNames: _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 <= 0.1) (type: boolean) + expressions: '100' (type: string), rand() (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - 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 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -283,29 +241,22 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) = 100.0) and ((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: rand() (type: double) - outputColumnNames: _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 <= 0.1) and (_col2 > 0.1)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 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 + 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 + 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 Stage: Stage-0 Fetch Operator @@ -333,28 +284,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Select Operator - expressions: rand() (type: double), '4' (type: string) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col3 <= 3) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col2 (type: double), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - 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 + expressions: '100' (type: string), rand() (type: double), '4' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 @@ -384,26 +328,19 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) = 100.0) and ((UDFToDouble(value) * 10.0) <= 200)) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: rand() (type: double), (value * 10) (type: double) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col3 <= 200.0) (type: boolean) + expressions: '100' (type: string), rand() (type: double), (UDFToDouble(value) * 10.0) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - 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 + table: + input format: org.apache.hadoop.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 ql/src/test/results/clientpositive/ppd_union.q.out ql/src/test/results/clientpositive/ppd_union.q.out index 642c9a8..508acf9 100644 --- ql/src/test/results/clientpositive/ppd_union.q.out +++ ql/src/test/results/clientpositive/ppd_union.q.out @@ -28,7 +28,7 @@ STAGE PLANS: alias: 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) + 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) @@ -36,25 +36,22 @@ STAGE PLANS: 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 - Filter Operator - predicate: ((_col0 > '4') and (_col1 > 'val_4')) (type: boolean) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - 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 + 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 + 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 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) + 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) @@ -62,20 +59,17 @@ STAGE PLANS: 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 - Filter Operator - predicate: ((_col0 > '4') and (_col1 > 'val_4')) (type: boolean) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - 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 + 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 + 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 @@ -304,7 +298,7 @@ STAGE PLANS: alias: 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) + 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) @@ -327,7 +321,7 @@ STAGE PLANS: alias: 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) + 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) diff --git ql/src/test/results/clientpositive/ppd_union_view.q.out ql/src/test/results/clientpositive/ppd_union_view.q.out index 1aae964..5b2bc71 100644 --- ql/src/test/results/clientpositive/ppd_union_view.q.out +++ ql/src/test/results/clientpositive/ppd_union_view.q.out @@ -365,7 +365,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -458,12 +458,12 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Needs Tagging: true Reduce Operator Tree: @@ -473,11 +473,11 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} 1 {VALUE._col0} - outputColumnNames: _col1, _col6 + outputColumnNames: _col1, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col6 (type: string), _col1 (type: string), '2011-10-15' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col3 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false @@ -488,8 +488,8 @@ 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,string,string + 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 @@ -501,46 +501,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - GatherStats: false - Union - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2 - 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 - 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,_col2 - columns.types 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 - TableScan alias: t1_new Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), value (type: string), '2011-10-15' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + expressions: _col0 (type: string), _col1 (type: string), '2011-10-15' (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -564,17 +535,46 @@ STAGE PLANS: TotalFiles: 1 GatherStats: false MultiFileSpray: false + TableScan + GatherStats: false + Union + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2011-10-15' (type: string) + outputColumnNames: _col0, _col1, _col2 + 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 + 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,_col2 + columns.types 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 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,string + 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 @@ -582,8 +582,8 @@ 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,string,string + 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 @@ -633,7 +633,7 @@ STAGE PLANS: name: default.t1_new name: default.t1_new Truncated Path -> Alias: - /t1_new/ds=2011-10-15 [t1-subquery1:subq-subquery1:t1_new] + /t1_new/ds=2011-10-15 [null-subquery1:$hdt$_0-subquery1:t1_new] #### A masked pattern was here #### Stage: Stage-0 diff --git ql/src/test/results/clientpositive/ppd_vc.q.out ql/src/test/results/clientpositive/ppd_vc.q.out index 521bc8d..8228613 100644 --- ql/src/test/results/clientpositive/ppd_vc.q.out +++ ql/src/test/results/clientpositive/ppd_vc.q.out @@ -258,10 +258,10 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /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] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:srcpart] Stage: Stage-0 Fetch Operator @@ -729,7 +729,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out index 0793098..8350545 100644 --- ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out +++ ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out @@ -197,8 +197,8 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart] Stage: Stage-0 Fetch Operator @@ -521,10 +521,10 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /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] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:srcpart] Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/ppr_pushdown3.q.out ql/src/test/results/clientpositive/ppr_pushdown3.q.out index 7b36b95..0d2038b 100644 --- ql/src/test/results/clientpositive/ppr_pushdown3.q.out +++ ql/src/test/results/clientpositive/ppr_pushdown3.q.out @@ -3,36 +3,24 @@ PREHOOK: type: QUERY POSTHOOK: query: explain select * from srcpart where key < 10 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: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - 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 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.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 + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) < 10.0) (type: boolean) + 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 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: select * from srcpart where key < 10 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/print_header.q.out ql/src/test/results/clientpositive/print_header.q.out index 48d7455..f01d1d3 100644 --- ql/src/test/results/clientpositive/print_header.q.out +++ 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 +src.key c1 0 0.0 10 10.0 100 200.0 diff --git ql/src/test/results/clientpositive/query_properties.q.out ql/src/test/results/clientpositive/query_properties.q.out index 5684f0d..1ad8a3d 100644 --- ql/src/test/results/clientpositive/query_properties.q.out +++ ql/src/test/results/clientpositive/query_properties.q.out @@ -54,7 +54,7 @@ Has Join: true Has Group By: true Has Sort By: false Has Order By: false -Has Group By After Join: true +Has Group By After Join: false Uses Script: false Has Distribute By: false Has Cluster By: false diff --git ql/src/test/results/clientpositive/quotedid_basic.q.out ql/src/test/results/clientpositive/quotedid_basic.q.out index 46ec84b..4384faa 100644 --- ql/src/test/results/clientpositive/quotedid_basic.q.out +++ ql/src/test/results/clientpositive/quotedid_basic.q.out @@ -102,10 +102,10 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: x+1, y&y, !@#$%^&*()_q + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -161,10 +161,10 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: x+1, y&y, !@#$%^&*()_q + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -244,10 +244,10 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: x+1, y&y, !@#$%^&*()_q + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE diff --git ql/src/test/results/clientpositive/quotedid_partition.q.out ql/src/test/results/clientpositive/quotedid_partition.q.out index 3972c5d..9bb1c40 100644 --- ql/src/test/results/clientpositive/quotedid_partition.q.out +++ 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: x+1, y&y, !@#$%^&*()_q + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/rand_partitionpruner3.q.out ql/src/test/results/clientpositive/rand_partitionpruner3.q.out index 8cfa243..9a062e4 100644 --- ql/src/test/results/clientpositive/rand_partitionpruner3.q.out +++ ql/src/test/results/clientpositive/rand_partitionpruner3.q.out @@ -57,52 +57,14 @@ TOK_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: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((rand(1) < 0.1) and (not ((key > 50) or (key < 10)))) (type: boolean) - Statistics: Num rows: 56 Data size: 594 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 - Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 56 Data size: 594 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.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: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -146,14 +108,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=12 [a] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((rand(1) < 0.1) and (not ((UDFToDouble(key) > 50.0) or (UDFToDouble(key) < 10.0)))) (type: boolean) + Statistics: Num rows: 56 Data size: 594 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 + Statistics: Num rows: 56 Data size: 594 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 @@ -221,52 +189,14 @@ TOK_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: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (not ((key > 50) or (key < 10))) (type: boolean) - Statistics: Num rows: 168 Data size: 1784 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 - Statistics: Num rows: 168 Data size: 1784 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 168 Data size: 1784 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.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: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -310,14 +240,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=12 [a] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (not ((UDFToDouble(key) > 50.0) or (UDFToDouble(key) < 10.0))) (type: boolean) + Statistics: Num rows: 168 Data size: 1784 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 + Statistics: Num rows: 168 Data size: 1784 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: 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 diff --git ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out index 58757d4..87a005c 100644 --- ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out +++ ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out @@ -88,12 +88,12 @@ STAGE PLANS: value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + expressions: KEY.reducesinkkey0 (type: string), lower(VALUE._col0) (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) - keys: _col0 (type: string), lower(_col1) (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -131,23 +131,23 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), (value + 1) (type: double) + expressions: key (type: string), (UDFToDouble(value) + 1.0) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (_col1 + 1) (type: double) + key expressions: _col0 (type: string), (_col1 + 1.0) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (_col1 + 1) (type: double) + Map-reduce partition columns: _col0 (type: string), (_col1 + 1.0) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) + expressions: KEY.reducesinkkey0 (type: string), (VALUE._col0 + 1.0) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) - keys: _col0 (type: string), (_col1 + 1) (type: double) + keys: _col0 (type: string), _col1 (type: double) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -188,11 +188,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(key) - keys: key (type: string) + aggregations: sum(_col0) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -248,23 +248,31 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Join Operator condition map: @@ -342,28 +350,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 - 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 - 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: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) + TableScan + alias: src1 + 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 Reduce Operator Tree: Join Operator condition map: @@ -430,10 +446,10 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -492,10 +508,10 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2594,12 +2610,12 @@ STAGE PLANS: value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + expressions: KEY.reducesinkkey0 (type: string), lower(VALUE._col0) (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) - keys: _col0 (type: string), lower(_col1) (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -2637,23 +2653,23 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), (value + 1) (type: double) + expressions: key (type: string), (UDFToDouble(value) + 1.0) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (_col1 + 1) (type: double) + key expressions: _col0 (type: string), (_col1 + 1.0) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (_col1 + 1) (type: double) + Map-reduce partition columns: _col0 (type: string), (_col1 + 1.0) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) + expressions: KEY.reducesinkkey0 (type: string), (VALUE._col0 + 1.0) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) - keys: _col0 (type: string), (_col1 + 1) (type: double) + keys: _col0 (type: string), _col1 (type: double) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -2694,12 +2710,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: key (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -2747,23 +2763,31 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Join Operator condition map: @@ -2834,28 +2858,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 - 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 - 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: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) + TableScan + alias: src1 + 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 Reduce Operator Tree: Join Operator condition map: @@ -2922,12 +2954,12 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string), value (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: key (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -2979,12 +3011,12 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string), value (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: key (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/regex_col.q.out ql/src/test/results/clientpositive/regex_col.q.out index abb6aa7..829cc2c 100644 --- ql/src/test/results/clientpositive/regex_col.q.out +++ ql/src/test/results/clientpositive/regex_col.q.out @@ -84,29 +84,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + 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) Statistics: Num rows: 500 Data size: 5312 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), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: ds (type: string), hr (type: string) + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string), _col3 (type: string) TableScan 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) Statistics: Num rows: 500 Data size: 5312 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), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: ds (type: string), hr (type: string) + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -114,10 +122,10 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 {VALUE._col0} {VALUE._col1} - outputColumnNames: _col2, _col3, _col9, _col10 + outputColumnNames: _col2, _col3, _col6, _col7 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col9 (type: string), _col10 (type: string) + expressions: _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -154,27 +162,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 103) (type: boolean) + predicate: (UDFToDouble(key) = 103.0) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '103' (type: string), hr (type: string), ds (type: string) - sort order: +++ - Map-reduce partition columns: hr (type: string), ds (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col1, _col2 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) + sort order: +++ + Map-reduce partition columns: _col2 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan alias: a Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 103) (type: boolean) + predicate: (UDFToDouble(key) = 103.0) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '103' (type: string), hr (type: string), ds (type: string) - sort order: +++ - Map-reduce partition columns: hr (type: string), ds (type: string) + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col1, _col2 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) + sort order: +++ + Map-reduce partition columns: _col2 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -182,10 +198,10 @@ STAGE PLANS: condition expressions: 0 1 {KEY.reducesinkkey2} {KEY.reducesinkkey1} - outputColumnNames: _col9, _col10 + outputColumnNames: _col4, _col5 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col9 (type: string), _col10 (type: string) + expressions: _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/router_join_ppr.q.out ql/src/test/results/clientpositive/router_join_ppr.q.out index f70706b..c1fba6e 100644 --- ql/src/test/results/clientpositive/router_join_ppr.q.out +++ ql/src/test/results/clientpositive/router_join_ppr.q.out @@ -109,37 +109,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) - Statistics: Num rows: 222 Data size: 2358 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string), ds (type: string) - auto parallelism: false - TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + TableScan + alias: b + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) + 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 + Statistics: Num rows: 222 Data size: 2358 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -372,32 +380,32 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /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] + /src [$hdt$_0:$hdt$_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] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:$hdt$_0:b] + /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:$hdt$_0:b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} filter mappings: - 1 [0, 1] + 0 [1, 1] filter predicates: - 0 - 1 {(VALUE._col1 = '2008-04-08')} - outputColumnNames: _col0, _col1, _col5, _col6 + 0 {(VALUE._col1 = '2008-04-08')} + 1 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -581,37 +589,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false - TableScan alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) + predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 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: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + 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 + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -752,9 +768,9 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [b] - /srcpart/ds=2008-04-08/hr=11 [a] - /srcpart/ds=2008-04-08/hr=12 [a] + /src [$hdt$_0:$hdt$_1:b] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:$hdt$_0:a] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:$hdt$_0:a] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -763,14 +779,14 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col7, _col8 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 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), _col7 (type: string), _col8 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -950,37 +966,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false - TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) + 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 - 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: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + TableScan + alias: b + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) + 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 + Statistics: Num rows: 111 Data size: 1179 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1121,25 +1145,25 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [a] - /srcpart/ds=2008-04-08/hr=11 [b] - /srcpart/ds=2008-04-08/hr=12 [b] + /src [$hdt$_0:$hdt$_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] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 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), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1319,37 +1343,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: a + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false + predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) + 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 + Statistics: Num rows: 111 Data size: 1179 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false TableScan - alias: a - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 15) and (key < 25)) (type: boolean) - Statistics: Num rows: 222 Data size: 2358 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string), ds (type: string) - auto parallelism: false + 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 + 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 + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1489,120 +1521,26 @@ 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 defaultdefault - 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 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 true - bucket_count -1 - columns key,value - columns.comments defaultdefault - 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 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: - /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] + /src [$hdt$_0:$hdt$_1:b] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:$hdt$_0:a] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:$hdt$_0:a] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} + 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col7, _col8 - Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (((_col0 > 10) and (_col0 < 20)) and (_col2 = '2008-04-08')) (type: boolean) + predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 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), _col7 (type: string), _col8 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1645,8 +1583,6 @@ PREHOOK: Input: default@src 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: FROM srcpart a @@ -1660,8 +1596,6 @@ 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: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 17 val_17 17 val_17 17 val_17 17 val_17 diff --git ql/src/test/results/clientpositive/sample10.q.out ql/src/test/results/clientpositive/sample10.q.out index 6de9ea8..b9616a7 100644 --- ql/src/test/results/clientpositive/sample10.q.out +++ ql/src/test/results/clientpositive/sample10.q.out @@ -363,7 +363,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/select_unquote_and.q.out ql/src/test/results/clientpositive/select_unquote_and.q.out index 55d4a85..03ad48d 100644 --- ql/src/test/results/clientpositive/select_unquote_and.q.out +++ ql/src/test/results/clientpositive/select_unquote_and.q.out @@ -59,7 +59,7 @@ STAGE PLANS: alias: npe_test Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((ds > 1970) and (ds < 1985)) (type: boolean) + predicate: ((UDFToDouble(ds) > 1970.0) and (UDFToDouble(ds) < 1985.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) diff --git ql/src/test/results/clientpositive/select_unquote_not.q.out ql/src/test/results/clientpositive/select_unquote_not.q.out index 9e0f928..64de433 100644 --- ql/src/test/results/clientpositive/select_unquote_not.q.out +++ ql/src/test/results/clientpositive/select_unquote_not.q.out @@ -59,7 +59,7 @@ STAGE PLANS: alias: npe_test Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (not (ds < 1970)) (type: boolean) + predicate: (not (UDFToDouble(ds) < 1970.0)) (type: boolean) 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) diff --git ql/src/test/results/clientpositive/select_unquote_or.q.out ql/src/test/results/clientpositive/select_unquote_or.q.out index f7fa467..de91313 100644 --- ql/src/test/results/clientpositive/select_unquote_or.q.out +++ ql/src/test/results/clientpositive/select_unquote_or.q.out @@ -59,7 +59,7 @@ STAGE PLANS: alias: npe_test Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((ds > 1970) or (ds < 1985)) (type: boolean) + predicate: ((UDFToDouble(ds) > 1970.0) or (UDFToDouble(ds) < 1985.0)) (type: boolean) 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) diff --git ql/src/test/results/clientpositive/semijoin.q.out ql/src/test/results/clientpositive/semijoin.q.out index 920b2c7..12b73f3 100644 --- ql/src/test/results/clientpositive/semijoin.q.out +++ ql/src/test/results/clientpositive/semijoin.q.out @@ -2603,6 +2603,22 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan + alias: a + Statistics: Num rows: 22 Data size: 163 Basic stats: COMPLETE Column stats: NONE + Filter Operator + 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: 3 Data size: 22 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: 3 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + TableScan alias: b Statistics: Num rows: 11 Data size: 84 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -2610,10 +2626,10 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: value + outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: value (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE @@ -2622,18 +2638,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: a - Statistics: Num rows: 22 Data size: 163 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (value is not null and (key > 100)) (type: boolean) - Statistics: Num rows: 3 Data size: 22 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: 3 Data size: 22 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: int) Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/set_processor_namespaces.q.out ql/src/test/results/clientpositive/set_processor_namespaces.q.out index 992865a..3c67727 100644 --- ql/src/test/results/clientpositive/set_processor_namespaces.q.out +++ ql/src/test/results/clientpositive/set_processor_namespaces.q.out @@ -19,7 +19,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 5) (type: boolean) + predicate: (UDFToDouble(key) = 5.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/skewjoin.q.out ql/src/test/results/clientpositive/skewjoin.q.out index deb0a8f..e80c0a5 100644 --- ql/src/test/results/clientpositive/skewjoin.q.out +++ ql/src/test/results/clientpositive/skewjoin.q.out @@ -624,17 +624,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} {VALUE._col0} + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 handleSkewJoin: true - outputColumnNames: _col2, _col3 + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string) - outputColumnNames: _col2, _col3 + expressions: hash(_col0) (type: int), hash(_col1) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col2)), sum(hash(_col3)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -659,8 +659,8 @@ STAGE PLANS: TableScan HashTable Sink Operator condition expressions: - 0 - 1 {1_VALUE_0} {1_VALUE_1} + 0 {0_VALUE_0} {0_VALUE_1} + 1 keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) @@ -673,17 +673,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {1_VALUE_0} {1_VALUE_1} + 0 {0_VALUE_0} {0_VALUE_1} + 1 keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - outputColumnNames: _col2, _col3 + outputColumnNames: _col0, _col1 Select Operator - expressions: _col2 (type: string), _col3 (type: string) - outputColumnNames: _col2, _col3 + expressions: hash(_col0) (type: int), hash(_col1) (type: int) + outputColumnNames: _col0, _col1 Group By Operator - aggregations: sum(hash(_col2)), sum(hash(_col3)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 File Output Operator @@ -776,33 +776,33 @@ STAGE PLANS: alias: 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: (key is not null and (UDFToDouble(substring(value, 5)) + 1.0) 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: 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: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) + Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) Statistics: Num rows: 125 Data size: 1328 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 Filter Operator - predicate: (key is not null and (substring(value, 5) + 1) is not null) (type: boolean) + predicate: (key is not null and UDFToDouble(substring(value, 5)) 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (substring(_col1, 5) + 1) (type: double) + key expressions: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (substring(_col1, 5) + 1) (type: double) + Map-reduce partition columns: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -814,11 +814,11 @@ STAGE PLANS: outputColumnNames: _col2, _col3 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string) - outputColumnNames: _col2, _col3 + expressions: hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col2)), sum(hash(_col3)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -864,10 +864,10 @@ STAGE PLANS: 1 reducesinkkey0 (type: string), reducesinkkey1 (type: double) outputColumnNames: _col2, _col3 Select Operator - expressions: _col2 (type: string), _col3 (type: string) - outputColumnNames: _col2, _col3 + expressions: hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1 Group By Operator - aggregations: sum(hash(_col2)), sum(hash(_col3)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 File Output Operator @@ -953,40 +953,41 @@ JOIN ON src1.c1 = src3.c5 AND src3.c5 < 80 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-8, Stage-9, Stage-2 - Stage-8 - Stage-5 depends on stages: Stage-8 - Stage-2 depends on stages: Stage-5, Stage-6 + Stage-3 is a root stage + Stage-8 depends on stages: Stage-3 , consists of Stage-10, Stage-1 + 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-6 depends on stages: Stage-9 + Stage-5 depends on stages: Stage-9 + Stage-2 depends on stages: Stage-5 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key < 100) and (key < 80)) 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) and (UDFToDouble(key) < 80.0)) (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: _col0 + 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 80) and (key < 100)) (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) @@ -997,39 +998,114 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (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 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 + handleSkewJoin: true + outputColumnNames: _col0 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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 + + Stage: Stage-8 + Conditional Operator + + Stage: Stage-10 + Map Reduce Local Work + Alias -> Map Local Tables: + 1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + 1 + TableScan + HashTable Sink Operator + condition expressions: + 0 {0_VALUE_0} + 1 + keys: + 0 reducesinkkey0 (type: string) + 1 reducesinkkey0 (type: string) + + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {0_VALUE_0} + 1 + keys: + 0 reducesinkkey0 (type: string) + 1 reducesinkkey0 (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (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 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 100) and (key < 80)) (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 + 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 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 + Statistics: Num rows: 166 Data size: 1763 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: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - 2 + 0 {VALUE._col0} + 1 {KEY.reducesinkkey0} handleSkewJoin: true - outputColumnNames: _col0, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col2 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + expressions: hash(_col2) (type: int), hash(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col3)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1040,18 +1116,15 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-7 + Stage: Stage-6 Conditional Operator - Stage: Stage-8 + Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: 1 Fetch Operator limit: -1 - 2 - Fetch Operator - limit: -1 Alias -> Map Local Operator Tree: 1 TableScan @@ -1059,22 +1132,9 @@ STAGE PLANS: condition expressions: 0 {0_VALUE_0} 1 {1_VALUE_0} - 2 keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - 2 reducesinkkey0 (type: string) - 2 - TableScan - HashTable Sink Operator - condition expressions: - 0 {0_VALUE_0} - 1 {1_VALUE_0} - 2 - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - 2 reducesinkkey0 (type: string) Stage: Stage-5 Map Reduce @@ -1083,21 +1143,18 @@ STAGE PLANS: Map Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 condition expressions: 0 {0_VALUE_0} 1 {1_VALUE_0} - 2 keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - 2 reducesinkkey0 (type: string) - outputColumnNames: _col0, _col3 + outputColumnNames: _col1, _col2 Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 + expressions: hash(_col2) (type: int), hash(_col1) (type: int) + outputColumnNames: _col0, _col1 Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col3)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 File Output Operator @@ -1135,72 +1192,6 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-9 - Map Reduce Local Work - Alias -> Map Local Tables: - 0 - Fetch Operator - limit: -1 - 2 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - 0 - TableScan - HashTable Sink Operator - condition expressions: - 0 {0_VALUE_0} - 1 {1_VALUE_0} - 2 - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - 2 reducesinkkey0 (type: string) - 2 - TableScan - HashTable Sink Operator - condition expressions: - 0 {0_VALUE_0} - 1 {1_VALUE_0} - 2 - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - 2 reducesinkkey0 (type: string) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - condition expressions: - 0 {0_VALUE_0} - 1 {1_VALUE_0} - 2 - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - 2 reducesinkkey0 (type: string) - outputColumnNames: _col0, _col3 - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col3)) - mode: hash - 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 - Local Work: - Map Reduce Local Work - Stage: Stage-0 Fetch Operator limit: -1 diff --git ql/src/test/results/clientpositive/stats_only_null.q.out ql/src/test/results/clientpositive/stats_only_null.q.out index 4549b79..503f111 100644 --- ql/src/test/results/clientpositive/stats_only_null.q.out +++ 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: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(a), count(b), count(c), count(d) + aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -139,10 +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: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(a), count(b), count(c), count(d) + aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/str_to_map.q.out ql/src/test/results/clientpositive/str_to_map.q.out index ac522b7..cc3931e 100644 --- ql/src/test/results/clientpositive/str_to_map.q.out +++ ql/src/test/results/clientpositive/str_to_map.q.out @@ -62,10 +62,10 @@ STAGE PLANS: Select Operator expressions: str_to_map('a:1,b:2,c:3') (type: map) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 460000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3 @@ -97,10 +97,10 @@ STAGE PLANS: Select Operator expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 460000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 diff --git ql/src/test/results/clientpositive/subq2.q.out ql/src/test/results/clientpositive/subq2.q.out index e661887..80ad37b 100644 --- ql/src/test/results/clientpositive/subq2.q.out +++ ql/src/test/results/clientpositive/subq2.q.out @@ -20,15 +20,15 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key >= 90) (type: boolean) + 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: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/subq_where_serialization.q.out ql/src/test/results/clientpositive/subq_where_serialization.q.out index f91a7d5..7166fb0 100644 --- ql/src/test/results/clientpositive/subq_where_serialization.q.out +++ ql/src/test/results/clientpositive/subq_where_serialization.q.out @@ -22,10 +22,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -70,10 +70,10 @@ STAGE PLANS: TableScan HashTable Sink Operator condition expressions: - 0 {key} + 0 {_col0} 1 keys: - 0 key (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) Stage: Stage-4 @@ -83,25 +83,28 @@ STAGE PLANS: alias: src Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Left Semi Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 _col0 (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - Select Operator - expressions: _col0 (type: string) + Map Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) 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: string) + 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 Local Work: Map Reduce Local Work @@ -120,11 +123,15 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: diff --git ql/src/test/results/clientpositive/subquery_exists.q.out ql/src/test/results/clientpositive/subquery_exists.q.out index f939c7d..755f699 100644 --- ql/src/test/results/clientpositive/subquery_exists.q.out +++ ql/src/test/results/clientpositive/subquery_exists.q.out @@ -32,23 +32,27 @@ STAGE PLANS: 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 - Reduce Output Operator - key expressions: value (type: string), key (type: string) - sort order: ++ - Map-reduce partition columns: value (type: string), key (type: string) + 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 + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 125 Data size: 1328 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: ((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: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col1 (type: string), _col2 (type: string) + 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 diff --git ql/src/test/results/clientpositive/subquery_exists_having.q.out ql/src/test/results/clientpositive/subquery_exists_having.q.out index e6c1716..b294379 100644 --- ql/src/test/results/clientpositive/subquery_exists_having.q.out +++ 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: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -57,13 +57,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) 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 + 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 + 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 Stage: Stage-2 Map Reduce @@ -73,20 +77,20 @@ STAGE PLANS: 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 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: a + 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 Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col1 (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE @@ -103,14 +107,14 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1460 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: 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 @@ -188,11 +192,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -203,17 +207,17 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: a + 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 Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col1 (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE @@ -231,27 +235,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 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 - Join Operator - condition map: - Left Semi Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + 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 + Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 outputColumnNames: _col0, _col1 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: 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 diff --git ql/src/test/results/clientpositive/subquery_in.q.out ql/src/test/results/clientpositive/subquery_in.q.out index 84d316f..0af91d5 100644 --- ql/src/test/results/clientpositive/subquery_in.q.out +++ ql/src/test/results/clientpositive/subquery_in.q.out @@ -119,7 +119,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '9') (type: boolean) @@ -144,12 +144,16 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 - value expressions: value (type: string) + 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: Join Operator condition map: @@ -234,13 +238,17 @@ STAGE PLANS: 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 - 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 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: 125 Data size: 1328 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 > '9') and value is not null) (type: boolean) @@ -350,12 +358,16 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_size (type: int) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_mfgr (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Reduce Operator Tree: Extract Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE @@ -365,7 +377,7 @@ STAGE PLANS: predicate: (_wcol0 <= 2) (type: boolean) Statistics: Num rows: 10 Data size: 1057 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 1057 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -425,26 +437,30 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(p_size) is not null (type: boolean) - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(p_size) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(p_size) (type: double) + Select Operator + expressions: p_name (type: string), p_size (type: int), UDFToDouble(p_size) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col2 is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col2 (type: double) + sort order: + + Map-reduce partition columns: _col2 (type: double) + Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: - 0 {VALUE._col1} {VALUE._col5} + 0 {VALUE._col0} {VALUE._col1} 1 - outputColumnNames: _col1, _col5 + outputColumnNames: _col0, _col1 Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col5 (type: int) + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -512,24 +528,28 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part + alias: b Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_size (type: int) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_mfgr (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Reduce Operator Tree: Extract Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE PTF Operator Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_wcol0 <= 2) and _col2 is not null) (type: boolean) + predicate: ((_wcol0 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -590,12 +610,16 @@ STAGE PLANS: Filter Operator predicate: (p_size is not null and p_mfgr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_size (type: int), p_mfgr (type: string) - sort order: ++ - Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) + Select Operator + expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + key expressions: _col2 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) @@ -607,12 +631,12 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 condition expressions: - 0 {VALUE._col1} {KEY.reducesinkkey1} {KEY.reducesinkkey0} + 0 {VALUE._col0} {KEY.reducesinkkey1} {KEY.reducesinkkey0} 1 - outputColumnNames: _col1, _col2, _col5 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 930 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 930 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -674,26 +698,26 @@ where b.key in ) 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: a + 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 Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + 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 @@ -724,26 +748,30 @@ 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 + 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: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + TableScan alias: b 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: 125 Data size: 1328 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - TableScan - 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: 41 Data size: 435 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/subquery_in_having.q.out ql/src/test/results/clientpositive/subquery_in_having.q.out index 163b0d1..ed9e0ad 100644 --- ql/src/test/results/clientpositive/subquery_in_having.q.out +++ ql/src/test/results/clientpositive/subquery_in_having.q.out @@ -65,18 +65,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: src 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: key + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -157,11 +157,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -181,12 +181,16 @@ STAGE PLANS: Filter Operator predicate: _col1 is not null (type: boolean) 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-0 Fetch Operator @@ -281,23 +285,23 @@ STAGE PLANS: 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: ((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: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string), key (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -305,33 +309,42 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) - 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 + 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 + 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 Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: _col0 (type: bigint), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator key expressions: _col2 (type: bigint), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: bigint), _col1 (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: bigint), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -357,26 +370,26 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + 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 (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: value, key - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: value (type: string), key (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -384,25 +397,20 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 - 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 + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + 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 Stage: Stage-0 Fetch Operator @@ -452,33 +460,45 @@ 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: p_mfgr, p_size + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(p_size) - keys: p_mfgr (type: string) + aggregations: max(_col1), min(_col1) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 15 Data size: 1586 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: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct) + value expressions: _col1 (type: int), _col2 (type: int) Reduce Operator Tree: Group By Operator - aggregations: avg(VALUE._col0) + aggregations: max(VALUE._col0), min(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - 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: _col0, _col1, _col2 + Statistics: Num rows: 7 Data size: 740 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col1 - _col2) < 20) (type: boolean) + Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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 Stage: Stage-2 Map Reduce @@ -488,14 +508,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + Statistics: Num rows: 2 Data size: 211 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: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 740 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: double) Reduce Operator Tree: Join Operator condition map: @@ -504,14 +524,14 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 814 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 814 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + 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 @@ -521,52 +541,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part + alias: b 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: p_mfgr, p_size + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(p_size), min(p_size) - keys: p_mfgr (type: string) + aggregations: avg(_col1) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 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: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) + aggregations: avg(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 740 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 - _col2) < 20) (type: boolean) - Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 740 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 @@ -614,42 +626,42 @@ 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: p_mfgr, p_size + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(p_size) - keys: p_mfgr (type: string) + aggregations: max(_col1), min(_col1) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 15 Data size: 1586 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: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct) + value expressions: _col1 (type: int), _col2 (type: int) TableScan - alias: part + alias: b 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: p_mfgr, p_size + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(p_size), min(p_size) - keys: p_mfgr (type: string) + aggregations: avg(_col1) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 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: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + value expressions: _col1 (type: struct) Reduce Operator Tree: Demux Operator Statistics: Num rows: 30 Data size: 3172 Basic stats: COMPLETE Column stats: NONE @@ -659,27 +671,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 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 - Join Operator - condition map: - Left Semi Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + 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 + Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 outputColumnNames: _col0, _col1 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: double) + 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 + 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) @@ -777,10 +793,10 @@ having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.k 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-5 - Stage-5 is a root stage - Stage-0 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-1, Stage-4 + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 @@ -790,103 +806,66 @@ STAGE PLANS: 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 - 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: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key > '8') (type: boolean) + 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 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator + aggregations: count() keys: _col0 (type: string) mode: hash - outputColumnNames: _col0 + outputColumnNames: _col0, _col1 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 - condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 - 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 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string), _col1 (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 - Map Operator Tree: - TableScan - 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) + value expressions: _col1 (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: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is not null (type: boolean) - 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 + predicate: _col1 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 + 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 - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: _col0 (type: bigint) + sort order: + + Map-reduce partition columns: _col0 (type: bigint) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator key expressions: _col2 (type: bigint) sort order: + Map-reduce partition columns: _col2 (type: bigint) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: bigint) - sort order: + - Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -908,56 +887,101 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-5 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > '9') (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 + 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) + TableScan + alias: b + 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: key + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 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 - value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + 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 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col0 (type: string), _col1 (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 + Map Reduce + Map Operator Tree: + TableScan + 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) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: _col2 is not null (type: boolean) + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - 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 + 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 + File Output Operator + compressed: false + table: + input format: 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 @@ -994,32 +1018,32 @@ group by key, value having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-5 is a root stage - Stage-7 depends on stages: Stage-2, Stage-5 , consists of Stage-9, Stage-3 - Stage-9 has a backup stage: Stage-3 + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1, Stage-4 , consists of Stage-9, Stage-2 + Stage-9 has a backup stage: Stage-2 Stage-6 depends on stages: Stage-9 - Stage-3 + Stage-2 Stage-10 is a root stage - Stage-2 depends on stages: Stage-10 - Stage-0 depends on stages: Stage-6, Stage-3 + Stage-4 depends on stages: Stage-10 + Stage-0 depends on stages: Stage-6, Stage-2 STAGE PLANS: - Stage: Stage-5 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: b 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: key + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -1061,11 +1085,11 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $INTNAME1 + $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $INTNAME1 + $INTNAME TableScan HashTable Sink Operator condition expressions: @@ -1101,22 +1125,22 @@ 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: bigint) + sort order: + + Map-reduce partition columns: _col0 (type: bigint) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator key expressions: _col2 (type: bigint) sort order: + Map-reduce partition columns: _col2 (type: bigint) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: bigint) - sort order: + - Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -1141,13 +1165,13 @@ STAGE PLANS: Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - sq_1:src + $hdt$_0:$hdt$_0:$hdt$_1:b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - sq_1:src + $hdt$_0:$hdt$_0:$hdt$_1:b TableScan - alias: src + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '8') (type: boolean) @@ -1163,13 +1187,13 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: - 0 {key} {value} + 0 {_col0} {_col1} 1 keys: - 0 key (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - Stage: Stage-2 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -1178,33 +1202,37 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 _col0 (type: string) + Select Operator + expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 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 - Group By Operator - aggregations: count() - 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: 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() + keys: _col0 (type: string), _col1 (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: @@ -1217,12 +1245,16 @@ STAGE PLANS: Filter Operator predicate: _col2 is not null (type: boolean) 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 + 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 + File Output Operator + compressed: false + table: + input format: 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 @@ -1262,12 +1294,16 @@ STAGE PLANS: TableScan alias: part 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) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col1 (type: string), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) Reduce Operator Tree: Extract Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE @@ -1352,7 +1388,7 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col2 (type: double) Reduce Operator Tree: Join Operator @@ -1386,11 +1422,11 @@ 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: p_mfgr, p_name, p_size + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(p_size) - keys: p_mfgr (type: string), p_name (type: string) + aggregations: avg(_col2) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE @@ -1406,13 +1442,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - 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 + Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 ql/src/test/results/clientpositive/subquery_notexists.q.out ql/src/test/results/clientpositive/subquery_notexists.q.out index b31a75f..4298388 100644 --- ql/src/test/results/clientpositive/subquery_notexists.q.out +++ ql/src/test/results/clientpositive/subquery_notexists.q.out @@ -29,25 +29,29 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: value (type: string), key (type: string) - sort order: ++ - Map-reduce partition columns: value (type: string), key (type: string) + 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: _col1 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 500 Data size: 5312 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: (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: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator @@ -56,10 +60,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} 1 {KEY.reducesinkkey1} - outputColumnNames: _col0, _col1, _col7 + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col7 is null (type: boolean) + predicate: _col3 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) @@ -248,17 +252,17 @@ 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 > '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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -275,7 +279,7 @@ STAGE PLANS: Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -290,17 +294,21 @@ STAGE PLANS: TableScan alias: b 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + 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 @@ -309,10 +317,10 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col6 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col6 is null (type: boolean) + predicate: _col2 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) diff --git ql/src/test/results/clientpositive/subquery_notexists_having.q.out ql/src/test/results/clientpositive/subquery_notexists_having.q.out index f377e66..f6c7d80 100644 --- ql/src/test/results/clientpositive/subquery_notexists_having.q.out +++ ql/src/test/results/clientpositive/subquery_notexists_having.q.out @@ -21,12 +21,12 @@ having not exists ) 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 @@ -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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -51,38 +51,42 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - 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 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 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: (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: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -90,18 +94,18 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} 1 {KEY.reducesinkkey1} - outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col4 is null (type: boolean) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + predicate: _col3 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 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1455 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: 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 @@ -186,10 +190,10 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -203,13 +207,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - 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 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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-2 Map Reduce @@ -219,13 +227,13 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + 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 @@ -234,18 +242,18 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + predicate: _col2 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 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 1455 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: 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 @@ -255,17 +263,17 @@ 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 > '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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -282,7 +290,7 @@ STAGE PLANS: Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git ql/src/test/results/clientpositive/subquery_notin.q.out ql/src/test/results/clientpositive/subquery_notin.q.out index c5cfe15..019d68a 100644 --- ql/src/test/results/clientpositive/subquery_notin.q.out +++ ql/src/test/results/clientpositive/subquery_notin.q.out @@ -94,7 +94,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/lineitem.txt' OVERWRIT POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@lineitem -Warning: Shuffle Join JOIN[18][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr explain select * @@ -124,7 +124,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '2') and key is null) (type: boolean) @@ -150,20 +150,13 @@ STAGE PLANS: predicate: (_col0 = 0) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: 0 (type: bigint) - outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - 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 @@ -175,14 +168,18 @@ STAGE PLANS: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 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 - value expressions: key (type: string), value (type: string) + 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) Reduce Operator Tree: Join Operator condition map: - Left Semi Join 0 to 1 + Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 @@ -206,7 +203,7 @@ STAGE PLANS: Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan - alias: s1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '2') (type: boolean) @@ -227,10 +224,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col5 + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col5 is null (type: boolean) + predicate: _col3 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) @@ -250,7 +247,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[18][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from src where src.key not in ( select key from src s1 where s1.key > '2') @@ -1272,7 +1269,7 @@ POSTHOOK: Input: default@lineitem 139636 1 175839 1 182052 1 -Warning: Shuffle Join JOIN[18][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- alternate not in syntax select * from src @@ -1436,7 +1433,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@t1_v POSTHOOK: Output: database:default POSTHOOK: Output: default@T2_v -Warning: Shuffle Join JOIN[24][tables = [t1_v, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2: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) @@ -1459,26 +1456,19 @@ STAGE PLANS: alias: 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 + predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE (key) END is null) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is null (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 83 Data size: 881 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) + Statistics: Num rows: 83 Data size: 881 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) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1489,20 +1479,13 @@ STAGE PLANS: predicate: (_col0 = 0) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: 0 (type: bigint) - outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - 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 @@ -1528,7 +1511,7 @@ STAGE PLANS: Reduce Operator Tree: Join Operator condition map: - Left Semi Join 0 to 1 + Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} 1 @@ -1554,17 +1537,17 @@ STAGE PLANS: alias: 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 + 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 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -1572,10 +1555,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col2 Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is null (type: boolean) + 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) @@ -1595,7 +1578,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[24][tables = [t1_v, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2: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 ql/src/test/results/clientpositive/subquery_notin_having.q.out ql/src/test/results/clientpositive/subquery_notin_having.q.out index 87da349..e05b0da 100644 --- ql/src/test/results/clientpositive/subquery_notin_having.q.out +++ ql/src/test/results/clientpositive/subquery_notin_having.q.out @@ -40,7 +40,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwri POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@part -Warning: Shuffle Join JOIN[22][tables = [gby_sq1, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr explain select key, count(*) @@ -63,9 +63,9 @@ having key not in POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 + Stage-2 depends on stages: Stage-1, Stage-4 Stage-3 depends on stages: Stage-2 - Stage-5 is a root stage + Stage-4 is a root stage Stage-0 depends on stages: Stage-3 STAGE PLANS: @@ -73,46 +73,41 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key > '12') and key is null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 83 Data size: 881 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) - 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 - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: 0 (type: bigint) + expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: bigint) + aggregations: count() + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - 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: _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: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(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 + 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 @@ -120,21 +115,21 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: bigint) TableScan 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: bigint) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Reduce Operator Tree: Join Operator condition map: - Left Semi Join 0 to 1 + Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -150,10 +145,10 @@ STAGE PLANS: 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 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: s1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '12') (type: boolean) @@ -174,58 +169,60 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE + predicate: _col3 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 - 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 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 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-5 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan alias: 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 - Group By Operator - aggregations: count() - keys: key (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 - value expressions: _col1 (type: bigint) + Filter Operator + predicate: ((key > '12') and key is null) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 83 Data size: 881 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) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - 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 + 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index 027c195..a8325ec 100644 --- ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -108,11 +108,15 @@ STAGE PLANS: Filter Operator predicate: (key1 is not null and value1 is not null) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Reduce Output Operator - key expressions: key1 (type: string), value1 (type: string) - sort order: ++ - Map-reduce partition columns: key1 (type: string), value1 (type: string) + Select Operator + expressions: key1 (type: string), value1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -158,13 +162,17 @@ STAGE PLANS: 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 - 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + 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) @@ -229,34 +237,38 @@ from part b where b.p_size in ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 + Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan alias: part2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Reduce Output Operator - key expressions: p2_mfgr (type: string), p2_size (type: int) - sort order: ++ - Map-reduce partition columns: p2_mfgr (type: string) + Select Operator + expressions: p2_mfgr (type: string), p2_size (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - value expressions: p2_mfgr (type: string), p2_size (type: int) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Reduce Operator Tree: Extract Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE PTF Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: ((_wcol0 <= 2) and _col2 is not null) (type: boolean) + predicate: ((_wcol0 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator @@ -272,7 +284,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -308,38 +320,42 @@ 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 - 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE - TableScan alias: b Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator predicate: (p_size is not null and p_mfgr is not null) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Reduce Output Operator - key expressions: p_size (type: int), p_mfgr (type: string) - sort order: ++ - Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) + Select Operator + expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + key expressions: _col2 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string) + TableScan + 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 condition expressions: - 0 {VALUE._col1} {KEY.reducesinkkey1} {KEY.reducesinkkey0} + 0 {VALUE._col0} {KEY.reducesinkkey1} {KEY.reducesinkkey0} 1 - outputColumnNames: _col1, _col2, _col5 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -383,24 +399,28 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part + alias: b Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_size (type: int) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - value expressions: p_mfgr (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Reduce Operator Tree: Extract Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE PTF Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Filter Operator - predicate: ((_wcol0 <= 2) and _col2 is not null) (type: boolean) + predicate: ((_wcol0 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator @@ -461,12 +481,16 @@ STAGE PLANS: Filter Operator predicate: (p_size is not null and p_mfgr is not null) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Reduce Output Operator - key expressions: p_size (type: int), p_mfgr (type: string) - sort order: ++ - Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) + Select Operator + expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + key expressions: _col2 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) @@ -478,12 +502,12 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 condition expressions: - 0 {VALUE._col1} {KEY.reducesinkkey1} {KEY.reducesinkkey0} + 0 {VALUE._col0} {KEY.reducesinkkey1} {KEY.reducesinkkey0} 1 - outputColumnNames: _col1, _col2, _col5 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -521,26 +545,26 @@ where b.key in ) 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: 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 Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + 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 @@ -571,26 +595,30 @@ 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 + 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: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + TableScan alias: b 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: 125 Data size: 1328 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - TableScan - 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: 41 Data size: 435 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -646,23 +674,23 @@ STAGE PLANS: 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: ((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: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string), key (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: key (type: string), value (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -670,33 +698,42 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) - 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 + 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 + 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 Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: _col0 (type: bigint), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator key expressions: _col2 (type: bigint), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: bigint), _col1 (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: bigint), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -722,26 +759,26 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + 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 (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: value, key - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: value (type: string), key (type: string) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -749,25 +786,20 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 - 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 + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + 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 Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/subquery_views.q.out ql/src/test/results/clientpositive/subquery_views.q.out index c928db4..d14b2af 100644 --- ql/src/test/results/clientpositive/subquery_views.q.out +++ 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[42][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-5:MAPRED' is a cross product -Warning: Shuffle Join JOIN[18][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-4:MAPRED' is a cross product +Warning: Shuffle Join JOIN[51][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from cv2 where cv2.key in (select key from cv2 c where c.key < '11') @@ -80,24 +80,24 @@ select * from cv2 where cv2.key in (select key from cv2 c where c.key < '11') POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-4 is a root stage + Stage-6 is a root stage + Stage-4 depends on stages: Stage-6 Stage-5 depends on stages: Stage-4 - Stage-6 depends on stages: Stage-5 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-9 is a root stage - Stage-1 depends on stages: Stage-9 + Stage-3 depends on stages: Stage-2, Stage-5 + 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-3 STAGE PLANS: - Stage: Stage-4 + Stage: Stage-6 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 > 'val_11') and ((key is null or value is null) or key is null)) (type: boolean) + predicate: ((value > 'val_11') and (key is null or (value is null or key is null))) (type: boolean) Statistics: Num rows: 249 Data size: 2645 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 249 Data size: 2645 Basic stats: COMPLETE Column stats: NONE @@ -120,47 +120,44 @@ STAGE PLANS: predicate: (_col0 = 0) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: 0 (type: bigint) - outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - 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 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - TableScan alias: 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) + 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 + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Reduce Operator Tree: Join Operator condition map: - Left Semi Join 0 to 1 + Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -168,7 +165,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -176,49 +173,44 @@ STAGE PLANS: 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 + Statistics: Num rows: 275 Data size: 2921 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: (((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') 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), key (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 881 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 + 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 condition expressions: - 0 {KEY.reducesinkkey0} + 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col5 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col5 is null (type: boolean) - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE + predicate: _col3 is null (type: boolean) + Statistics: Num rows: 151 Data size: 1606 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: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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 @@ -228,14 +220,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 100 Data size: 1066 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: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -257,14 +249,14 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-9 + Stage: Stage-7 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 > 'val_11') and ((key is null or value is null) or key is null)) (type: boolean) + predicate: ((value > 'val_11') and (key is null or (value is null or key is null))) (type: boolean) Statistics: Num rows: 249 Data size: 2645 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 249 Data size: 2645 Basic stats: COMPLETE Column stats: NONE @@ -287,20 +279,13 @@ STAGE PLANS: predicate: (_col0 = 0) (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: 0 (type: bigint) - outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - table: - 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 @@ -309,12 +294,16 @@ STAGE PLANS: 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) + 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) TableScan Reduce Output Operator sort order: @@ -322,12 +311,12 @@ STAGE PLANS: Reduce Operator Tree: Join Operator condition map: - Left Semi Join 0 to 1 + Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 outputColumnNames: _col0, _col1 - 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 File Output Operator compressed: false table: @@ -343,44 +332,49 @@ STAGE PLANS: 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 1939 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: ((value > 'val_11') and key is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + 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 Select Operator expressions: key (type: string), value (type: string), key (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 297 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col3 + Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col5 is null (type: boolean) - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE + predicate: _col3 is null (type: boolean) + Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - 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: _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 Stage: Stage-0 Fetch Operator @@ -388,8 +382,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[42][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-5:MAPRED' is a cross product -Warning: Shuffle Join JOIN[18][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-4:MAPRED' is a cross product +Warning: Shuffle Join JOIN[51][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-1: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 ql/src/test/results/clientpositive/symlink_text_input_format.q.out ql/src/test/results/clientpositive/symlink_text_input_format.q.out index f9d517c..f52429c 100644 --- ql/src/test/results/clientpositive/symlink_text_input_format.q.out +++ ql/src/test/results/clientpositive/symlink_text_input_format.q.out @@ -176,9 +176,11 @@ STAGE PLANS: alias: symlink_text_input_format Statistics: Num rows: 0 Data size: 72 Basic stats: PARTIAL Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 72 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/table_access_keys_stats.q.out ql/src/test/results/clientpositive/table_access_keys_stats.q.out index fbe392e..b5cff09 100644 --- ql/src/test/results/clientpositive/table_access_keys_stats.q.out +++ 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_2 +Operator:GBY_4 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_2 +Operator:GBY_4 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_4 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_5 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_2 +Operator:GBY_4 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_2 +Operator:GBY_4 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_2 +Operator:GBY_4 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_2 +Operator:GBY_4 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_2 +Operator:GBY_12 Table:default@t1 Keys:key -Operator:GBY_8 +Operator:GBY_4 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_5 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_4 +Operator:GBY_5 Table:default@t1 Keys:key,val diff --git ql/src/test/results/clientpositive/tez/correlationoptimizer1.q.out ql/src/test/results/clientpositive/tez/correlationoptimizer1.q.out index 5631926..be40828 100644 --- ql/src/test/results/clientpositive/tez/correlationoptimizer1.q.out +++ ql/src/test/results/clientpositive/tez/correlationoptimizer1.q.out @@ -36,45 +36,53 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: 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 - 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 + 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 + 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 Map 5 Map Operator Tree: 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 Filter Operator 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: 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 + 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 Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -94,11 +102,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -176,45 +184,53 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: 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 - 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 + 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 + 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 Map 5 Map Operator Tree: 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 Filter Operator 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: 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 + 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 Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -234,11 +250,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -316,62 +332,70 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 2 <- Map 1 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Map 1 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 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 - 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 - Map 2 - Map Operator Tree: - TableScan alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - input vertices: - 0 Map 1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 + input vertices: + 1 Map 4 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 + Select Operator + expressions: _col1 (type: string), 1 (type: int) 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) + Group By Operator + aggregations: count(_col1) + 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) - Reducer 3 + 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) + Map 4 + 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 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -380,11 +404,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -392,7 +416,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reducer 4 + Reducer 3 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) @@ -473,11 +497,15 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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 Map 5 Map Operator Tree: TableScan @@ -488,10 +516,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -511,11 +539,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -535,11 +563,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -622,11 +650,15 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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 Map 5 Map Operator Tree: TableScan @@ -637,10 +669,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -660,11 +692,11 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -684,11 +716,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -772,39 +804,47 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -824,11 +864,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -906,39 +946,47 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -958,11 +1006,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1046,40 +1094,48 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1098,11 +1154,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1180,40 +1236,48 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1232,11 +1296,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1317,40 +1381,48 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan alias: x Statistics: Num rows: 25 Data size: 191 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: _col0, _col1 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: y + 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), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey1} - outputColumnNames: _col0, _col6 + 0 {KEY.reducesinkkey1} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col6 + expressions: _col2 (type: string), _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col6 (type: string) + aggregations: count(_col2) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1441,40 +1513,48 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan alias: x Statistics: Num rows: 25 Data size: 191 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: _col0, _col1 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: y + 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), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {KEY.reducesinkkey1} - outputColumnNames: _col0, _col6 + 0 {KEY.reducesinkkey1} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col6 + expressions: _col2 (type: string), _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col6 (type: string) + aggregations: count(_col2) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1574,40 +1654,48 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1626,11 +1714,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1708,40 +1796,48 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} - outputColumnNames: _col5 + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string) - outputColumnNames: _col5 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col5 (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1760,11 +1856,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1848,39 +1944,47 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1900,11 +2004,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1982,39 +2086,47 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2034,11 +2146,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2124,39 +2236,47 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Outer Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2176,11 +2296,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2258,39 +2378,47 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: y Statistics: Num rows: 500 Data size: 5312 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: _col0 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 + Map 5 + Map Operator Tree: + TableScan + alias: x + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Outer Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col1 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2310,11 +2438,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2394,46 +2522,54 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: 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 - 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) + 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 + 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 Map 5 Map Operator Tree: 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 Filter Operator 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: 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 + 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 + 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: string) Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 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: _col1 (type: string), _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2453,11 +2589,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -2535,46 +2671,54 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: 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 - 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) + 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 + 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 Map 5 Map Operator Tree: 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 Filter Operator 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: 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 + 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 + 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: string) Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 - outputColumnNames: _col0, _col1 + 0 + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col1, _col2 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: _col1 (type: string), _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2594,11 +2738,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col2)) + 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 @@ -2678,45 +2822,53 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: 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 - 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: 53 Basic stats: COMPLETE Column stats: NONE + 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: 125 Data size: 1328 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: 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 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 - 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + 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: 7 Data size: 53 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: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2736,11 +2888,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -2818,45 +2970,53 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: 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 - 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: 53 Basic stats: COMPLETE Column stats: NONE + 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: 125 Data size: 1328 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: 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 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 - 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + 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: 7 Data size: 53 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: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col2 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2876,11 +3036,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) + expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) + aggregations: sum(_col0), sum(_col1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/count.q.out ql/src/test/results/clientpositive/tez/count.q.out index fe63101..876654b 100644 --- ql/src/test/results/clientpositive/tez/count.q.out +++ ql/src/test/results/clientpositive/tez/count.q.out @@ -51,11 +51,11 @@ 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: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) - keys: a (type: int), b (type: int), c (type: int) + aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) + keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -124,12 +124,12 @@ 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: a, b, c, d + expressions: 1 (type: int), a (type: int), b (type: int), c (type: int), d (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: 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) - keys: a (type: int), b (type: int), c (type: int), d (type: int) + aggregations: count(_col0), 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) 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 @@ -194,14 +194,14 @@ 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: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: a (type: int), b (type: int), c (type: int) + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ - Map-reduce partition columns: a (type: int) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: d (type: int) + value expressions: _col3 (type: int) Reducer 2 Reduce Operator Tree: Group By Operator @@ -261,17 +261,18 @@ 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: a, b, c, d + expressions: 1 (type: int), a (type: int), b (type: int), c (type: int), d (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: a (type: int), b (type: int), c (type: int), d (type: int) + key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Reducer 2 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(VALUE._col0), 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) mode: complete 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: 168 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/cross_join.q.out ql/src/test/results/clientpositive/tez/cross_join.q.out index ad0c759..840e6ff 100644 --- ql/src/test/results/clientpositive/tez/cross_join.q.out +++ ql/src/test/results/clientpositive/tez/cross_join.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[7][tables = [src, src2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- current explain select src.key from src join src src2 PREHOOK: type: QUERY @@ -19,20 +19,26 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + 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) Map 3 Map Operator Tree: TableScan alias: src - 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) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -61,7 +67,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[7][tables = [src, src2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- ansi cross join explain select src.key from src cross join src src2 PREHOOK: type: QUERY @@ -82,20 +88,26 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + 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) Map 3 Map Operator Tree: TableScan alias: src - 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) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -144,16 +156,20 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: src2 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 Map 3 Map Operator Tree: TableScan @@ -162,11 +178,15 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 Reducer 2 Reduce Operator Tree: Merge Join Operator diff --git ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out index 5286cac..e39e2d6 100644 --- ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out +++ ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out @@ -24,7 +24,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Shuffle Join MERGEJOIN[7][tables = [a, b]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -45,19 +45,27 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE - value expressions: key (type: string), value (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Map 3 Map Operator Tree: TableScan alias: a Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -66,10 +74,10 @@ STAGE PLANS: condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out index 3a2d725..05cff6b 100644 --- ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out +++ ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out @@ -24,7 +24,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Map Join MAPJOIN[7][bigTable=a] in task 'Map 2' is a cross product +Warning: Map Join MAPJOIN[14][bigTable=?] in task 'Map 2' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -45,39 +45,47 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE - value expressions: key (type: string), value (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 0 Data size: 114 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Map 2 Map Operator Tree: TableScan alias: a Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 {key} {value} - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col5, _col6 - input vertices: - 1 Map 1 - Statistics: Num rows: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} {_col1} + keys: + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 1 Statistics: Num rows: 31 Data size: 6393 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: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.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 ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out index 9a3315f..046fea9 100644 --- ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out @@ -1865,49 +1865,23 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 4 - Map 4 - Map Operator Tree: - TableScan - alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -1916,8 +1890,54 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: ds + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Target column: ds + Target Vertex: Map 5 + Reducer 3 + Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 @@ -1936,7 +1956,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1954,22 +1974,6 @@ 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 - Reducer 5 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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 Stage: Stage-0 Fetch Operator @@ -2834,9 +2838,9 @@ STAGE PLANS: Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) - Reducer 4 <- Map 6 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE) + Reducer 4 <- Map 8 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 7 <- Map 6 (SIMPLE_EDGE), Union 3 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 @@ -2846,10 +2850,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2861,24 +2865,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map 7 - Map Operator Tree: - TableScan - alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2886,6 +2879,21 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) + Map 8 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator @@ -2919,7 +2927,7 @@ STAGE PLANS: Target Input: srcpart Partition key expr: ds Target column: ds - Target Vertex: Map 6 + Target Vertex: Map 8 Reducer 4 Reduce Operator Tree: Merge Join Operator @@ -2958,7 +2966,7 @@ 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 - Reducer 8 + Reducer 7 Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -2991,7 +2999,7 @@ STAGE PLANS: Target Input: srcpart Partition key expr: ds Target column: ds - Target Vertex: Map 6 + Target Vertex: Map 8 Union 3 Vertex: Union 3 @@ -3043,10 +3051,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3060,11 +3068,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -3072,10 +3084,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3086,7 +3098,7 @@ STAGE PLANS: Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator @@ -3125,14 +3137,14 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} 1 - outputColumnNames: _col2 + outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col2 + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col2 (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE @@ -3162,7 +3174,7 @@ STAGE PLANS: Reducer 8 Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator @@ -3232,11 +3244,11 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 7 (CONTAINS) Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 7 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 7 (CONTAINS) - Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 7 (CONTAINS) + Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 3 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 @@ -3246,10 +3258,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3261,20 +3273,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -3283,10 +3297,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -3299,68 +3313,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 84 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Reducer 11 Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Filter Operator - predicate: _col0 is not null (type: boolean) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - 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 - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Target column: ds - Target Vertex: Map 5 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Target column: ds - Target Vertex: Map 8 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator @@ -3406,7 +3388,7 @@ STAGE PLANS: Target Input: srcpart Partition key expr: ds Target column: ds - Target Vertex: Map 8 + Target Vertex: Map 10 Reducer 4 Reduce Operator Tree: Merge Join Operator @@ -3437,23 +3419,59 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Reducer 9 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Filter Operator + predicate: _col0 is not null (type: boolean) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + 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 + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: ds + Target column: ds + Target Vertex: Map 5 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: ds + Target column: ds + Target Vertex: Map 10 Union 3 Vertex: Union 3 Union 7 @@ -4319,7 +4337,7 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 1 <- Reducer 4 (BROADCAST_EDGE) + Map 3 <- Reducer 2 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -4328,43 +4346,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - keys: - 0 ds (type: string) - 1 _col0 (type: string) - input vertices: - 1 Reducer 4 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Map 3 - Map Operator Tree: - TableScan - alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -4373,27 +4362,42 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 3 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Reducer 2 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + 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 + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 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 - 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 - 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 - Reducer 4 - Reduce Operator Tree: - Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 @@ -4421,7 +4425,25 @@ STAGE PLANS: Partition key expr: ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Target column: ds - Target Vertex: Map 1 + Target Vertex: Map 3 + Reducer 4 + 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 + 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 + 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 @@ -5004,10 +5026,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -5021,33 +5043,37 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - condition expressions: - 0 {ds} - 1 - keys: - 0 ds (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - input vertices: - 1 Union 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col2 + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Union 3 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col2 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 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: 2200 Data size: 23372 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: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan @@ -5055,10 +5081,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -5069,7 +5095,7 @@ STAGE PLANS: Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator @@ -5121,7 +5147,7 @@ STAGE PLANS: Reducer 7 Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator diff --git ql/src/test/results/clientpositive/tez/having.q.out ql/src/test/results/clientpositive/tez/having.q.out index 7eb6725..9463505 100644 --- ql/src/test/results/clientpositive/tez/having.q.out +++ ql/src/test/results/clientpositive/tez/having.q.out @@ -104,15 +104,15 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key <> 302) (type: boolean) + predicate: (UDFToDouble(key) <> 302.0) (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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -486,11 +486,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -757,15 +757,15 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > 300) (type: boolean) + predicate: (UDFToDouble(key) > 300.0) (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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -959,11 +959,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(value) - keys: key (type: string) + aggregations: max(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1231,11 +1231,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/limit_pushdown.q.out ql/src/test/results/clientpositive/tez/limit_pushdown.q.out index c765ab7..129c195 100644 --- ql/src/test/results/clientpositive/tez/limit_pushdown.q.out +++ ql/src/test/results/clientpositive/tez/limit_pushdown.q.out @@ -195,12 +195,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: value, key + expressions: value (type: string), (UDFToDouble(key) + 1.0) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum((key + 1)) - keys: value (type: string) + aggregations: sum(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -293,12 +293,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: value, key + expressions: value (type: string), (UDFToDouble(key) + 1.0) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg((key + 1)) - keys: value (type: string) + aggregations: avg(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -392,10 +392,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) - outputColumnNames: cdouble + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: cdouble (type: double) + keys: _col0 (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -485,11 +485,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: ctinyint, cdouble + outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT cdouble) - keys: ctinyint (type: tinyint), cdouble (type: double) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -582,11 +582,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: ctinyint, cstring1, cstring2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) - keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) + aggregations: count(DISTINCT _col1), count(DISTINCT _col2) + keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -706,11 +706,11 @@ 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: value, key + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(key) - keys: value (type: string) + aggregations: sum(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -814,9 +814,9 @@ STAGE PLANS: Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE) - Reducer 6 <- Reducer 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -825,12 +825,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -841,18 +841,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 value expressions: _col1 (type: bigint) - Map 4 + Map 5 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: key (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -876,29 +876,47 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit - Number of rows: 2 + 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 + TopN Hash Memory Usage: 0.3 + value expressions: _col0 (type: string), _col1 (type: bigint) + Reducer 3 + 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) 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Reducer 3 + Reducer 4 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3 + 1 {VALUE._col0} + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint) + expressions: _col0 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Limit @@ -911,7 +929,7 @@ 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 - Reducer 5 + Reducer 6 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -924,31 +942,21 @@ STAGE PLANS: outputColumnNames: _col0, _col1 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 - TopN Hash Memory Usage: 0.3 - value expressions: _col0 (type: string), _col1 (type: bigint) - Reducer 6 - 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) + Number of rows: 2 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: bigint) + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + 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 + 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: bigint) Stage: Stage-0 Fetch Operator @@ -981,16 +989,16 @@ 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: key, value + expressions: value (type: string), key (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: value (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: value (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: key (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator @@ -1238,16 +1246,16 @@ 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: key, value + expressions: concat(key, value, value, value, value, value, value, value, value, value) (type: string), key (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: concat(key, value, value, value, value, value, value, value, value, value) (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: concat(key, value, value, value, value, value, value, value, value, value) (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 2.0E-5 - value expressions: key (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out index b261f37..04b704e 100644 --- ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out @@ -70,63 +70,71 @@ STAGE PLANS: 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - Estimated key counts: Map 3 => 250 - keys: - 0 value (type: string) - 1 value (type: string) - outputColumnNames: _col0 - input vertices: - 1 Map 3 - Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 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 Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} + 0 {_col0} {_col1} 1 - Estimated key counts: Map 2 => 13 + Estimated key counts: Map 3 => 13 keys: 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0 + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 input vertices: - 1 Map 2 + 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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 + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 {_col0} + Estimated key counts: Map 2 => 250 + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1 + input vertices: + 0 Map 2 + Position of Big Table: 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.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: _col1 (type: string) + outputColumnNames: _col0 + 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.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: @@ -322,26 +330,30 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: src + 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 - 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: 1 - auto parallelism: true + predicate: value 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 + 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: 0 + auto parallelism: true Path -> Alias: #### A masked pattern was here #### 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: @@ -351,14 +363,14 @@ STAGE PLANS: columns.comments defaultdefault 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 @@ -371,43 +383,47 @@ STAGE PLANS: columns.comments defaultdefault 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 Truncated Path -> Alias: - /src1 [src1] + /src [src] Map 3 Map Operator Tree: TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: src1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: 1 - auto parallelism: true + 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 + tag: 1 + auto parallelism: true Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: src + base file name: src1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -417,14 +433,14 @@ STAGE PLANS: columns.comments defaultdefault 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 @@ -437,20 +453,20 @@ STAGE PLANS: columns.comments defaultdefault 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: - /src [src] + /src1 [src1] Stage: Stage-0 Fetch Operator @@ -481,71 +497,87 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 value (type: string) - 1 value (type: string) - outputColumnNames: _col0 - input vertices: - 1 Map 3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + 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 + 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 Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col0} + 0 {_col0} {_col1} 1 keys: 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0 + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 input vertices: - 1 Map 2 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + 1 Map 3 + Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - table: - 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: _col0 (type: string), _col1 (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 + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1 + input vertices: + 0 Map 2 + Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (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 Map 2 Map Operator Tree: TableScan - alias: src1 - 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 - 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 - Map 3 - Map Operator Tree: - TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value > 'val_450') (type: boolean) Statistics: Num rows: 166 Data size: 1763 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: value (type: string) + outputColumnNames: _col0 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 + Map 3 + Map Operator Tree: + TableScan + alias: src1 + 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 Stage: Stage-0 Fetch Operator @@ -567,87 +599,99 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE) + Map 3 <- Map 1 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE) + Reducer 4 <- Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: src + 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 + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + 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 + Map 2 + Map Operator Tree: + TableScan + alias: 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 + 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 + Map 3 + Map Operator Tree: + TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {ds} - 1 - keys: - 0 value (type: string) - 1 value (type: string) - outputColumnNames: _col0, _col2 - input vertices: - 1 Map 4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 {_col2} + 0 {_col0} {_col2} 1 keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col2 + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 input vertices: - 1 Map 3 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string) + 1 Map 1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col2} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col2 + input vertices: + 1 Map 2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col2 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 605 Data size: 6427 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: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Map 3 - Map Operator Tree: - TableScan - 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 - 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 - Map 4 - Map Operator Tree: - TableScan - alias: src - 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 - Reduce Output Operator - key expressions: value (type: string) - sort order: + - Map-reduce partition columns: value (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reducer 2 + 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 + value expressions: _col1 (type: bigint) + Reducer 4 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out index 31c77bc..647764b 100644 --- ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out +++ ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out @@ -199,11 +199,11 @@ 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: s, bo, bin, si, i, b + 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: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 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(s), count(bo), count(bin), count(si), max(i), min(b) + aggregations: count(), sum(_col0), sum(_col1), count(_col0), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) 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 @@ -259,11 +259,11 @@ 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: s, bo, bin, si, i, b + 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: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 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(s), count(bo), count(bin), count(si), max(i), min(b) + aggregations: count(), sum(_col0), sum(_col1), count(_col0), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) 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 @@ -456,10 +456,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: ts + outputColumnNames: _col0 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(ts) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/metadataonly1.q.out ql/src/test/results/clientpositive/tez/metadataonly1.q.out index cd038c8..58c1d04 100644 --- ql/src/test/results/clientpositive/tez/metadataonly1.q.out +++ ql/src/test/results/clientpositive/tez/metadataonly1.q.out @@ -139,10 +139,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -153,9 +153,9 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [test1] Path -> Partition: - -mr-10002default.test1{ds=1} + -mr-10003default.test1{ds=1} Partition base file name: ds=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -196,7 +196,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [test1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -290,11 +290,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(DISTINCT ds) - keys: ds (type: string) + aggregations: count(DISTINCT _col0) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -305,9 +305,9 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [test1] Path -> Partition: - -mr-10002default.test1{ds=1} + -mr-10003default.test1{ds=1} Partition base file name: ds=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -348,7 +348,7 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=1} [test1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -442,10 +442,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(ds) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -626,15 +626,15 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: test1 + alias: a2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -728,21 +728,25 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - /test1/ds=1 [test1] - /test1/ds=2 [test1] + /test1/ds=1 [a2] + /test1/ds=2 [a2] Map 5 Map Operator Tree: TableScan alias: a2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE GatherStats: false - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 0 - auto parallelism: true + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + tag: 0 + auto parallelism: true Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1021,11 +1025,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: ds, hr + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(DISTINCT hr) - keys: ds (type: string), hr (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -1037,11 +1041,11 @@ STAGE PLANS: tag: -1 auto parallelism: true Path -> Alias: - -mr-10002default.test2{ds=1, hr=1} [test2] - -mr-10003default.test2{ds=1, hr=2} [test2] - -mr-10004default.test2{ds=1, hr=3} [test2] + -mr-10003default.test2{ds=1, hr=1} [test2] + -mr-10004default.test2{ds=1, hr=2} [test2] + -mr-10005default.test2{ds=1, hr=3} [test2] Path -> Partition: - -mr-10002default.test2{ds=1, hr=1} + -mr-10003default.test2{ds=1, hr=1} Partition base file name: hr=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1082,7 +1086,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10003default.test2{ds=1, hr=2} + -mr-10004default.test2{ds=1, hr=2} Partition base file name: hr=2 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1123,7 +1127,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10004default.test2{ds=1, hr=3} + -mr-10005default.test2{ds=1, hr=3} Partition base file name: hr=3 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1165,9 +1169,9 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -mr-10002default.test2{ds=1, hr=1} [test2] - -mr-10003default.test2{ds=1, hr=2} [test2] - -mr-10004default.test2{ds=1, hr=3} [test2] + -mr-10003default.test2{ds=1, hr=1} [test2] + -mr-10004default.test2{ds=1, hr=2} [test2] + -mr-10005default.test2{ds=1, hr=3} [test2] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -1272,11 +1276,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: ds, hr + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(hr) - keys: ds (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -1515,10 +1519,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1529,10 +1533,10 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10002default.test1{ds=1} [test1] - -mr-10003default.test1{ds=2} [test1] + -mr-10003default.test1{ds=1} [test1] + -mr-10004default.test1{ds=2} [test1] Path -> Partition: - -mr-10002default.test1{ds=1} + -mr-10003default.test1{ds=1} Partition base file name: ds=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1572,7 +1576,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 - -mr-10003default.test1{ds=2} + -mr-10004default.test1{ds=2} Partition base file name: ds=2 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1613,8 +1617,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10002default.test1{ds=1} [test1] - -mr-10003default.test1{ds=2} [test1] + -mr-10003default.test1{ds=1} [test1] + -mr-10004default.test1{ds=2} [test1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -1767,11 +1771,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: ds, hr + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(DISTINCT hr) - keys: ds (type: string), hr (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE @@ -1783,13 +1787,13 @@ STAGE PLANS: tag: -1 auto parallelism: true Path -> Alias: - -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] + -mr-10003default.test2{ds=01_10_10, hr=01} [test2] + -mr-10004default.test2{ds=01_10_20, hr=02} [test2] + -mr-10005default.test2{ds=1, hr=1} [test2] + -mr-10006default.test2{ds=1, hr=2} [test2] + -mr-10007default.test2{ds=1, hr=3} [test2] Path -> Partition: - -mr-10002default.test2{ds=01_10_10, hr=01} + -mr-10003default.test2{ds=01_10_10, hr=01} Partition base file name: hr=01 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1830,7 +1834,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10003default.test2{ds=01_10_20, hr=02} + -mr-10004default.test2{ds=01_10_20, hr=02} Partition base file name: hr=02 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1871,7 +1875,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10004default.test2{ds=1, hr=1} + -mr-10005default.test2{ds=1, hr=1} Partition base file name: hr=1 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1912,7 +1916,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10005default.test2{ds=1, hr=2} + -mr-10006default.test2{ds=1, hr=2} Partition base file name: hr=2 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1953,7 +1957,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10006default.test2{ds=1, hr=3} + -mr-10007default.test2{ds=1, hr=3} Partition base file name: hr=3 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1995,11 +1999,11 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -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] + -mr-10003default.test2{ds=01_10_10, hr=01} [test2] + -mr-10004default.test2{ds=01_10_20, hr=02} [test2] + -mr-10005default.test2{ds=1, hr=1} [test2] + -mr-10006default.test2{ds=1, hr=2} [test2] + -mr-10007default.test2{ds=1, hr=3} [test2] Reducer 2 Needs Tagging: false Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/mrr.q.out ql/src/test/results/clientpositive/tez/mrr.q.out index 5718c32..090bae5 100644 --- ql/src/test/results/clientpositive/tez/mrr.q.out +++ ql/src/test/results/clientpositive/tez/mrr.q.out @@ -23,11 +23,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -413,17 +413,21 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: s2 + alias: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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) Map 5 Map Operator Tree: TableScan @@ -432,28 +436,32 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 condition expressions: - 0 - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col5, _col6 + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string), _col6 (type: string) - outputColumnNames: _col5, _col6 + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col6) - keys: _col5 (type: string), _col6 (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE @@ -830,26 +838,52 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 2 <- Map 1 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Map 1 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: s2 + alias: 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 - 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: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) - Map 2 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 4 + 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 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + 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) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Map 4 Map Operator Tree: TableScan alias: s1 @@ -857,35 +891,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 {key} {value} - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col5, _col6 - input vertices: - 1 Map 1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: string), _col6 (type: string) - outputColumnNames: _col5, _col6 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(DISTINCT _col6) - keys: _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - 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) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reducer 3 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + 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 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) @@ -902,7 +917,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) - Reducer 4 + Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: bigint) @@ -1301,11 +1316,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -1325,11 +1340,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -1349,11 +1364,11 @@ 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -1432,12 +1447,12 @@ STAGE PLANS: Inner Join 0 to 2 condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} - 1 {KEY.reducesinkkey0} {VALUE._col0} + 1 {VALUE._col0} 2 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col3, _col4, _col5 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint), _col4 (type: string), _col5 (type: bigint) + expressions: _col0 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (type: bigint), _col4 (type: string), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -1686,8 +1701,8 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 1 <- Reducer 3 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (SIMPLE_EDGE) + Map 3 <- Reducer 2 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1698,45 +1713,13 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} {_col1} - 1 {key} {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - input vertices: - 0 Reducer 3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (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 - 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 - Map 2 - Map Operator Tree: - TableScan - alias: 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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(value) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -1746,7 +1729,43 @@ STAGE PLANS: 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) - Reducer 3 + Map 3 + Map Operator Tree: + TableScan + alias: 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 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col1} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 1 Reducer 2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col3 (type: bigint), _col0 (type: string), _col1 (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 + 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 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out index 2af6134..58e9cd7 100644 --- ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out +++ ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out @@ -241,12 +241,12 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 0 + tag: 1 auto parallelism: true Path -> Alias: - -mr-10002default.src{} [src] + -mr-10003default.src{} [src] Path -> Partition: - -mr-10002default.src{} + -mr-10003default.src{} Partition base file name: src input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -291,7 +291,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - -mr-10002default.src{} [src] + -mr-10003default.src{} [src] Map 3 Map Operator Tree: TableScan @@ -312,12 +312,12 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10003default.srcpart{ds=2008-04-08, hr=11} [srcpart] - -mr-10004default.srcpart{ds=2008-04-08, hr=12} [srcpart] - -mr-10005default.srcpart{ds=2008-04-09, hr=11} [srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=12} [srcpart] + -mr-10004default.srcpart{ds=2008-04-08, hr=11} [srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=12} [srcpart] + -mr-10006default.srcpart{ds=2008-04-09, hr=11} [srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=12} [srcpart] Path -> Partition: - -mr-10003default.srcpart{ds=2008-04-08, hr=11} + -mr-10004default.srcpart{ds=2008-04-08, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -363,7 +363,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10004default.srcpart{ds=2008-04-08, hr=12} + -mr-10005default.srcpart{ds=2008-04-08, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -409,7 +409,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10005default.srcpart{ds=2008-04-09, hr=11} + -mr-10006default.srcpart{ds=2008-04-09, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -455,7 +455,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10006default.srcpart{ds=2008-04-09, hr=12} + -mr-10007default.srcpart{ds=2008-04-09, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -502,16 +502,16 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - -mr-10003default.srcpart{ds=2008-04-08, hr=11} [srcpart] - -mr-10004default.srcpart{ds=2008-04-08, hr=12} [srcpart] - -mr-10005default.srcpart{ds=2008-04-09, hr=11} [srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=12} [srcpart] + -mr-10004default.srcpart{ds=2008-04-08, hr=11} [srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=12} [srcpart] + -mr-10006default.srcpart{ds=2008-04-09, hr=11} [srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=12} [srcpart] Reducer 2 Needs Tagging: false Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} @@ -519,7 +519,7 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -553,13 +553,17 @@ STAGE PLANS: Limit Number of rows: 0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 1 - auto parallelism: true + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + tag: 0 + auto parallelism: true Stage: Stage-0 Fetch Operator @@ -654,15 +658,89 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count(_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 + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false + Path -> Alias: + -mr-10003default.src{} [src] + Path -> Partition: + -mr-10003default.src{} + Partition + base file name: src + input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments defaultdefault + 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.NullStructSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.NullStructSerDe + + 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 defaultdefault + 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 + Truncated Path -> Alias: + -mr-10003default.src{} [src] + Map 4 + Map Operator Tree: + TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -864,80 +942,6 @@ STAGE PLANS: /srcpart/ds=2008-04-08/hr=12 [srcpart] /srcpart/ds=2008-04-09/hr=11 [srcpart] /srcpart/ds=2008-04-09/hr=12 [srcpart] - Map 4 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: - 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-10002default.src{} [src] - Path -> Partition: - -mr-10002default.src{} - Partition - base file name: src - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments defaultdefault - 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.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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 defaultdefault - 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 - Truncated Path -> Alias: - -mr-10002default.src{} [src] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -1031,9 +1035,9 @@ 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 #### -2000 0 -Warning: Shuffle Join MERGEJOIN[15][tables = [a, b]] in Stage 'Reducer 2' is a cross product +2000 +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain extended select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b PREHOOK: type: QUERY @@ -1117,13 +1121,13 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 0 + tag: 1 value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10002default.src{} [src] + -mr-10003default.src{} [src] Path -> Partition: - -mr-10002default.src{} + -mr-10003default.src{} Partition base file name: src input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1168,7 +1172,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - -mr-10002default.src{} [src] + -mr-10003default.src{} [src] Map 3 Map Operator Tree: TableScan @@ -1189,12 +1193,12 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10003default.srcpart{ds=2008-04-08, hr=11} [srcpart] - -mr-10004default.srcpart{ds=2008-04-08, hr=12} [srcpart] - -mr-10005default.srcpart{ds=2008-04-09, hr=11} [srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=12} [srcpart] + -mr-10004default.srcpart{ds=2008-04-08, hr=11} [srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=12} [srcpart] + -mr-10006default.srcpart{ds=2008-04-09, hr=11} [srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=12} [srcpart] Path -> Partition: - -mr-10003default.srcpart{ds=2008-04-08, hr=11} + -mr-10004default.srcpart{ds=2008-04-08, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1240,7 +1244,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10004default.srcpart{ds=2008-04-08, hr=12} + -mr-10005default.srcpart{ds=2008-04-08, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1286,7 +1290,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10005default.srcpart{ds=2008-04-09, hr=11} + -mr-10006default.srcpart{ds=2008-04-09, hr=11} Partition base file name: hr=11 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1332,7 +1336,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - -mr-10006default.srcpart{ds=2008-04-09, hr=12} + -mr-10007default.srcpart{ds=2008-04-09, hr=12} Partition base file name: hr=12 input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat @@ -1379,24 +1383,27 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - -mr-10003default.srcpart{ds=2008-04-08, hr=11} [srcpart] - -mr-10004default.srcpart{ds=2008-04-08, hr=12} [srcpart] - -mr-10005default.srcpart{ds=2008-04-09, hr=11} [srcpart] - -mr-10006default.srcpart{ds=2008-04-09, hr=12} [srcpart] + -mr-10004default.srcpart{ds=2008-04-08, hr=11} [srcpart] + -mr-10005default.srcpart{ds=2008-04-08, hr=12} [srcpart] + -mr-10006default.srcpart{ds=2008-04-09, hr=11} [srcpart] + -mr-10007default.srcpart{ds=2008-04-09, hr=12} [srcpart] Reducer 2 Needs Tagging: false Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: 0 {VALUE._col0} 1 {VALUE._col0} + filter predicates: + 0 + 1 {true} outputColumnNames: _col0, _col1 Position of Big Table: 0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) + expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator @@ -1430,12 +1437,16 @@ STAGE PLANS: Limit Number of rows: 0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - tag: 1 - value expressions: _col0 (type: string) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + tag: 0 + value expressions: _col0 (type: string) + auto parallelism: false Stage: Stage-0 Fetch Operator @@ -1443,7 +1454,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[15][tables = [a, b]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -1535,23 +1546,97 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 4 <- Union 3 (CONTAINS) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS) + Map 5 <- Union 3 (CONTAINS) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Union 3 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + tag: 1 + auto parallelism: true + Path -> Alias: + -mr-10003default.src{} [src] + Path -> Partition: + -mr-10003default.src{} + Partition + base file name: src + input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments defaultdefault + 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.NullStructSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.NullStructSerDe + + 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 defaultdefault + 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 + Truncated Path -> Alias: + -mr-10003default.src{} [src] + Map 4 + Map Operator Tree: + TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: 1 - auto parallelism: true + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + tag: 0 + auto parallelism: true Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1744,7 +1829,7 @@ STAGE PLANS: /srcpart/ds=2008-04-08/hr=12 [srcpart] /srcpart/ds=2008-04-09/hr=11 [srcpart] /srcpart/ds=2008-04-09/hr=12 [srcpart] - Map 4 + Map 5 Map Operator Tree: TableScan alias: src @@ -1827,108 +1912,43 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [src] - Map 5 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: true - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### 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 defaultdefault - 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 defaultdefault - 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 - Truncated Path -> Alias: - /src [src] Reducer 2 Needs Tagging: false Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 + 0 + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1 Position of Big Table: 0 - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Select Operator - expressions: _col0 (type: string) - 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 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 + 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 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 Union 3 Vertex: Union 3 diff --git ql/src/test/results/clientpositive/tez/subquery_exists.q.out ql/src/test/results/clientpositive/tez/subquery_exists.q.out index 24f2d10..ade2d1f 100644 --- ql/src/test/results/clientpositive/tez/subquery_exists.q.out +++ ql/src/test/results/clientpositive/tez/subquery_exists.q.out @@ -37,25 +37,29 @@ STAGE PLANS: 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 - Reduce Output Operator - key expressions: value (type: string), key (type: string) - sort order: ++ - Map-reduce partition columns: value (type: string), key (type: string) + 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 + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Map 3 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 > '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: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col1 (type: string), _col2 (type: string) + 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 diff --git ql/src/test/results/clientpositive/tez/subquery_in.q.out ql/src/test/results/clientpositive/tez/subquery_in.q.out index b35a266..9786a20 100644 --- ql/src/test/results/clientpositive/tez/subquery_in.q.out +++ ql/src/test/results/clientpositive/tez/subquery_in.q.out @@ -124,7 +124,7 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: s1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '9') (type: boolean) @@ -151,12 +151,16 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 - value expressions: value (type: string) + 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) Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -247,15 +251,19 @@ STAGE PLANS: 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 - 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: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Map 3 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 > '9') and value is not null) (type: boolean) @@ -371,26 +379,34 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_size (type: int) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_mfgr (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Map 5 Map Operator Tree: TableScan alias: part Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(p_size) is not null (type: boolean) - Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(p_size) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(p_size) (type: double) + Select Operator + expressions: p_name (type: string), p_size (type: int), UDFToDouble(p_size) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col2 is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col2 (type: double) + sort order: + + Map-reduce partition columns: _col2 (type: double) + Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Reducer 2 Reduce Operator Tree: Extract @@ -401,7 +417,7 @@ STAGE PLANS: predicate: (_wcol0 <= 2) (type: boolean) Statistics: Num rows: 10 Data size: 1057 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 1057 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -443,12 +459,12 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 condition expressions: - 0 {VALUE._col1} {VALUE._col5} + 0 {VALUE._col0} {VALUE._col1} 1 - outputColumnNames: _col1, _col5 + outputColumnNames: _col0, _col1 Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col5 (type: int) + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 16 Data size: 1744 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -526,35 +542,43 @@ STAGE PLANS: Filter Operator predicate: (p_size is not null and p_mfgr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_size (type: int), p_mfgr (type: string) - sort order: ++ - Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) + Select Operator + expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + key expressions: _col2 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Map 3 Map Operator Tree: TableScan - alias: part + alias: b Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_size (type: int) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_mfgr (type: string), p_size (type: int) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int) Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: Left Semi Join 0 to 1 condition expressions: - 0 {VALUE._col1} {KEY.reducesinkkey1} {KEY.reducesinkkey0} + 0 {VALUE._col0} {KEY.reducesinkkey1} {KEY.reducesinkkey0} 1 - outputColumnNames: _col1, _col2, _col5 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 930 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 930 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -571,10 +595,10 @@ STAGE PLANS: PTF Operator Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_wcol0 <= 2) and _col2 is not null) (type: boolean) + predicate: ((_wcol0 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -673,8 +697,8 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -683,27 +707,14 @@ STAGE PLANS: alias: b 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: 125 Data size: 1328 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Map 3 - Map Operator Tree: - TableScan - 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 Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string), value (type: string) + 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 @@ -712,29 +723,25 @@ STAGE PLANS: 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 4 + Map Operator Tree: + TableScan + alias: b + 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: 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: 125 Data size: 1328 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: - Merge Join Operator - condition map: - Left Semi Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - 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 - Reducer 4 - Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial @@ -754,6 +761,27 @@ STAGE PLANS: 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 + Reducer 3 + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + 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 diff --git ql/src/test/results/clientpositive/tez/tez_join_tests.q.out ql/src/test/results/clientpositive/tez/tez_join_tests.q.out index 64285b7..957f892 100644 --- ql/src/test/results/clientpositive/tez/tez_join_tests.q.out +++ ql/src/test/results/clientpositive/tez/tez_join_tests.q.out @@ -12,10 +12,10 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) - Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) + Reducer 6 <- Reducer 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -23,68 +23,49 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) - Map 6 - Map Operator Tree: - TableScan - alias: c - 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) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) - Map 7 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Map 4 Map Operator Tree: TableScan alias: a Statistics: Num rows: 25 Data size: 191 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: _col0 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Map 7 + Map Operator Tree: + TableScan + 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) Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 - condition expressions: - 0 - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _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 - value expressions: _col0 (type: string) - Reducer 4 - Reduce Operator Tree: - Merge Join Operator - condition map: Right Outer Join0 to 1 condition expressions: 0 {VALUE._col0} {KEY.reducesinkkey0} @@ -100,7 +81,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reducer 5 + Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) @@ -113,6 +94,37 @@ 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 + Reducer 5 + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _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 + value expressions: _col0 (type: string) Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/tez/tez_joins_explain.q.out ql/src/test/results/clientpositive/tez/tez_joins_explain.q.out index b600345..2352203 100644 --- ql/src/test/results/clientpositive/tez/tez_joins_explain.q.out +++ ql/src/test/results/clientpositive/tez/tez_joins_explain.q.out @@ -12,10 +12,10 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) - Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) + Reducer 6 <- Reducer 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -23,68 +23,49 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 500 Data size: 5312 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: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) - Map 6 - Map Operator Tree: - TableScan - alias: c - 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) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) - Map 7 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Map 4 Map Operator Tree: TableScan alias: a Statistics: Num rows: 25 Data size: 191 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: _col0 Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Map 7 + Map Operator Tree: + TableScan + 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) Reducer 2 Reduce Operator Tree: Merge Join Operator condition map: - Left Outer Join0 to 1 - condition expressions: - 0 - 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _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 - value expressions: _col0 (type: string) - Reducer 4 - Reduce Operator Tree: - Merge Join Operator - condition map: Right Outer Join0 to 1 condition expressions: 0 {VALUE._col0} {KEY.reducesinkkey0} @@ -100,7 +81,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reducer 5 + Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) @@ -113,6 +94,37 @@ 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 + Reducer 5 + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _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 + value expressions: _col0 (type: string) Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/tez/tez_smb_main.q.out ql/src/test/results/clientpositive/tez/tez_smb_main.q.out index 1f4e305..e123aaa 100644 --- ql/src/test/results/clientpositive/tez/tez_smb_main.q.out +++ ql/src/test/results/clientpositive/tez/tez_smb_main.q.out @@ -23,12 +23,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) 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) + 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 - value expressions: value (type: string) + 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: string) Map 3 Map Operator Tree: TableScan @@ -37,12 +41,16 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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 - value expressions: value (type: string) + 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) Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -51,10 +59,10 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} {VALUE._col0} 1 {KEY.reducesinkkey0} {VALUE._col0} - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + 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 File Output Operator diff --git ql/src/test/results/clientpositive/tez/tez_union.q.out ql/src/test/results/clientpositive/tez/tez_union.q.out index e1ea884..aca83d3 100644 --- ql/src/test/results/clientpositive/tez/tez_union.q.out +++ ql/src/test/results/clientpositive/tez/tez_union.q.out @@ -16,8 +16,8 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 1 <- Map 3 (BROADCAST_EDGE), Union 2 (CONTAINS) - Map 4 <- Union 2 (CONTAINS) + Map 1 <- Map 4 (BROADCAST_EDGE), Union 2 (CONTAINS) + Map 3 <- Union 2 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 @@ -26,47 +26,37 @@ STAGE PLANS: alias: s1 Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - input vertices: - 1 Map 3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1 + input vertices: + 1 Map 4 Select Operator expressions: _col0 (type: string), _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 + Select Operator + expressions: _col0 (type: string), _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 Map 3 Map Operator Tree: TableScan - alias: s3 - 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 - 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 - Map 4 - Map Operator Tree: - TableScan - alias: s2 + alias: s1 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 @@ -79,6 +69,23 @@ 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 + Map 4 + Map Operator Tree: + TableScan + alias: 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 + 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 Union 2 Vertex: Union 2 @@ -159,10 +166,10 @@ STAGE PLANS: Tez Edges: Map 1 <- Union 2 (CONTAINS) - Map 5 <- Union 6 (CONTAINS) - Map 7 <- Union 2 (CONTAINS) - Map 8 <- Union 6 (CONTAINS) - Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 6 (SIMPLE_EDGE) + Map 5 <- Union 2 (CONTAINS) + Map 6 <- Union 7 (CONTAINS) + Map 8 <- Union 7 (CONTAINS) + Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 7 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: @@ -175,10 +182,13 @@ STAGE PLANS: Select Operator expressions: key (type: string) outputColumnNames: _col0 - 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Map 5 Map Operator Tree: TableScan @@ -188,11 +198,14 @@ STAGE PLANS: Select Operator expressions: key (type: string) outputColumnNames: _col0 - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Map 7 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Map 6 Map Operator Tree: TableScan alias: src @@ -201,10 +214,13 @@ STAGE PLANS: Select Operator expressions: key (type: string) outputColumnNames: _col0 - 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Map 8 Map Operator Tree: TableScan @@ -214,10 +230,13 @@ STAGE PLANS: Select Operator expressions: key (type: string) outputColumnNames: _col0 - 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Reducer 3 Reduce Operator Tree: Merge Join Operator @@ -258,8 +277,8 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Union 2 Vertex: Union 2 - Union 6 - Vertex: Union 6 + Union 7 + Vertex: Union 7 Stage: Stage-0 Fetch Operator @@ -316,90 +335,100 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 2 <- Map 1 (BROADCAST_EDGE), Union 3 (CONTAINS) - Map 4 <- Map 1 (BROADCAST_EDGE), Union 3 (CONTAINS) + Map 1 <- Map 3 (BROADCAST_EDGE), Union 2 (CONTAINS) + Map 4 <- Map 3 (BROADCAST_EDGE), Union 2 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: 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 - 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: 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 - Map 2 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 3 + Select Operator + expressions: _col1 (type: string), _col0 (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 + Map 3 Map Operator Tree: TableScan - alias: src + alias: 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 {_col0} - keys: - 0 key (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col5 - input vertices: - 0 Map 1 - Select Operator - expressions: _col0 (type: string), _col5 (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 + 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 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 Map 4 Map Operator Tree: TableScan - alias: src + alias: s1 Filter Operator predicate: key is not null (type: boolean) Select Operator expressions: key (type: string) outputColumnNames: _col0 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 {_col0} - keys: - 0 key (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col5 - input vertices: - 0 Map 1 - Select Operator - expressions: _col0 (type: string), _col5 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (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 - Union 3 - Vertex: Union 3 + input vertices: + 1 Map 3 + Select Operator + expressions: _col1 (type: string), _col0 (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 + Union 2 + Vertex: Union 2 Stage: Stage-0 Fetch Operator @@ -483,10 +512,10 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 2 <- Map 1 (BROADCAST_EDGE), Map 5 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Union 3 (CONTAINS) - Map 7 <- Map 1 (BROADCAST_EDGE), Map 6 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Union 3 (CONTAINS) - Map 9 <- Map 1 (BROADCAST_EDGE), Map 10 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Union 3 (CONTAINS) - Reducer 4 <- Union 3 (SIMPLE_EDGE) + Map 10 <- Map 1 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Union 4 (CONTAINS) + Map 3 <- Map 1 (BROADCAST_EDGE), Map 7 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Union 4 (CONTAINS) + Map 6 <- Map 1 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) + Reducer 5 <- Union 4 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -497,230 +526,298 @@ STAGE PLANS: Filter Operator 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: 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: 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 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 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 Map 10 Map Operator Tree: TableScan - alias: s5 - 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 - 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 - Map 2 - Map Operator Tree: - TableScan - alias: s2 + alias: s1 Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - input vertices: - 1 Map 5 - Select Operator - expressions: _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0 - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - condition expressions: - 0 {key} - 1 {_col0} - 2 {key} - keys: - 0 key (type: string) - 1 _col0 (type: string) - 2 key (type: string) - outputColumnNames: _col0, _col5, _col6 - input vertices: - 0 Map 1 - 2 Map 8 + input vertices: + 1 Map 2 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - value expressions: _col0 (type: string), _col1 (type: string) - Map 5 + expressions: _col0 (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 8 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 1 + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + value expressions: _col0 (type: string), _col1 (type: string) + Map 2 Map Operator Tree: TableScan - alias: s3 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map 6 + 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 + Map 3 Map Operator Tree: TableScan - alias: s7 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: s1 Filter Operator 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: 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 - Map 7 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 7 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 8 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 1 + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + value expressions: _col0 (type: string), _col1 (type: string) + Map 6 Map Operator Tree: TableScan - alias: s6 + alias: s1 Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - input vertices: - 1 Map 6 - Select Operator - expressions: _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0 - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - condition expressions: - 0 {key} - 1 {_col0} - 2 {key} - keys: - 0 key (type: string) - 1 _col0 (type: string) - 2 key (type: string) - outputColumnNames: _col0, _col5, _col6 - input vertices: - 0 Map 1 - 2 Map 8 + input vertices: + 1 Map 9 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - value expressions: _col0 (type: string), _col1 (type: string) - Map 8 + expressions: _col0 (type: string) + outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 8 + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 1 + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + value expressions: _col0 (type: string), _col1 (type: string) + Map 7 Map Operator Tree: TableScan - alias: s8 + alias: 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 - 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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) + 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 + Map 8 + Map Operator Tree: + TableScan + alias: 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 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 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 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 Map 9 Map Operator Tree: TableScan - alias: s4 + alias: s1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - input vertices: - 1 Map 10 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - condition expressions: - 0 {key} - 1 {_col0} - 2 {key} - keys: - 0 key (type: string) - 1 _col0 (type: string) - 2 key (type: string) - outputColumnNames: _col0, _col5, _col6 - input vertices: - 0 Map 1 - 2 Map 8 - Select Operator - expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - value expressions: _col0 (type: string), _col1 (type: string) - Reducer 4 + 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 + Reducer 5 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1815 Data size: 19278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 10602 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1815 Data size: 19278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 10602 Basic stats: COMPLETE Column stats: NONE table: 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 3 - Vertex: Union 3 + Union 4 + Vertex: Union 4 Stage: Stage-0 Fetch Operator @@ -884,8 +981,8 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 1 <- Map 3 (BROADCAST_EDGE), Union 2 (CONTAINS) - Map 4 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS) + Map 1 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS) + Map 4 <- Map 3 (BROADCAST_EDGE), Union 2 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 @@ -894,86 +991,100 @@ STAGE PLANS: alias: s2 Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - input vertices: - 1 Map 3 - Select Operator - expressions: _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0 + input vertices: + 1 Map 5 Select Operator expressions: _col0 (type: string) 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: string) + 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 Map 3 Map Operator Tree: TableScan - alias: s3 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 Map 4 Map Operator Tree: TableScan - alias: s4 + alias: s2 Filter Operator predicate: key is not null (type: boolean) - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string) outputColumnNames: _col0 - input vertices: - 1 Map 5 - Select Operator - expressions: _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0 + input vertices: + 1 Map 3 Select Operator expressions: _col0 (type: string) 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: string) + 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 Map 5 Map Operator Tree: TableScan - alias: s5 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 Union 2 Vertex: Union 2 @@ -1072,44 +1183,51 @@ STAGE PLANS: Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Map Join Operator - condition map: - Left Outer Join0 to 1 - condition expressions: - 0 {_col0} {_col1} - 1 {key} {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - input vertices: - 1 Map 3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Map Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} {_col1} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - 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 + input vertices: + 1 Map 3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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 Map 3 Map Operator Tree: TableScan - alias: s + alias: src Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 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) + 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 - value expressions: value (type: string) + 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) + 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) Map 4 Map Operator Tree: TableScan @@ -1117,27 +1235,30 @@ STAGE PLANS: Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Map Join Operator - condition map: - Left Outer Join0 to 1 - condition expressions: - 0 {_col0} {_col1} - 1 {key} {value} - keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - input vertices: - 1 Map 3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Map Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 {_col0} {_col1} + 1 {_col0} {_col1} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - 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 + input vertices: + 1 Map 3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + 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 Union 2 Vertex: Union 2 @@ -1177,39 +1298,46 @@ STAGE PLANS: Select Operator expressions: key (type: string) outputColumnNames: _col0 - 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Map 3 Map Operator Tree: TableScan - alias: s + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join0 to 1 - condition expressions: - 0 {_col0} - 1 {key} - keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col2 - input vertices: - 0 Union 2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1 + input vertices: + 0 Union 2 Statistics: Num rows: 1100 Data size: 11686 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: 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 + 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 Map 4 Map Operator Tree: TableScan @@ -1217,10 +1345,13 @@ STAGE PLANS: Select Operator expressions: key (type: string) outputColumnNames: _col0 - 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Union 2 Vertex: Union 2 diff --git ql/src/test/results/clientpositive/tez/union2.q.out ql/src/test/results/clientpositive/tez/union2.q.out index 2249b1b..06cb30b 100644 --- ql/src/test/results/clientpositive/tez/union2.q.out +++ ql/src/test/results/clientpositive/tez/union2.q.out @@ -31,8 +31,10 @@ STAGE PLANS: alias: s1 Select Operator Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Reduce Output Operator @@ -41,11 +43,13 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: s2 + alias: s1 Select Operator Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Reduce Output Operator diff --git ql/src/test/results/clientpositive/tez/union5.q.out ql/src/test/results/clientpositive/tez/union5.q.out index d35ed31..e161460 100644 --- ql/src/test/results/clientpositive/tez/union5.q.out +++ ql/src/test/results/clientpositive/tez/union5.q.out @@ -33,9 +33,11 @@ STAGE PLANS: alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -46,12 +48,14 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: s2 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -66,13 +70,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Select Operator - expressions: 'tst1' (type: string) + expressions: 'tst2' (type: string) outputColumnNames: _col0 Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -107,13 +111,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Select Operator - expressions: 'tst2' (type: string) + expressions: 'tst1' (type: string) outputColumnNames: _col0 Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/tez/union7.q.out ql/src/test/results/clientpositive/tez/union7.q.out index 2971029..bde4608 100644 --- ql/src/test/results/clientpositive/tez/union7.q.out +++ ql/src/test/results/clientpositive/tez/union7.q.out @@ -22,39 +22,23 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 5 <- Union 3 (CONTAINS) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) - Reducer 4 <- Union 3 (SIMPLE_EDGE) + Map 1 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE), Union 2 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: 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 - 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: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Map 5 - Map Operator Tree: - TableScan alias: s2 Select Operator expressions: key (type: string) outputColumnNames: _col0 Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -63,29 +47,25 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) value expressions: _col1 (type: bigint) - Reducer 2 - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Select Operator - expressions: 'tst1' (type: string) - outputColumnNames: _col0 + Map 4 + Map Operator Tree: + TableScan + alias: s1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string) + expressions: 1 (type: int) outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count(_col0) mode: hash - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 + 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) - value expressions: _col1 (type: bigint) - Reducer 4 + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 3 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -104,8 +84,30 @@ 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 - Union 3 - Vertex: Union 3 + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Select Operator + expressions: 'tst1' (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + value expressions: _col1 (type: bigint) + Union 2 + Vertex: Union 2 Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/tez/union8.q.out ql/src/test/results/clientpositive/tez/union8.q.out index c09124e..07a0639 100644 --- ql/src/test/results/clientpositive/tez/union8.q.out +++ ql/src/test/results/clientpositive/tez/union8.q.out @@ -46,35 +46,41 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: s2 + alias: s1 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Select Operator expressions: _col0 (type: string), _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 + Select Operator + expressions: _col0 (type: string), _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 Map 4 Map Operator Tree: TableScan - alias: s3 + alias: s1 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Select Operator expressions: _col0 (type: string), _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 + Select Operator + expressions: _col0 (type: string), _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 Union 2 Vertex: Union 2 diff --git ql/src/test/results/clientpositive/tez/union9.q.out ql/src/test/results/clientpositive/tez/union9.q.out index d33824b..aad619a 100644 --- ql/src/test/results/clientpositive/tez/union9.q.out +++ ql/src/test/results/clientpositive/tez/union9.q.out @@ -34,21 +34,26 @@ STAGE PLANS: alias: s1 Select Operator Select Operator - Group By Operator - aggregations: count(1) - mode: hash + Select Operator + expressions: 1 (type: int) outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count(_col0) + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Map 4 Map Operator Tree: TableScan - alias: s2 + alias: s1 Select Operator Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Reduce Output Operator @@ -57,16 +62,19 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: s3 + alias: s1 Select Operator Select Operator - Group By Operator - aggregations: count(1) - mode: hash + Select Operator + expressions: 1 (type: int) outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Group By Operator + aggregations: count(_col0) + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reducer 3 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/tez/vector_cast_constant.q.out ql/src/test/results/clientpositive/tez/vector_cast_constant.q.out index c2592dd..d668dee 100644 --- ql/src/test/results/clientpositive/tez/vector_cast_constant.q.out +++ ql/src/test/results/clientpositive/tez/vector_cast_constant.q.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: i + expressions: i (type: int), 50 (type: int), 50.0 (type: double), CAST( 50 AS decimal(10,0)) (type: decimal(10,0)) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(50), avg(UDFToDouble(50)), avg(CAST( 50 AS decimal(10,0))) - keys: i (type: int) + aggregations: avg(_col1), avg(_col2), avg(_col3) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE @@ -142,7 +142,7 @@ 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 Reducer 2 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out index 7c89109..2b28bb5 100644 --- ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out +++ ql/src/test/results/clientpositive/tez/vector_count_distinct.q.out @@ -1257,11 +1257,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ws_order_number (type: int) - outputColumnNames: ws_order_number + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT ws_order_number) - keys: ws_order_number (type: int) + aggregations: count(DISTINCT _col0) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out index f1b7b8b..2713afa 100644 --- ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out +++ ql/src/test/results/clientpositive/tez/vector_decimal_aggregate.q.out @@ -50,11 +50,11 @@ 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: cint, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() - keys: cint (type: int) + aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() + keys: _col0 (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 @@ -155,11 +155,11 @@ 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: cint, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), avg(cdecimal1), stddev_pop(cdecimal1), stddev_samp(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), avg(cdecimal2), stddev_pop(cdecimal2), stddev_samp(cdecimal2), count() - keys: cint (type: int) + 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) 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 diff --git ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out index 1ae5982..7926e45 100644 --- ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out +++ ql/src/test/results/clientpositive/tez/vector_distinct_2.q.out @@ -125,10 +125,10 @@ 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: s, t + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: s (type: string), t (type: tinyint) + keys: _col0 (type: string), _col1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vector_elt.q.out ql/src/test/results/clientpositive/tez/vector_elt.q.out index d7a46e1..b27798a 100644 --- ql/src/test/results/clientpositive/tez/vector_elt.q.out +++ ql/src/test/results/clientpositive/tez/vector_elt.q.out @@ -19,7 +19,7 @@ STAGE PLANS: Filter Operator predicate: (ctinyint > 0) (type: boolean) Select Operator - expressions: ((ctinyint % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((ctinyint % 2) + 1), cstring1, cint) (type: string) + 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 Limit Number of rows: 10 diff --git ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out index 491c6f7..d614449 100644 --- ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out +++ ql/src/test/results/clientpositive/tez/vector_groupby_3.q.out @@ -125,11 +125,11 @@ 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: s, t, b + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(b) - keys: s (type: string), t (type: tinyint) + aggregations: max(_col2) + keys: _col0 (type: string), _col1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out index d45fbde..e7c1bbc 100644 --- ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out +++ ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out @@ -245,10 +245,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: ss_ticket_number + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ss_ticket_number (type: int) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -367,10 +367,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: ss_ticket_number + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ss_ticket_number (type: int) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out index 71367c4..528c116 100644 --- ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out +++ ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out @@ -31,66 +31,78 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: hd + alias: c Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ctinyint (type: tinyint) - sort order: + - Map-reduce partition columns: ctinyint (type: tinyint) + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 2 Map Operator Tree: TableScan alias: c Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - condition expressions: - 0 {ctinyint} - 1 - keys: - 0 cint (type: int) - 1 cint (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 4 - Statistics: Num rows: 13516 Data size: 414960 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ctinyint (type: tinyint), cint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 condition expressions: - 0 + 0 {_col0} 1 keys: - 0 _col0 (type: tinyint) - 1 ctinyint (type: tinyint) + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 input vertices: - 1 Map 1 - Statistics: Num rows: 14867 Data size: 456456 Basic stats: COMPLETE Column stats: NONE - Select Operator + 1 Map 4 + Statistics: Num rows: 13516 Data size: 414960 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + input vertices: + 1 Map 1 Statistics: Num rows: 14867 Data size: 456456 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: 456456 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) Execution mode: vectorized Map 4 Map Operator Tree: TableScan - alias: cd + alias: c Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: cint (type: int) - sort order: + - Map-reduce partition columns: cint (type: int) + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 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: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 3 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out index 8a4d25a..2c526ee 100644 --- ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out +++ ql/src/test/results/clientpositive/tez/vector_orderby_5.q.out @@ -126,11 +126,11 @@ 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: bo, b + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(b) - keys: bo (type: boolean) + aggregations: max(_col1) + keys: _col0 (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out index dce61d5..32df88f 100644 --- ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out +++ ql/src/test/results/clientpositive/tez/vector_partitioned_date_time.q.out @@ -373,11 +373,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: fl_date + outputColumnNames: _col0 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: fl_date (type: date) + keys: _col0 (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE @@ -1157,11 +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: fl_date + outputColumnNames: _col0 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: fl_date (type: date) + keys: _col0 (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE @@ -1965,11 +1965,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_time (type: timestamp) - outputColumnNames: fl_time + outputColumnNames: _col0 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: fl_time (type: timestamp) + keys: _col0 (type: timestamp) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out index 14acfc5..830b38a 100644 --- ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out +++ ql/src/test/results/clientpositive/tez/vector_reduce_groupby_decimal.q.out @@ -46,11 +46,11 @@ 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: cint, cdouble, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(cdecimal1) - keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) + aggregations: min(_col2) + keys: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (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 diff --git ql/src/test/results/clientpositive/tez/vectorization_0.q.out ql/src/test/results/clientpositive/tez/vectorization_0.q.out index 7703158..ac8842d 100644 --- ql/src/test/results/clientpositive/tez/vectorization_0.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_0.q.out @@ -133,10 +133,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: ctinyint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(ctinyint) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -451,10 +451,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: cbigint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(cbigint) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -769,10 +769,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: cfloat + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(cfloat) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1026,14 +1026,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 like '%b%') or ((79.553 <> cint) or (cbigint < cdouble))) (type: boolean) + predicate: ((cstring2 like '%b%') or ((79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: cbigint, cfloat, ctinyint + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) + aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -1050,7 +1050,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (- _col0) (type: double), (-6432 + _col0) (type: double), _col1 (type: double), (- (-6432 + _col0)) (type: double), ((- (-6432 + _col0)) + (-6432 + _col0)) (type: double), _col2 (type: double), (- (-6432 + _col0)) (type: double), (-6432 + (- (-6432 + _col0))) (type: double), (- (-6432 + _col0)) (type: double), ((- (-6432 + _col0)) / (- (-6432 + _col0))) (type: double), _col3 (type: bigint), _col4 (type: double), (_col2 % _col1) (type: double), (- _col2) (type: double), ((- (-6432 + _col0)) * (- _col0)) (type: double), _col5 (type: tinyint), (- _col5) (type: tinyint) + 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 File Output Operator diff --git ql/src/test/results/clientpositive/tez/vectorization_13.q.out ql/src/test/results/clientpositive/tez/vectorization_13.q.out index 3410c33..11ab84b 100644 --- ql/src/test/results/clientpositive/tez/vectorization_13.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_13.q.out @@ -79,15 +79,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > 11) and ((ctimestamp2 <> 12) and (ctinyint < 9763215.5639)))) (type: boolean) + predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > 11.0) and ((UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 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: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) - keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE @@ -107,7 +107,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 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 * ((- _col1) + _col5)) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col10 (type: tinyint) + 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 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Limit @@ -316,15 +316,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > -1.388) and ((ctimestamp2 <> -1.3359999999999999) and (ctinyint < 9763215.5639)))) (type: boolean) + predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > -1.388) and ((UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 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: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) - keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE @@ -344,7 +344,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 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 * ((- _col1) + _col5)) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col10 (type: tinyint) + 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 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/tez/vectorization_14.q.out ql/src/test/results/clientpositive/tez/vectorization_14.q.out index 871d442..8ca24aa 100644 --- ql/src/test/results/clientpositive/tez/vectorization_14.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_14.q.out @@ -82,15 +82,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((ctinyint <= cbigint) and ((cint <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < ctinyint)) and ((cbigint > -257) or (cfloat < cint))) (type: boolean) + predicate: ((((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < UDFToDouble(ctinyint))) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double) - outputColumnNames: ctimestamp1, cfloat, cstring1, cboolean1, cdouble + 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 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp((- ((- 26.28) + cdouble))), max(cfloat), stddev_pop(cfloat), count(cfloat), var_pop(cfloat), var_samp(cfloat) - keys: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE @@ -110,7 +110,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 303 Data size: 9301 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), (_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), (_col1 - _col4) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (_col1 - _col4)) (type: double) + 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 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git ql/src/test/results/clientpositive/tez/vectorization_15.q.out ql/src/test/results/clientpositive/tez/vectorization_15.q.out index 79e6e9b..8140494 100644 --- ql/src/test/results/clientpositive/tez/vectorization_15.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_15.q.out @@ -78,15 +78,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cstring2 like '%ss%') or (cstring1 like '10%')) or ((cint >= -75) and ((ctinyint = csmallint) and (cdouble >= -3728)))) (type: boolean) + predicate: ((cstring2 like '%ss%') or ((cstring1 like '10%') or ((cint >= -75) and ((UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: cfloat, cboolean1, cdouble, cstring1, ctinyint, cint, ctimestamp1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) - keys: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -106,7 +106,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 6144 Data size: 188618 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 - _col5) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (_col5 - _col0) (type: float), (-23 % _col4) (type: int), (- (-26.28 - _col5)) (type: double), _col12 (type: double) + 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 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git ql/src/test/results/clientpositive/tez/vectorization_16.q.out ql/src/test/results/clientpositive/tez/vectorization_16.q.out index 5d18b83..f7bea1b 100644 --- ql/src/test/results/clientpositive/tez/vectorization_16.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_16.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: cstring1, cdouble, ctimestamp1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) - keys: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) + aggregations: count(_col1), stddev_samp(_col1), min(_col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE @@ -83,7 +83,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 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 * _col3) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (_col3 / -1.389) (type: double), _col4 (type: double) + 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 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/tez/vectorization_7.q.out ql/src/test/results/clientpositive/tez/vectorization_7.q.out index 6c0b27f..1e7019b 100644 --- ql/src/test/results/clientpositive/tez/vectorization_7.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_7.q.out @@ -65,10 +65,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ctinyint <> 0) and ((ctimestamp1 <= 0) or ((ctinyint = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((ctimestamp2 > -15) and (3569.0 >= cdouble)))) (type: boolean) + predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > -15.0) and (3569.0 >= cdouble)))) (type: boolean) Statistics: Num rows: 7281 Data size: 223523 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), (csmallint % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), ((- ctinyint) + 17) (type: int), (cbigint * (- csmallint)) (type: bigint), (cint % csmallint) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + 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 Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE Limit @@ -237,10 +237,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ctinyint <> 0) and ((ctimestamp1 <= 0.0) or ((ctinyint = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((ctimestamp2 > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) + predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) Statistics: Num rows: 7281 Data size: 223523 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), (csmallint % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), ((- ctinyint) + 17) (type: int), (cbigint * (- csmallint)) (type: bigint), (cint % csmallint) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + 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 Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/tez/vectorization_8.q.out ql/src/test/results/clientpositive/tez/vectorization_8.q.out index 0238f25..3bd5183 100644 --- ql/src/test/results/clientpositive/tez/vectorization_8.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_8.q.out @@ -61,10 +61,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 is not null and ((ctimestamp1 <= 10) and (ctimestamp2 <> 16))) or ((cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) + predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 10.0) and (UDFToDouble(ctimestamp2) <> 16.0))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) Statistics: Num rows: 9216 Data size: 282927 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) (type: double), (cint + cfloat) (type: float), ((- cdouble) + cbigint) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + (cint + cfloat)) (type: double) + 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 Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE Limit @@ -220,10 +220,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 is not null and ((ctimestamp1 <= 12.503) and (ctimestamp2 <> 11.998))) or ((cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) + predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 12.503) and (UDFToDouble(ctimestamp2) <> 11.998))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) Statistics: Num rows: 9216 Data size: 282927 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) (type: double), (cint + cfloat) (type: float), ((- cdouble) + cbigint) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + (cint + cfloat)) (type: double) + 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 Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/tez/vectorization_9.q.out ql/src/test/results/clientpositive/tez/vectorization_9.q.out index 0383de1..be6c6c9 100644 --- ql/src/test/results/clientpositive/tez/vectorization_9.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_9.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: cstring1, cdouble, ctimestamp1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) - keys: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) + aggregations: count(_col1), stddev_samp(_col1), min(_col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE @@ -83,7 +83,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 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 * _col3) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (_col3 / -1.389) (type: double), _col4 (type: double) + 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 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/tez/vectorization_div0.q.out ql/src/test/results/clientpositive/tez/vectorization_div0.q.out index 54b09d0..fdf82d4 100644 --- ql/src/test/results/clientpositive/tez/vectorization_div0.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_div0.q.out @@ -165,7 +165,7 @@ STAGE PLANS: predicate: ((cbigint > 0) and (cbigint < 100000000)) (type: boolean) Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cbigint - 988888) (type: bigint), (cdouble / (cbigint - 988888)) (type: double), (1.2 / (cbigint - 988888)) (type: double) + expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / UDFToDouble((cbigint - 988888))) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -337,10 +337,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble >= -500) and (cdouble < -199)) (type: boolean) + predicate: ((cdouble >= -500.0) and (cdouble < -199.0)) (type: boolean) Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cdouble + 200.0) (type: double), (cbigint / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) + 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 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git ql/src/test/results/clientpositive/tez/vectorization_part_project.q.out ql/src/test/results/clientpositive/tez/vectorization_part_project.q.out index d3e3923..40c4522 100644 --- ql/src/test/results/clientpositive/tez/vectorization_part_project.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_part_project.q.out @@ -67,7 +67,7 @@ STAGE PLANS: alias: alltypesorc_part Statistics: Num rows: 200 Data size: 41576 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cdouble + 2) (type: double) + expressions: (cdouble + 2.0) (type: double) outputColumnNames: _col0 Statistics: Num rows: 200 Data size: 41576 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out index e7b133f..9ca5971 100644 --- ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out @@ -18,17 +18,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - filterExpr: (cbigint < cdouble) (type: boolean) + filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cbigint < cdouble) (type: boolean) + predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: cbigint + outputColumnNames: _col0 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cbigint) + aggregations: avg(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out index aa477cd..c36b5b2 100644 --- ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out @@ -148,14 +148,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((762 = cbigint) or ((csmallint < cfloat) and ((ctimestamp2 > -5) and (cdouble <> cint)))) or (cstring1 = 'a')) or ((cbigint <= -1.389) and ((cstring2 <> 'a') and ((79.553 <> cint) and (cboolean2 <> cboolean1))))) (type: boolean) + predicate: ((762 = cbigint) or (((UDFToFloat(csmallint) < cfloat) and ((UDFToDouble(ctimestamp2) > -5.0) and (cdouble <> UDFToDouble(cint)))) or ((cstring1 = 'a') or ((UDFToDouble(cbigint) <= -1.389) and ((cstring2 <> 'a') and ((79.553 <> UDFToDouble(cint)) and (cboolean2 <> cboolean1))))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: cint, cdouble, csmallint, cfloat, ctinyint + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) + aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) 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 @@ -172,7 +172,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 68 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (_col0 + -3728) (type: double), (- (_col0 + -3728)) (type: double), (- (- (_col0 + -3728))) (type: double), ((- (- (_col0 + -3728))) * (_col0 + -3728)) (type: double), _col1 (type: double), (- _col0) (type: double), _col2 (type: double), (((- (- (_col0 + -3728))) * (_col0 + -3728)) * (- (- (_col0 + -3728)))) (type: double), _col3 (type: double), (- _col2) (type: double), (_col2 - (- (- (_col0 + -3728)))) (type: double), ((_col2 - (- (- (_col0 + -3728)))) * _col2) (type: double), _col4 (type: double), _col5 (type: double), (10.175 - _col4) (type: double), (- (10.175 - _col4)) (type: double), ((- _col2) / -563) (type: double), _col6 (type: double), (- ((- _col2) / -563)) (type: double), (_col0 / _col1) (type: double), _col7 (type: tinyint), _col8 (type: bigint), (_col7 / ((- _col2) / -563)) (type: double), (- (_col0 / _col1)) (type: double) + 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 File Output Operator @@ -360,14 +360,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((cbigint <= 197) and (cint < cbigint)) or ((cdouble >= -26.28) and (csmallint > cdouble))) or ((ctinyint > cfloat) and (cstring1 rlike '.*ss.*'))) or ((cfloat > 79.553) and (cstring2 like '10%'))) (type: boolean) + predicate: (((cbigint <= 197) and (UDFToLong(cint) < cbigint)) or (((cdouble >= -26.28) and (UDFToDouble(csmallint) > cdouble)) or (((UDFToFloat(ctinyint) > cfloat) and (cstring1 rlike '.*ss.*')) or ((cfloat > 79.553) and (cstring2 like '10%'))))) (type: boolean) Statistics: Num rows: 6826 Data size: 209555 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: cint, cbigint, csmallint, cdouble, ctinyint + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) + aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) 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 @@ -384,7 +384,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), (_col0 / -3728) (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), ((_col0 * -3728) % (_col2 - 10.175)) (type: double), (- _col3) (type: double), _col6 (type: double), (_col3 % -26.28) (type: double), _col7 (type: double), (- (_col0 / -3728)) (type: double), ((- (_col0 * -3728)) % (-563 % (_col0 * -3728))) (type: int), ((_col0 / -3728) - _col4) (type: double), (- (_col0 * -3728)) (type: int), _col8 (type: double) + 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 File Output Operator @@ -563,14 +563,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((ctimestamp1 = ctimestamp2) or (762.0 = cfloat)) or (cstring1 = 'ss')) or ((csmallint <= cbigint) and (1 = cboolean2))) or (cboolean1 is not null and (ctimestamp2 is not null and (cstring2 > 'a')))) (type: boolean) + predicate: ((ctimestamp1 = ctimestamp2) or ((762.0 = cfloat) or ((cstring1 = 'ss') or (((UDFToLong(csmallint) <= cbigint) and (1 = cboolean2)) or (cboolean1 is not null and (ctimestamp2 is not null and (cstring2 > 'a'))))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: cbigint, ctinyint, csmallint, cint, cdouble + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) + aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -587,7 +587,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (- _col0) (type: double), (_col0 - (- _col0)) (type: double), _col1 (type: bigint), (_col1 % 79.553) (type: double), _col2 (type: tinyint), (_col1 - (- _col0)) (type: double), (- (- _col0)) (type: double), (-1 % (- _col0)) (type: double), _col1 (type: bigint), (- _col1) (type: bigint), _col3 (type: double), (- (- (- _col0))) (type: double), (762 * (- _col1)) (type: bigint), _col4 (type: int), (_col2 + (762 * (- _col1))) (type: bigint), ((- _col0) + _col4) (type: double), _col5 (type: double), ((- _col1) % _col1) (type: bigint), _col6 (type: bigint), _col7 (type: double), (-3728 % (_col2 + (762 * (- _col1)))) (type: bigint) + 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 File Output Operator @@ -745,14 +745,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((ctimestamp2 <= ctimestamp1) and ((cbigint <> cdouble) and ('ss' <= cstring1))) or ((csmallint < ctinyint) and (ctimestamp1 >= 0))) or (cfloat = 17.0)) (type: boolean) + predicate: (((ctimestamp2 <= ctimestamp1) and ((UDFToDouble(cbigint) <> cdouble) and ('ss' <= cstring1))) or (((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0)) or (cfloat = 17.0))) (type: boolean) Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) - outputColumnNames: ctinyint, cbigint, cint, cfloat + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) + aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -769,7 +769,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (_col0 + 6981) (type: double), ((_col0 + 6981) + _col0) (type: double), _col1 (type: bigint), (((_col0 + 6981) + _col0) / _col0) (type: double), (- (_col0 + 6981)) (type: double), _col2 (type: double), (_col0 % (- (_col0 + 6981))) (type: double), _col3 (type: double), _col4 (type: double), (- _col1) (type: bigint), ((- _col1) / _col2) (type: double), _col5 (type: float), (_col4 * -26.28) (type: double) + 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 File Output Operator @@ -931,10 +931,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((cstring1 rlike 'a.*') and (cstring2 like '%ss%')) or ((1 <> cboolean2) and ((csmallint < 79.553) and (-257 <> ctinyint)))) or ((cdouble > ctinyint) and (cfloat >= cint))) or ((cint < cbigint) and (ctinyint > cbigint))) (type: boolean) + predicate: (((cstring1 rlike 'a.*') and (cstring2 like '%ss%')) or (((1 <> cboolean2) and ((UDFToDouble(csmallint) < 79.553) and (-257 <> UDFToInteger(ctinyint)))) or (((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or ((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint))))) (type: boolean) Statistics: Num rows: 9898 Data size: 303864 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 - cint) (type: double), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (cint / cint) (type: double), ((-863.257 - cint) - -26.28) (type: double), (- cfloat) (type: float), (cdouble * -89010) (type: double), (ctinyint / 988888) (type: double), (- ctinyint) (type: tinyint), (79.553 / ctinyint) (type: double) + 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 Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE Limit @@ -1172,10 +1172,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((197.0 > ctinyint) and (cint = cbigint)) or (cbigint = 359)) or (cboolean1 < 0)) or ((cstring1 like '%ss') and (cfloat <= ctinyint))) (type: boolean) + predicate: (((197.0 > UDFToDouble(ctinyint)) and (UDFToLong(cint) = cbigint)) or ((cbigint = 359) or ((cboolean1 < 0) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint)))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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), (cint / cbigint) (type: double), (cbigint % 79.553) (type: double), (- (cint / cbigint)) (type: double), (10.175 % cfloat) (type: double), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432) (type: float), (cdouble * csmallint) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (cfloat - (cint / cbigint)) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359 - cdouble) (type: double), (- csmallint) (type: smallint) + 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 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Limit @@ -1366,10 +1366,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((csmallint > -26.28) and (cstring2 like 'ss')) or ((cdouble <= cbigint) and ((cstring1 >= 'ss') and (cint <> cdouble)))) or (ctinyint = -89010)) or ((cbigint <= cfloat) and (-26.28 <= csmallint))) (type: boolean) + predicate: (((UDFToDouble(csmallint) > -26.28) and (cstring2 like 'ss')) or (((cdouble <= UDFToDouble(cbigint)) and ((cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble))) or ((UDFToInteger(ctinyint) = -89010) or ((UDFToFloat(cbigint) <= cfloat) and (-26.28 <= UDFToDouble(csmallint)))))) (type: boolean) Statistics: Num rows: 10922 Data size: 335301 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 + csmallint) (type: int), (cbigint - ctinyint) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - ctinyint) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), ((cint + csmallint) * (- cbigint)) (type: bigint), ((- cdouble) + cbigint) (type: double), (-1.389 / ctinyint) (type: double), (cbigint % cdouble) (type: double), (- csmallint) (type: smallint), (csmallint + (cint + csmallint)) (type: int) + 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 Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -1632,10 +1632,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((-1.389 >= cint) and ((csmallint < ctinyint) and (-6432 > csmallint))) or ((cdouble >= cfloat) and (cstring2 <= 'a'))) or ((cstring1 like 'ss%') and (10.175 > cbigint))) (type: boolean) + predicate: (((-1.389 >= UDFToDouble(cint)) and ((csmallint < UDFToShort(ctinyint)) and (-6432 > UDFToInteger(csmallint)))) or (((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (10.175 > UDFToDouble(cbigint))))) (type: boolean) Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), (cdouble * 10.175) (type: double), ((-6432 * cfloat) / cfloat) (type: double), (- cfloat) (type: float), (cint % csmallint) (type: int), (cdouble * (- cdouble)) (type: double), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (cbigint / 3569) (type: double), (-257 - csmallint) (type: int), (-6432 * cfloat) (type: float), (- cdouble) (type: double) + expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (cdouble * (- cdouble)) (type: double), 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) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col15, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -1840,15 +1840,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint >= -257) and ((-6432 = csmallint) or ((cint >= cdouble) and (ctinyint <= cint)))) (type: boolean) + predicate: ((UDFToInteger(csmallint) >= -257) and ((-6432 = UDFToInteger(csmallint)) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint)))) (type: boolean) Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) - outputColumnNames: csmallint, cbigint, ctinyint + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() - keys: csmallint (type: smallint) + aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() + keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE @@ -1868,7 +1868,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: smallint), (_col0 % -75) (type: int), _col1 (type: double), (-1.389 / _col0) (type: double), _col2 (type: bigint), ((_col0 % -75) / _col2) (type: double), (- (_col0 % -75)) (type: int), _col3 (type: double), (- (- (_col0 % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) + 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 Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -2048,15 +2048,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble > 2563.58) and (((cbigint >= cint) and ((csmallint < cint) and (cfloat < -5638.15))) or ((cdouble <= cbigint) and (-5638.15 > cbigint)))) (type: boolean) + predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and ((UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15))) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) - outputColumnNames: cdouble, cfloat + outputColumnNames: _col0, _col1 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) - keys: cdouble (type: double) + aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) + keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE @@ -2076,7 +2076,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762)) (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) + 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 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -2300,15 +2300,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((ctimestamp1 <> 0) and (((((((-257 <> ctinyint) and cboolean2 is not null) and ((cstring1 rlike '.*ss') and (-3 < ctimestamp1))) or (ctimestamp2 = -5)) or ((ctimestamp1 < 0) and (cstring2 like '%b%'))) or (cdouble = cint)) or (cboolean1 is null and (cfloat < cint)))) (type: boolean) + predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and (cboolean2 is not null and ((cstring1 rlike '.*ss') and (-3.0 < UDFToDouble(ctimestamp1))))) or ((UDFToDouble(ctimestamp2) = -5.0) or (((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or ((cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint)))))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: ctimestamp1, cstring1, cint, csmallint, ctinyint, cfloat, cdouble + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) - keys: ctimestamp1 (type: timestamp), cstring1 (type: string) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -2328,7 +2328,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 6144 Data size: 188618 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)) * (- _col4)) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) (type: double), (- (- _col2)) (type: double), ((- _col4) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) - (((-26.28 - _col2) * (- _col2)) * (- _col4))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) - (((-26.28 - _col2) * (- _col2)) * (- _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 / (- _col5)) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) % -26.28) (type: double) + 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 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Limit @@ -2619,15 +2619,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cboolean1 is not null and (((((cdouble < csmallint) and ((cboolean2 = cboolean1) and (cbigint <= -863.257))) or ((cint >= -257) and (cstring1 is not null and (cboolean1 >= 1)))) or (cstring2 rlike 'b')) or ((csmallint >= ctinyint) and ctimestamp2 is null))) (type: boolean) + predicate: (cboolean1 is not null and (((cdouble < UDFToDouble(csmallint)) and ((cboolean2 = cboolean1) and (UDFToDouble(cbigint) <= -863.257))) or (((cint >= -257) and (cstring1 is not null and (cboolean1 >= 1))) or ((cstring2 rlike 'b') or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null))))) (type: boolean) Statistics: Num rows: 4778 Data size: 146682 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: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) - keys: cboolean1 (type: boolean) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE @@ -2647,7 +2647,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: float), ((_col2 - 10.175) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + (- _col1))) (type: double), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * _col5) (type: double), (- _col1) (type: float), (_col7 - (-1.389 * _col5)) (type: double), _col9 (type: double), (- (_col7 - (-1.389 * _col5))) (type: double), _col10 (type: double), (- _col10) (type: double), (_col10 * _col7) (type: double), (-26.28 / _col1) (type: double), _col2 (type: bigint), (_col2 - 10.175) (type: double), _col3 (type: double), (_col3 % _col1) (type: double), (10.175 + (- _col1)) (type: double), _col4 (type: double) + 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 Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -2866,10 +2866,10 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: i + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(i) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3052,10 +3052,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: ctinyint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(ctinyint) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3123,10 +3123,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: cint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cint) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3194,10 +3194,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: cfloat + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cfloat) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3265,10 +3265,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: cstring1 + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cstring1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3336,10 +3336,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean) - outputColumnNames: cboolean1 + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cboolean1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vectorized_case.q.out ql/src/test/results/clientpositive/tez/vectorized_case.q.out index 449bdb8..7f824f1 100644 --- ql/src/test/results/clientpositive/tez/vectorized_case.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_case.q.out @@ -45,7 +45,7 @@ STAGE PLANS: TableScan alias: alltypesorc Filter Operator - predicate: (((csmallint = 418) or (csmallint = 12205)) or (csmallint = 10583)) (type: boolean) + predicate: ((csmallint = 418) or ((csmallint = 12205) or (csmallint = 10583))) (type: boolean) 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 diff --git ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out index 5cf41f0..c4684e2 100644 --- ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out @@ -1885,49 +1885,23 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 4 - Map 4 - Map Operator Tree: - TableScan - alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -1936,8 +1910,54 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + 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 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: ds + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Target column: ds + Target Vertex: Map 5 + Reducer 3 + Reduce Operator Tree: Merge Join Operator condition map: Inner Join 0 to 1 @@ -1956,7 +1976,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1975,23 +1995,6 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized - Reducer 5 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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 - Execution mode: vectorized Stage: Stage-0 Fetch Operator @@ -2868,9 +2871,9 @@ STAGE PLANS: Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) - Reducer 4 <- Map 6 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE) + Reducer 4 <- Map 8 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 7 <- Map 6 (SIMPLE_EDGE), Union 3 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 @@ -2880,10 +2883,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2895,24 +2898,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map 7 - Map Operator Tree: - TableScan - alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2920,6 +2912,21 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) + Map 8 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator @@ -2953,7 +2960,7 @@ STAGE PLANS: Target Input: srcpart Partition key expr: ds Target column: ds - Target Vertex: Map 6 + Target Vertex: Map 8 Reducer 4 Reduce Operator Tree: Merge Join Operator @@ -2993,7 +3000,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized - Reducer 8 + Reducer 7 Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3026,7 +3033,7 @@ STAGE PLANS: Target Input: srcpart Partition key expr: ds Target column: ds - Target Vertex: Map 6 + Target Vertex: Map 8 Union 3 Vertex: Union 3 @@ -3078,10 +3085,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3095,11 +3102,15 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -3107,10 +3118,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3121,7 +3132,7 @@ STAGE PLANS: Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator @@ -3160,14 +3171,14 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} 1 - outputColumnNames: _col2 + outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col2 + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col2 (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE @@ -3198,7 +3209,7 @@ STAGE PLANS: Reducer 8 Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator @@ -3268,11 +3279,11 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 7 (CONTAINS) Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 7 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 7 (CONTAINS) - Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 7 (CONTAINS) + Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 3 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 @@ -3282,10 +3293,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3297,20 +3308,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -3319,10 +3332,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -3335,68 +3348,37 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 84 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Reducer 11 Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Filter Operator - predicate: _col0 is not null (type: boolean) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - 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 - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Target column: ds - Target Vertex: Map 5 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Target column: ds - Target Vertex: Map 8 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Group By Operator @@ -3442,7 +3424,7 @@ STAGE PLANS: Target Input: srcpart Partition key expr: ds Target column: ds - Target Vertex: Map 8 + Target Vertex: Map 10 Reducer 4 Reduce Operator Tree: Merge Join Operator @@ -3473,25 +3455,60 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - 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 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Execution mode: vectorized Reducer 9 Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Execution mode: vectorized + Filter Operator + predicate: _col0 is not null (type: boolean) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + 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 + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: ds + Target column: ds + Target Vertex: Map 5 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: ds + Target column: ds + Target Vertex: Map 10 Union 3 Vertex: Union 3 Union 7 @@ -4366,7 +4383,7 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 1 <- Reducer 4 (BROADCAST_EDGE) + Map 3 <- Reducer 2 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -4375,43 +4392,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - keys: - 0 ds (type: string) - 1 _col0 (type: string) - input vertices: - 1 Reducer 4 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Map 3 - Map Operator Tree: - TableScan - alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ds (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -4420,28 +4408,42 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Map 3 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Reducer 2 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + 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 + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 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 - 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 - 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 - Execution mode: vectorized - Reducer 4 - Reduce Operator Tree: - Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 @@ -4469,7 +4471,26 @@ STAGE PLANS: Partition key expr: ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Target column: ds - Target Vertex: Map 1 + Target Vertex: Map 3 + Reducer 4 + 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 + 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 + 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 + Execution mode: vectorized Stage: Stage-0 Fetch Operator @@ -5062,10 +5083,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ds) + aggregations: max(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -5079,33 +5100,37 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - condition expressions: - 0 {ds} - 1 - keys: - 0 ds (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - input vertices: - 1 Union 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col2 + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Union 3 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col2 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 2200 Data size: 23372 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: 2200 Data size: 23372 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: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan @@ -5113,10 +5138,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: ds + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ds) + aggregations: min(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -5127,7 +5152,7 @@ STAGE PLANS: Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator @@ -5180,7 +5205,7 @@ STAGE PLANS: Reducer 7 Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Filter Operator diff --git ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out index 5aa9599..3d68c62 100644 --- ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out @@ -21,16 +21,20 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: t2 + alias: t1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: cint (type: int) - sort order: + - Map-reduce partition columns: cint (type: int) + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 Statistics: Num rows: 6144 Data size: 188618 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 2 Map Operator Tree: @@ -40,32 +44,36 @@ STAGE PLANS: Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {cint} - 1 {cint} - keys: - 0 cint (type: int) - 1 cint (type: int) - outputColumnNames: _col2, _col17 - input vertices: - 1 Map 1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: int), _col17 (type: int) - outputColumnNames: _col2, _col17 + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 1 Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col2), max(_col17), min(_col2), avg((_col2 + _col17)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), _col3 (type: struct) + 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: int), _col2 (type: int), _col3 (type: struct) Execution mode: vectorized Reducer 3 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out index 83c4bb8..3f73eaa 100644 --- ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out @@ -10,47 +10,29 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 1 <- Map 4 (BROADCAST_EDGE) - Map 4 <- Map 3 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE) + Map 3 <- Map 1 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE) + Reducer 4 <- Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: v3 + alias: v1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: csmallint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col1} - 1 - keys: - 0 _col0 (type: smallint) - 1 csmallint (type: smallint) - outputColumnNames: _col1 - input vertices: - 0 Map 4 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 6758 Data size: 207479 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: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) + Select Operator + expressions: csmallint (type: smallint) + outputColumnNames: _col0 + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: smallint) + sort order: + + Map-reduce partition columns: _col0 (type: smallint) + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 3 + Map 2 Map Operator Tree: TableScan alias: v1 @@ -58,49 +40,74 @@ STAGE PLANS: Filter Operator predicate: (ctinyint is not null and csmallint is not null) (type: boolean) Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ctinyint (type: tinyint) - sort order: + - Map-reduce partition columns: ctinyint (type: tinyint) + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE - value expressions: csmallint (type: smallint), cdouble (type: double) + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: smallint), _col2 (type: double) Execution mode: vectorized - Map 4 + Map 3 Map Operator Tree: TableScan - alias: v2 + alias: v1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {ctinyint} {csmallint} {cdouble} - 1 {ctinyint} - keys: - 0 ctinyint (type: tinyint) - 1 ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col5, _col15 - input vertices: - 0 Map 3 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = _col15) (type: boolean) - Statistics: Num rows: 3379 Data size: 103739 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col1} {_col2} + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + outputColumnNames: _col1, _col2 + input vertices: + 0 Map 2 + Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: smallint), _col5 (type: double) + expressions: _col1 (type: smallint), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3379 Data size: 103739 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint) - sort order: + - Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 3379 Data size: 103739 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col1} + 1 + keys: + 0 _col0 (type: smallint) + 1 _col0 (type: smallint) + outputColumnNames: _col1 + input vertices: + 1 Map 1 + Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 7433 Data size: 228226 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: double) Execution mode: vectorized - Reducer 2 + Reducer 4 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) @@ -134,4 +141,4 @@ 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 #### -6.06519093248863E11 +6.065190932486892E11 diff --git ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out index 0607cea..979a572 100644 --- ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_parquet.q.out @@ -135,11 +135,11 @@ 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: ctinyint, cint, csmallint, cstring1, cfloat, cdouble + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(cint), min(csmallint), count(cstring1), avg(cfloat), stddev_pop(cdouble) - keys: ctinyint (type: tinyint) + aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5) + keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out index d65e6c0..2726083 100644 --- ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out @@ -21,16 +21,20 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: t2 + alias: t1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: cint (type: int) - sort order: + - Map-reduce partition columns: cint (type: int) + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 Statistics: Num rows: 6144 Data size: 188618 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 4 Map Operator Tree: @@ -40,11 +44,15 @@ STAGE PLANS: Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: cint (type: int) - sort order: + - Map-reduce partition columns: cint (type: int) + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 Statistics: Num rows: 6144 Data size: 188618 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -54,14 +62,14 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col2, _col17 + outputColumnNames: _col0, _col1 Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: int), _col17 (type: int) - outputColumnNames: _col2, _col17 + expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col2), max(_col17), min(_col2), avg((_col2 + _col17)) + aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out index b5b74fb..4beabda 100644 --- ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_timestamp_funcs.q.out @@ -642,10 +642,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: ctimestamp1 + outputColumnNames: _col0 Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() + aggregations: min(_col0), max(_col0), count(_col0), count() mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE @@ -727,10 +727,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: ctimestamp1 + outputColumnNames: _col0 Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(ctimestamp1) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -817,10 +817,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: ctimestamp1 + outputColumnNames: _col0 Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(ctimestamp1), variance(ctimestamp1), var_pop(ctimestamp1), var_samp(ctimestamp1), std(ctimestamp1), stddev(ctimestamp1), stddev_pop(ctimestamp1), stddev_samp(ctimestamp1) + aggregations: avg(_col0), variance(_col0), var_pop(_col0), var_samp(_col0), std(_col0), stddev(_col0), stddev_pop(_col0), stddev_samp(_col0) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git ql/src/test/results/clientpositive/type_widening.q.out ql/src/test/results/clientpositive/type_widening.q.out index f93c81b..93d1bba 100644 --- ql/src/test/results/clientpositive/type_widening.q.out +++ ql/src/test/results/clientpositive/type_widening.q.out @@ -49,7 +49,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToLong(0) (type: bigint) + expressions: 9223372036854775807 (type: bigint) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Union @@ -66,7 +66,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 9223372036854775807 (type: bigint) + expressions: UDFToLong(0) (type: bigint) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Union diff --git ql/src/test/results/clientpositive/udaf_number_format.q.out ql/src/test/results/clientpositive/udaf_number_format.q.out index e73f8e7..b2b0bf8 100644 --- ql/src/test/results/clientpositive/udaf_number_format.q.out +++ ql/src/test/results/clientpositive/udaf_number_format.q.out @@ -24,9 +24,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 'a' (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum('a'), avg('a'), variance('a'), std('a') + aggregations: sum(_col0), avg(_col0), variance(_col0), std(_col0) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/udf8.q.out ql/src/test/results/clientpositive/udf8.q.out index 985933b..56a5773 100644 --- ql/src/test/results/clientpositive/udf8.q.out +++ 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: c1 + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(c1), sum(c1), count(c1) + aggregations: avg(_col0), sum(_col0), count(_col0) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/udf9.q.out ql/src/test/results/clientpositive/udf9.q.out index b03ccb6..5c12229 100644 --- ql/src/test/results/clientpositive/udf9.q.out +++ ql/src/test/results/clientpositive/udf9.q.out @@ -32,7 +32,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) 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) diff --git ql/src/test/results/clientpositive/udf_between.q.out ql/src/test/results/clientpositive/udf_between.q.out index cb63d1c..efe6615 100644 --- ql/src/test/results/clientpositive/udf_between.q.out +++ ql/src/test/results/clientpositive/udf_between.q.out @@ -24,7 +24,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key + 100) BETWEEN 100 AND 200 (type: boolean) + predicate: (UDFToDouble(key) + 100.0) BETWEEN 100 AND 200 (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -79,7 +79,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key + 100) NOT BETWEEN 100 AND 200 (type: boolean) + predicate: (UDFToDouble(key) + 100.0) NOT BETWEEN 100 AND 200 (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/udf_case_column_pruning.q.out ql/src/test/results/clientpositive/udf_case_column_pruning.q.out index bc32a5c..893b1d6 100644 --- ql/src/test/results/clientpositive/udf_case_column_pruning.q.out +++ ql/src/test/results/clientpositive/udf_case_column_pruning.q.out @@ -28,27 +28,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 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: diff --git ql/src/test/results/clientpositive/udf_count.q.out ql/src/test/results/clientpositive/udf_count.q.out index 78228ec..b7dcc17 100644 --- ql/src/test/results/clientpositive/udf_count.q.out +++ 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: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(key) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -90,11 +90,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key) - keys: key (type: string) + aggregations: count(DISTINCT _col0) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -152,11 +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: key, value + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT key, value) - keys: key (type: string), value (type: string) + aggregations: count(DISTINCT _col0, _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -272,9 +272,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/udf_hour.q.out ql/src/test/results/clientpositive/udf_hour.q.out index 689ed30..ab743d2 100644 --- ql/src/test/results/clientpositive/udf_hour.q.out +++ ql/src/test/results/clientpositive/udf_hour.q.out @@ -34,7 +34,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 13 (type: int), 13 (type: int), null (type: void) diff --git ql/src/test/results/clientpositive/udf_like.q.out ql/src/test/results/clientpositive/udf_like.q.out index b198680..8ffcf9b 100644 --- ql/src/test/results/clientpositive/udf_like.q.out +++ ql/src/test/results/clientpositive/udf_like.q.out @@ -35,7 +35,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) 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) diff --git ql/src/test/results/clientpositive/udf_lower.q.out ql/src/test/results/clientpositive/udf_lower.q.out index 94bb98d..0d662ac 100644 --- ql/src/test/results/clientpositive/udf_lower.q.out +++ ql/src/test/results/clientpositive/udf_lower.q.out @@ -30,7 +30,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'abc 123' (type: string), 'ABC 123' (type: string) diff --git ql/src/test/results/clientpositive/udf_minute.q.out ql/src/test/results/clientpositive/udf_minute.q.out index 0dd0b24..032cbee 100644 --- ql/src/test/results/clientpositive/udf_minute.q.out +++ ql/src/test/results/clientpositive/udf_minute.q.out @@ -34,7 +34,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 14 (type: int), 14 (type: int), null (type: void) diff --git ql/src/test/results/clientpositive/udf_parse_url.q.out ql/src/test/results/clientpositive/udf_parse_url.q.out index 22d3b15..f657fa9 100644 --- ql/src/test/results/clientpositive/udf_parse_url.q.out +++ ql/src/test/results/clientpositive/udf_parse_url.q.out @@ -57,7 +57,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) 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: void), '/path1/p.php?k1=v1&k2=v2' (type: string), 'http' (type: string), null (type: void), 'facebook.com' (type: string) diff --git ql/src/test/results/clientpositive/udf_second.q.out ql/src/test/results/clientpositive/udf_second.q.out index d80983a..6cdbffb 100644 --- ql/src/test/results/clientpositive/udf_second.q.out +++ ql/src/test/results/clientpositive/udf_second.q.out @@ -34,7 +34,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 86) (type: boolean) + predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 15 (type: int), 15 (type: int), null (type: void) diff --git ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out index 8292ca9..ce82461 100644 --- ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out +++ ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out @@ -102,18 +102,14 @@ STAGE PLANS: 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 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (unix_timestamp(_col0) > 10) (type: boolean) + 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 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - 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 - ListSink + ListSink PREHOOK: query: explain select * from (select * from src) a where to_unix_timestamp(a.key) > 10 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/udtf_explode.q.out ql/src/test/results/clientpositive/udtf_explode.q.out index 6213746..f8a11b7 100644 --- ql/src/test/results/clientpositive/udtf_explode.q.out +++ ql/src/test/results/clientpositive/udtf_explode.q.out @@ -321,7 +321,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -651,7 +651,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/union11.q.out ql/src/test/results/clientpositive/union11.q.out index b624c7d..b2cef5f 100644 --- ql/src/test/results/clientpositive/union11.q.out +++ ql/src/test/results/clientpositive/union11.q.out @@ -20,9 +20,10 @@ explain POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3, Stage-4 + Stage-2 depends on stages: Stage-1, Stage-4 Stage-3 is a root stage - Stage-4 is a root stage + Stage-4 depends on stages: Stage-3, Stage-5 + Stage-5 is a root stage Stage-0 depends on stages: Stage-2 STAGE PLANS: @@ -33,9 +34,11 @@ STAGE PLANS: alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -50,7 +53,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string) + expressions: 'tst3' (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -67,11 +70,11 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -86,30 +89,11 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 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) - TableScan - Union - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -143,12 +127,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s2 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -177,12 +163,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s3 + Union + Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 176 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 + TableScan + Union + Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 176 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-5 + Map Reduce + Map Operator Tree: + TableScan + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -197,7 +215,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst3' (type: string) + expressions: 'tst1' (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator diff --git ql/src/test/results/clientpositive/union13.q.out ql/src/test/results/clientpositive/union13.q.out index b0b80e9..97782c3 100644 --- ql/src/test/results/clientpositive/union13.q.out +++ ql/src/test/results/clientpositive/union13.q.out @@ -41,7 +41,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: s2 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/union14.q.out ql/src/test/results/clientpositive/union14.q.out index 02821d7..afbbcf8 100644 --- ql/src/test/results/clientpositive/union14.q.out +++ ql/src/test/results/clientpositive/union14.q.out @@ -29,9 +29,11 @@ STAGE PLANS: alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -69,11 +71,11 @@ STAGE PLANS: Union Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -88,11 +90,11 @@ STAGE PLANS: Union Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/union15.q.out ql/src/test/results/clientpositive/union15.q.out index 9cac42b..59829be 100644 --- ql/src/test/results/clientpositive/union15.q.out +++ ql/src/test/results/clientpositive/union15.q.out @@ -19,21 +19,24 @@ explain select s3.key as key, s3.value as value from src1 s3) unionsrc group by unionsrc.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 + Stage-5 is a root stage + Stage-4 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-4 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -58,29 +61,10 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - Union - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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: 25 Data size: 2400 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: 25 Data size: 2400 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 @@ -88,38 +72,49 @@ STAGE PLANS: 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: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - 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: 25 Data size: 2400 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: 25 Data size: 2400 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Statistics: Num rows: 26 Data size: 2288 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 + Union + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 26 Data size: 2288 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 + + Stage: Stage-2 + Map Reduce + Map Operator Tree: TableScan - alias: s3 + 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: 2479 Basic stats: COMPLETE Column stats: PARTIAL Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 51 Data size: 2479 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -130,6 +125,25 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 25 Data size: 2400 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) + TableScan + Union + Statistics: Num rows: 51 Data size: 2479 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 51 Data size: 2479 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 2400 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: 25 Data size: 2400 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/union2.q.out ql/src/test/results/clientpositive/union2.q.out index d79fb32..673450b 100644 --- ql/src/test/results/clientpositive/union2.q.out +++ ql/src/test/results/clientpositive/union2.q.out @@ -28,9 +28,11 @@ STAGE PLANS: Union Statistics: Num rows: 1000 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -39,16 +41,18 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan - alias: s2 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Union Statistics: Num rows: 1000 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/union20.q.out ql/src/test/results/clientpositive/union20.q.out index 1aa82e5..2fb3312 100644 --- ql/src/test/results/clientpositive/union20.q.out +++ ql/src/test/results/clientpositive/union20.q.out @@ -27,22 +27,24 @@ JOIN ON (unionsrc1.key = unionsrc2.key) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-6 + Stage-5 is a root stage + Stage-2 depends on stages: Stage-5, Stage-6 Stage-6 is a root stage Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: s3 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -71,19 +73,10 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - Union - Statistics: Num rows: 167 Data size: 2035 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: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) - TableScan - alias: s4 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 10) (type: boolean) + 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) @@ -91,17 +84,21 @@ STAGE PLANS: 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) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 167 Data size: 45424 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: 167 Data size: 45424 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: string) TableScan - alias: s2 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 10) (type: boolean) + 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) @@ -109,21 +106,42 @@ STAGE PLANS: 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) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 167 Data size: 45424 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: 167 Data size: 45424 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (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) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 167 Data size: 45424 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: 167 Data size: 45424 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: string) + TableScan + Union + Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 167 Data size: 45424 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: 167 Data size: 45424 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -152,9 +170,11 @@ STAGE PLANS: alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/union24.q.out ql/src/test/results/clientpositive/union24.q.out index 1decd24..8b24e0a 100644 --- ql/src/test/results/clientpositive/union24.q.out +++ ql/src/test/results/clientpositive/union24.q.out @@ -180,12 +180,12 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-2 depends on stages: Stage-3 + Stage-4 is a root stage + Stage-2 depends on stages: Stage-4 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -194,15 +194,15 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (key < 10) (type: boolean) + predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: key (type: string), 1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: key (type: string) + aggregations: count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE @@ -262,7 +262,7 @@ STAGE PLANS: name: default.src5 name: default.src5 Truncated Path -> Alias: - /src5 [null-subquery2:s-subquery2:src5] + /src5 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:src5] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -302,39 +302,96 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (key < 10) (type: boolean) + predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 360 Data size: 1726 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:bigint - 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 360 Data size: 1726 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:bigint + 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 + TableScan + alias: src3 + Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (UDFToDouble(key) < 10.0) (type: boolean) + Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), count (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 360 Data size: 1726 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:bigint + 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 TableScan GatherStats: false Union @@ -365,89 +422,62 @@ STAGE PLANS: GatherStats: false MultiFileSpray: false TableScan - alias: src3 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), count (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 360 Data size: 1726 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:bigint - 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 - TableScan alias: src2 Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (key < 10) (type: boolean) + predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 360 Data size: 1726 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:bigint - 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 + Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 360 Data size: 1726 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:bigint + 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -598,9 +628,9 @@ STAGE PLANS: name: default.src4 name: default.src4 Truncated Path -> Alias: - /src2 [null-subquery1-subquery1-subquery1:s-subquery1-subquery1-subquery1:src2] - /src3 [null-subquery1-subquery1-subquery2:s-subquery1-subquery1-subquery2:src3] - /src4 [null-subquery1-subquery2:s-subquery1-subquery2:src4] + /src2 [null-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1:src2] + /src3 [null-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1-subquery2:$hdt$_0-subquery2:src3] + /src4 [null-subquery1:$hdt$_0-subquery1-subquery2:$hdt$_0-subquery2:src4] #### A masked pattern was here #### Stage: Stage-0 @@ -1073,7 +1103,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -1557,7 +1587,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -1722,7 +1752,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: diff --git ql/src/test/results/clientpositive/union5.q.out ql/src/test/results/clientpositive/union5.q.out index 5d2a447..a5a3496 100644 --- ql/src/test/results/clientpositive/union5.q.out +++ ql/src/test/results/clientpositive/union5.q.out @@ -28,9 +28,11 @@ STAGE PLANS: alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -45,7 +47,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string) + expressions: 'tst2' (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -62,11 +64,11 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -81,11 +83,11 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -119,12 +121,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s2 + alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -139,7 +143,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst2' (type: string) + expressions: 'tst1' (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator diff --git ql/src/test/results/clientpositive/union7.q.out ql/src/test/results/clientpositive/union7.q.out index 46ed3db..48a7668 100644 --- ql/src/test/results/clientpositive/union7.q.out +++ ql/src/test/results/clientpositive/union7.q.out @@ -15,21 +15,23 @@ explain select s2.key as key, s2.value as value from src1 s2) unionsrc group by unionsrc.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -58,25 +60,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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: 13 Data size: 1248 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: 13 Data size: 1248 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 @@ -86,11 +69,11 @@ STAGE PLANS: Union Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - aggregations: count(1) + aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -101,6 +84,25 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) + TableScan + Union + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col0 (type: string), 1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 1248 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: 13 Data size: 1248 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/union8.q.out ql/src/test/results/clientpositive/union8.q.out index 8cb2a5e..6d76788 100644 --- ql/src/test/results/clientpositive/union8.q.out +++ ql/src/test/results/clientpositive/union8.q.out @@ -43,45 +43,57 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: s2 + alias: 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 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 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Union 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + 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: s3 + alias: 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 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 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Union 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 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + 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 ql/src/test/results/clientpositive/union_top_level.q.out ql/src/test/results/clientpositive/union_top_level.q.out index 2be60f0..4e9cae8 100644 --- ql/src/test/results/clientpositive/union_top_level.q.out +++ ql/src/test/results/clientpositive/union_top_level.q.out @@ -20,9 +20,10 @@ select key, 2 as value from src where key % 3 == 2 limit 3 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3, Stage-4 + Stage-2 depends on stages: Stage-1, Stage-4 Stage-3 is a root stage - Stage-4 is a root stage + Stage-4 depends on stages: Stage-3, Stage-5 + Stage-5 is a root stage Stage-0 depends on stages: Stage-2 STAGE PLANS: @@ -33,10 +34,10 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 0) (type: boolean) + 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), 0 (type: int) + expressions: key (type: string), 2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit @@ -54,12 +55,16 @@ STAGE PLANS: 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 + Select Operator + expressions: _col0 (type: string), _col1 (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 @@ -92,20 +97,6 @@ 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: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: _col0, _col1 - 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 @@ -114,7 +105,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 1) (type: boolean) + 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) @@ -135,24 +126,58 @@ STAGE PLANS: 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 + Select Operator + expressions: _col0 (type: string), _col1 (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: TableScan + Union + Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + 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: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: 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: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 2) (type: boolean) + 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), 2 (type: int) + expressions: key (type: string), 0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit @@ -170,12 +195,16 @@ STAGE PLANS: 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 + Select Operator + expressions: _col0 (type: string), _col1 (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-0 Fetch Operator @@ -221,9 +250,9 @@ 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-3 depends on stages: Stage-2, Stage-5 + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 Stage-0 depends on stages: Stage-3 STAGE PLANS: @@ -236,34 +265,42 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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) TableScan - alias: s2 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col6 + 0 {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col6 (type: string) + expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit @@ -292,12 +329,16 @@ STAGE PLANS: 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: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + 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 @@ -331,7 +372,7 @@ STAGE PLANS: 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 @@ -340,34 +381,42 @@ STAGE PLANS: Filter Operator 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: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + 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) TableScan - alias: s2 + alias: 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 - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + 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: Inner Join 0 to 1 condition expressions: - 0 {KEY.reducesinkkey0} - 1 {VALUE._col0} - outputColumnNames: _col0, _col6 + 0 {VALUE._col0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col6 (type: string) + expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit @@ -380,7 +429,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -396,12 +445,16 @@ STAGE PLANS: 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: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + 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 diff --git ql/src/test/results/clientpositive/union_view.q.out ql/src/test/results/clientpositive/union_view.q.out index ce987c3..e3b371e 100644 --- ql/src/test/results/clientpositive/union_view.q.out +++ ql/src/test/results/clientpositive/union_view.q.out @@ -44,181 +44,67 @@ POSTHOOK: type: CREATEINDEX POSTHOOK: Input: default@src_union_3 POSTHOOK: Output: default@default__src_union_3_src_union_3_key_idx__ STAGE DEPENDENCIES: - 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-0 is a root stage STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: default.default__src_union_1_src_union_1_key_idx__ - filterExpr: ((key = 86) and (ds = '1')) (type: boolean) - Filter Operator - predicate: (key = 86) (type: boolean) - Select Operator - expressions: _bucketname (type: string), _offsets (type: array) - 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-2 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: 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 - predicate: (key = 86) (type: boolean) - 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 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - 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 limit: -1 Processor Tree: - ListSink + TableScan + alias: 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 + predicate: (key = 86) (type: boolean) + 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 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + ListSink STAGE DEPENDENCIES: - 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-0 is a root stage STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: default.default__src_union_2_src_union_2_key_idx__ - filterExpr: ((key = 86) and (ds = '2')) (type: boolean) - Filter Operator - predicate: (key = 86) (type: boolean) - Select Operator - expressions: _bucketname (type: string), _offsets (type: array) - 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-2 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: 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 - predicate: (key = 86) (type: boolean) - 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 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - 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 limit: -1 Processor Tree: - ListSink + TableScan + alias: 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 + predicate: (key = 86) (type: boolean) + 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 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink STAGE DEPENDENCIES: - 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-0 is a root stage STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: default.default__src_union_3_src_union_3_key_idx__ - filterExpr: ((key = 86) and (ds = '3')) (type: boolean) - Filter Operator - predicate: (key = 86) (type: boolean) - Select Operator - expressions: _bucketname (type: string), _offsets (type: array) - 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-2 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: 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 - predicate: (key = 86) (type: boolean) - 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 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - 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 limit: -1 Processor Tree: - ListSink + TableScan + alias: 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 + predicate: (key = 86) (type: boolean) + 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 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink 86 val_86 1 86 val_86 2 @@ -262,9 +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: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -333,9 +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: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -404,9 +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: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -489,16 +381,22 @@ STAGE PLANS: Union Statistics: Num rows: 250 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: _col1 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Union 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 + Select Operator + expressions: 86 (type: int), _col1 (type: string), '1' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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 @@ -554,16 +452,22 @@ STAGE PLANS: Union Statistics: Num rows: 500 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: _col1 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Union 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 + Select Operator + expressions: 86 (type: int), _col1 (type: string), '2' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 @@ -651,7 +555,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default.default__src_union_2_src_union_2_key_idx__ + alias: default.default__src_union_1_src_union_1_key_idx__ filterExpr: (key = 86) (type: boolean) Filter Operator predicate: (key = 86) (type: boolean) @@ -675,38 +579,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_2 + alias: src_union_1 filterExpr: ((key = 86) and ds is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 + Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + + Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan - alias: src_union_1 + alias: src_union_3 filterExpr: ((key = 86) and ds is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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 @@ -719,7 +629,7 @@ STAGE PLANS: Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan - alias: src_union_3 + alias: 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 @@ -730,16 +640,22 @@ STAGE PLANS: outputColumnNames: _col1, _col2 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 + Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + + Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator expressions: 86 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) @@ -757,7 +673,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default.default__src_union_1_src_union_1_key_idx__ + alias: default.default__src_union_3_src_union_3_key_idx__ filterExpr: (key = 86) (type: boolean) Filter Operator predicate: (key = 86) (type: boolean) @@ -781,7 +697,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default.default__src_union_3_src_union_3_key_idx__ + alias: default.default__src_union_2_src_union_2_key_idx__ filterExpr: (key = 86) (type: boolean) Filter Operator predicate: (key = 86) (type: boolean) @@ -859,15 +775,21 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 500 Data size: 5312 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) + Union + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_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) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -934,15 +856,21 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1000 Data size: 10624 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) + Union + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_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) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1008,9 +936,11 @@ STAGE PLANS: Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1152,9 +1082,11 @@ STAGE PLANS: Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_cast_constant.q.out ql/src/test/results/clientpositive/vector_cast_constant.q.out index 6ea3b54..a701d59 100644 --- ql/src/test/results/clientpositive/vector_cast_constant.q.out +++ ql/src/test/results/clientpositive/vector_cast_constant.q.out @@ -123,12 +123,12 @@ STAGE PLANS: alias: over1korc Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: i (type: int) - outputColumnNames: i + expressions: i (type: int), 50 (type: int), 50.0 (type: double), CAST( 50 AS decimal(10,0)) (type: decimal(10,0)) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(50), avg(UDFToDouble(50)), avg(CAST( 50 AS decimal(10,0))) - keys: i (type: int) + aggregations: avg(_col1), avg(_col2), avg(_col3) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE @@ -137,7 +137,7 @@ 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 diff --git ql/src/test/results/clientpositive/vector_char_2.q.out ql/src/test/results/clientpositive/vector_char_2.q.out index 7d1512c..fcf1838 100644 --- ql/src/test/results/clientpositive/vector_char_2.q.out +++ ql/src/test/results/clientpositive/vector_char_2.q.out @@ -72,12 +72,12 @@ STAGE PLANS: alias: char_2 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: char(20)), key (type: char(10)) - outputColumnNames: value, key + expressions: value (type: char(20)), UDFToInteger(key) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(UDFToInteger(key)), count() - keys: value (type: char(20)) + aggregations: sum(_col1), count() + keys: _col0 (type: char(20)) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE @@ -206,12 +206,12 @@ STAGE PLANS: alias: char_2 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: char(20)), key (type: char(10)) - outputColumnNames: value, key + expressions: value (type: char(20)), UDFToInteger(key) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(UDFToInteger(key)), count() - keys: value (type: char(20)) + aggregations: sum(_col1), count() + keys: _col0 (type: char(20)) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_coalesce.q.out ql/src/test/results/clientpositive/vector_coalesce.q.out index 8ad63e3..746a1dd 100644 --- ql/src/test/results/clientpositive/vector_coalesce.q.out +++ ql/src/test/results/clientpositive/vector_coalesce.q.out @@ -87,7 +87,7 @@ STAGE PLANS: predicate: ctinyint is null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctinyint (type: tinyint), cdouble (type: double), cint (type: int), COALESCE((ctinyint + 10),(cdouble + log2(cint)),0) (type: double) + expressions: ctinyint (type: tinyint), cdouble (type: double), cint (type: int), COALESCE((UDFToInteger(ctinyint) + 10),(cdouble + log2(cint)),0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/vector_count_distinct.q.out ql/src/test/results/clientpositive/vector_count_distinct.q.out index becb4e2..0c23d24 100644 --- ql/src/test/results/clientpositive/vector_count_distinct.q.out +++ 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: ws_order_number + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT ws_order_number) - keys: ws_order_number (type: int) + aggregations: count(DISTINCT _col0) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out index c26fc9d..075dce2 100644 --- ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out +++ ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out @@ -45,11 +45,11 @@ 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: cint, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() - keys: cint (type: int) + aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() + keys: _col0 (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 @@ -143,11 +143,11 @@ 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: cint, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), avg(cdecimal1), stddev_pop(cdecimal1), stddev_samp(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), avg(cdecimal2), stddev_pop(cdecimal2), stddev_samp(cdecimal2), count() - keys: cint (type: int) + 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) 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 diff --git ql/src/test/results/clientpositive/vector_decimal_expressions.q.out ql/src/test/results/clientpositive/vector_decimal_expressions.q.out index ca94561..408a470 100644 --- ql/src/test/results/clientpositive/vector_decimal_expressions.q.out +++ ql/src/test/results/clientpositive/vector_decimal_expressions.q.out @@ -24,10 +24,10 @@ STAGE PLANS: alias: decimal_test Statistics: Num rows: 12288 Data size: 2128368 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((cdecimal1 > 0) and (cdecimal1 < 12345.5678)) and (cdecimal2 <> 0)) and (cdecimal2 > 1000)) and cdouble is not null) (type: boolean) + predicate: (((((cdecimal1 > CAST( 0 AS decimal(20,10))) and (cdecimal1 < CAST( 12345.5678 AS decimal(25,15)))) and (cdecimal2 <> CAST( 0 AS decimal(24,14)))) and (cdecimal2 > CAST( 1000 AS decimal(24,14)))) and cdouble is not null) (type: boolean) 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)), ((cdecimal1 + 2.34) / cdecimal2) (type: double), (cdecimal1 * (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) + expressions: (cdecimal1 + cdecimal2) (type: decimal(25,14)), (cdecimal1 - (CAST( 2 AS decimal(10,0)) * cdecimal2)) (type: decimal(26,14)), ((UDFToDouble(cdecimal1) + 2.34) / UDFToDouble(cdecimal2)) (type: double), (UDFToDouble(cdecimal1) * (UDFToDouble(cdecimal2) / 3.4)) (type: double), (cdecimal1 % CAST( 10 AS decimal(10,0))) (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 Statistics: Num rows: 228 Data size: 39491 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out index 2cfa45a..74d964d 100644 --- ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out +++ ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out @@ -101,7 +101,7 @@ STAGE PLANS: predicate: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0)) (type: boolean) 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((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(38,18)), 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) + 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(38,18)), 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 Statistics: Num rows: 2048 Data size: 366958 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/vector_distinct_2.q.out ql/src/test/results/clientpositive/vector_distinct_2.q.out index 0019f95..bd399be 100644 --- ql/src/test/results/clientpositive/vector_distinct_2.q.out +++ ql/src/test/results/clientpositive/vector_distinct_2.q.out @@ -120,10 +120,10 @@ 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: s, t + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: s (type: string), t (type: tinyint) + keys: _col0 (type: string), _col1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_elt.q.out ql/src/test/results/clientpositive/vector_elt.q.out index d3cc179..5e350e5 100644 --- ql/src/test/results/clientpositive/vector_elt.q.out +++ ql/src/test/results/clientpositive/vector_elt.q.out @@ -21,7 +21,7 @@ STAGE PLANS: predicate: (ctinyint > 0) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ((ctinyint % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((ctinyint % 2) + 1), cstring1, cint) (type: string) + 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 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/vector_groupby_3.q.out ql/src/test/results/clientpositive/vector_groupby_3.q.out index aff5082..869123d 100644 --- ql/src/test/results/clientpositive/vector_groupby_3.q.out +++ ql/src/test/results/clientpositive/vector_groupby_3.q.out @@ -120,11 +120,11 @@ 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: s, t, b + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(b) - keys: s (type: string), t (type: tinyint) + aggregations: max(_col2) + keys: _col0 (type: string), _col1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_groupby_reduce.q.out ql/src/test/results/clientpositive/vector_groupby_reduce.q.out index 438d6b6..4051509 100644 --- ql/src/test/results/clientpositive/vector_groupby_reduce.q.out +++ 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: ss_ticket_number + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ss_ticket_number (type: int) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -355,10 +355,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: ss_ticket_number + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ss_ticket_number (type: int) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_left_outer_join.q.out ql/src/test/results/clientpositive/vector_left_outer_join.q.out index d1c5855..ca240f9 100644 --- ql/src/test/results/clientpositive/vector_left_outer_join.q.out +++ ql/src/test/results/clientpositive/vector_left_outer_join.q.out @@ -25,35 +25,43 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - t1:cd + $hdt$_0:$hdt$_0:$hdt$_1:c Fetch Operator limit: -1 - t1:hd + $hdt$_0:$hdt$_0:$hdt$_2:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - t1:cd + $hdt$_0:$hdt$_0:$hdt$_1:c TableScan - alias: cd + alias: c Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 {ctinyint} - 1 - keys: - 0 cint (type: int) - 1 cint (type: int) - t1:hd + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col0} + 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + $hdt$_0:$hdt$_0:$hdt$_2:c TableScan - alias: hd + alias: c Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 - 1 - keys: - 0 _col0 (type: tinyint) - 1 ctinyint (type: tinyint) + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) Stage: Stage-2 Map Reduce @@ -61,38 +69,42 @@ STAGE PLANS: TableScan alias: c Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join0 to 1 - condition expressions: - 0 {ctinyint} - 1 - keys: - 0 cint (type: int) - 1 cint (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 13516 Data size: 414960 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ctinyint (type: tinyint), cint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 condition expressions: - 0 + 0 {_col0} 1 keys: - 0 _col0 (type: tinyint) - 1 ctinyint (type: tinyint) - Statistics: Num rows: 14867 Data size: 456456 Basic stats: COMPLETE Column stats: NONE - Select Operator + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 13516 Data size: 414960 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) Statistics: Num rows: 14867 Data size: 456456 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: 456456 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 diff --git ql/src/test/results/clientpositive/vector_orderby_5.q.out ql/src/test/results/clientpositive/vector_orderby_5.q.out index aa43500..6be9d9b 100644 --- ql/src/test/results/clientpositive/vector_orderby_5.q.out +++ 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: bo, b + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(b) - keys: bo (type: boolean) + aggregations: max(_col1) + keys: _col0 (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out index f3eff07..5eecf63 100644 --- ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out +++ ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out @@ -370,11 +370,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: fl_date + outputColumnNames: _col0 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: fl_date (type: date) + keys: _col0 (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE @@ -1151,11 +1151,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: fl_date + outputColumnNames: _col0 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: fl_date (type: date) + keys: _col0 (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE @@ -1956,11 +1956,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_time (type: timestamp) - outputColumnNames: fl_time + outputColumnNames: _col0 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: fl_time (type: timestamp) + keys: _col0 (type: timestamp) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out index 2343508..93c3ae4 100644 --- ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out +++ 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: cint, cdouble, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(cdecimal1) - keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) + aggregations: min(_col2) + keys: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (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 diff --git ql/src/test/results/clientpositive/vectorization_0.q.out ql/src/test/results/clientpositive/vectorization_0.q.out index d50899e..d328b36 100644 --- ql/src/test/results/clientpositive/vectorization_0.q.out +++ ql/src/test/results/clientpositive/vectorization_0.q.out @@ -130,10 +130,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: ctinyint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(ctinyint) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -455,10 +455,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: cbigint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(cbigint) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -780,10 +780,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: cfloat + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(cfloat) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1042,14 +1042,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 like '%b%') or ((79.553 <> cint) or (cbigint < cdouble))) (type: boolean) + predicate: ((cstring2 like '%b%') or ((79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: cbigint, cfloat, ctinyint + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) + aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -1065,7 +1065,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (- _col0) (type: double), (-6432 + _col0) (type: double), _col1 (type: double), (- (-6432 + _col0)) (type: double), ((- (-6432 + _col0)) + (-6432 + _col0)) (type: double), _col2 (type: double), (- (-6432 + _col0)) (type: double), (-6432 + (- (-6432 + _col0))) (type: double), (- (-6432 + _col0)) (type: double), ((- (-6432 + _col0)) / (- (-6432 + _col0))) (type: double), _col3 (type: bigint), _col4 (type: double), (_col2 % _col1) (type: double), (- _col2) (type: double), ((- (-6432 + _col0)) * (- _col0)) (type: double), _col5 (type: tinyint), (- _col5) (type: tinyint) + 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 File Output Operator diff --git ql/src/test/results/clientpositive/vectorization_13.q.out ql/src/test/results/clientpositive/vectorization_13.q.out index 1cefe30..d03f1e5 100644 --- ql/src/test/results/clientpositive/vectorization_13.q.out +++ ql/src/test/results/clientpositive/vectorization_13.q.out @@ -74,15 +74,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > 11) and ((ctimestamp2 <> 12) and (ctinyint < 9763215.5639)))) (type: boolean) + predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > 11.0) and ((UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 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: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) - keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE @@ -101,7 +101,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 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 * ((- _col1) + _col5)) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col10 (type: tinyint) + 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 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Limit @@ -305,15 +305,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > -1.388) and ((ctimestamp2 <> -1.3359999999999999) and (ctinyint < 9763215.5639)))) (type: boolean) + predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > -1.388) and ((UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 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: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) - keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE @@ -332,7 +332,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 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 * ((- _col1) + _col5)) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col10 (type: tinyint) + 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 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/vectorization_14.q.out ql/src/test/results/clientpositive/vectorization_14.q.out index eb2c486..cff0ccd 100644 --- ql/src/test/results/clientpositive/vectorization_14.q.out +++ ql/src/test/results/clientpositive/vectorization_14.q.out @@ -77,15 +77,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((ctinyint <= cbigint) and ((cint <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < ctinyint)) and ((cbigint > -257) or (cfloat < cint))) (type: boolean) + predicate: ((((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < UDFToDouble(ctinyint))) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double) - outputColumnNames: ctimestamp1, cfloat, cstring1, cboolean1, cdouble + 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 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp((- ((- 26.28) + cdouble))), max(cfloat), stddev_pop(cfloat), count(cfloat), var_pop(cfloat), var_samp(cfloat) - keys: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE @@ -104,7 +104,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 303 Data size: 9301 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), (_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), (_col1 - _col4) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (_col1 - _col4)) (type: double) + 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 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/vectorization_15.q.out ql/src/test/results/clientpositive/vectorization_15.q.out index e6be949..5cc9cb0 100644 --- ql/src/test/results/clientpositive/vectorization_15.q.out +++ ql/src/test/results/clientpositive/vectorization_15.q.out @@ -73,15 +73,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cstring2 like '%ss%') or (cstring1 like '10%')) or ((cint >= -75) and ((ctinyint = csmallint) and (cdouble >= -3728)))) (type: boolean) + predicate: ((cstring2 like '%ss%') or ((cstring1 like '10%') or ((cint >= -75) and ((UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: cfloat, cboolean1, cdouble, cstring1, ctinyint, cint, ctimestamp1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) - keys: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -100,7 +100,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 6144 Data size: 188618 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 - _col5) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (_col5 - _col0) (type: float), (-23 % _col4) (type: int), (- (-26.28 - _col5)) (type: double), _col12 (type: double) + 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 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/vectorization_16.q.out ql/src/test/results/clientpositive/vectorization_16.q.out index 1fc662b..6184dca 100644 --- ql/src/test/results/clientpositive/vectorization_16.q.out +++ ql/src/test/results/clientpositive/vectorization_16.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: cstring1, cdouble, ctimestamp1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) - keys: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) + aggregations: count(_col1), stddev_samp(_col1), min(_col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE @@ -77,7 +77,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 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 * _col3) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (_col3 / -1.389) (type: double), _col4 (type: double) + 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 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/vectorization_7.q.out ql/src/test/results/clientpositive/vectorization_7.q.out index a4b7b40..292da75 100644 --- ql/src/test/results/clientpositive/vectorization_7.q.out +++ ql/src/test/results/clientpositive/vectorization_7.q.out @@ -62,10 +62,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ctinyint <> 0) and ((ctimestamp1 <= 0) or ((ctinyint = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((ctimestamp2 > -15) and (3569.0 >= cdouble)))) (type: boolean) + predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > -15.0) and (3569.0 >= cdouble)))) (type: boolean) Statistics: Num rows: 7281 Data size: 223523 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), (csmallint % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), ((- ctinyint) + 17) (type: int), (cbigint * (- csmallint)) (type: bigint), (cint % csmallint) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + 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 Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE Limit @@ -231,10 +231,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((ctinyint <> 0) and ((ctimestamp1 <= 0.0) or ((ctinyint = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((ctimestamp2 > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) + predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) Statistics: Num rows: 7281 Data size: 223523 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), (csmallint % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), ((- ctinyint) + 17) (type: int), (cbigint * (- csmallint)) (type: bigint), (cint % csmallint) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + 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 Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/vectorization_8.q.out ql/src/test/results/clientpositive/vectorization_8.q.out index c300faa..feef5b9 100644 --- ql/src/test/results/clientpositive/vectorization_8.q.out +++ ql/src/test/results/clientpositive/vectorization_8.q.out @@ -58,10 +58,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 is not null and ((ctimestamp1 <= 10) and (ctimestamp2 <> 16))) or ((cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) + predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 10.0) and (UDFToDouble(ctimestamp2) <> 16.0))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) Statistics: Num rows: 9216 Data size: 282927 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) (type: double), (cint + cfloat) (type: float), ((- cdouble) + cbigint) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + (cint + cfloat)) (type: double) + 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 Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE Limit @@ -214,10 +214,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 is not null and ((ctimestamp1 <= 12.503) and (ctimestamp2 <> 11.998))) or ((cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) + predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 12.503) and (UDFToDouble(ctimestamp2) <> 11.998))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) Statistics: Num rows: 9216 Data size: 282927 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) (type: double), (cint + cfloat) (type: float), ((- cdouble) + cbigint) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + (cint + cfloat)) (type: double) + 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 Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE Limit diff --git ql/src/test/results/clientpositive/vectorization_9.q.out ql/src/test/results/clientpositive/vectorization_9.q.out index 9481d0a..1ff5d94 100644 --- ql/src/test/results/clientpositive/vectorization_9.q.out +++ ql/src/test/results/clientpositive/vectorization_9.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: cstring1, cdouble, ctimestamp1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) - keys: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) + aggregations: count(_col1), stddev_samp(_col1), min(_col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE @@ -77,7 +77,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 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 * _col3) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (_col3 / -1.389) (type: double), _col4 (type: double) + 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 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/vectorization_div0.q.out ql/src/test/results/clientpositive/vectorization_div0.q.out index 962c466..56e9de7 100644 --- ql/src/test/results/clientpositive/vectorization_div0.q.out +++ ql/src/test/results/clientpositive/vectorization_div0.q.out @@ -176,7 +176,7 @@ STAGE PLANS: predicate: ((cbigint > 0) and (cbigint < 100000000)) (type: boolean) Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cbigint - 988888) (type: bigint), (cdouble / (cbigint - 988888)) (type: double), (1.2 / (cbigint - 988888)) (type: double) + expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / UDFToDouble((cbigint - 988888))) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -341,10 +341,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble >= -500) and (cdouble < -199)) (type: boolean) + predicate: ((cdouble >= -500.0) and (cdouble < -199.0)) (type: boolean) Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cdouble + 200.0) (type: double), (cbigint / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) + 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 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git ql/src/test/results/clientpositive/vectorization_limit.q.out ql/src/test/results/clientpositive/vectorization_limit.q.out index 5a31b9e..60f4b92 100644 --- ql/src/test/results/clientpositive/vectorization_limit.q.out +++ ql/src/test/results/clientpositive/vectorization_limit.q.out @@ -15,7 +15,7 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cbigint < cdouble) and (cint > 0)) (type: boolean) + predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) @@ -160,12 +160,12 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: ctinyint, cdouble + expressions: ctinyint (type: tinyint), (cdouble + 1.0) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg((cdouble + 1)) - keys: ctinyint (type: tinyint) + aggregations: avg(_col1) + keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -254,10 +254,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: ctinyint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: ctinyint (type: tinyint) + keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -342,11 +342,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: ctinyint, cdouble + outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT cdouble) - keys: ctinyint (type: tinyint), cdouble (type: double) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -464,11 +464,11 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: cdouble, ctinyint + outputColumnNames: _col0, _col1 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(ctinyint) - keys: cdouble (type: double) + aggregations: sum(_col1) + keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vectorization_part_project.q.out ql/src/test/results/clientpositive/vectorization_part_project.q.out index d2c2c38..57012b2 100644 --- ql/src/test/results/clientpositive/vectorization_part_project.q.out +++ ql/src/test/results/clientpositive/vectorization_part_project.q.out @@ -62,7 +62,7 @@ STAGE PLANS: alias: alltypesorc_part Statistics: Num rows: 200 Data size: 41576 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cdouble + 2) (type: double) + expressions: (cdouble + 2.0) (type: double) outputColumnNames: _col0 Statistics: Num rows: 200 Data size: 41576 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git ql/src/test/results/clientpositive/vectorization_pushdown.q.out ql/src/test/results/clientpositive/vectorization_pushdown.q.out index 3a39a15..bfbf81e 100644 --- ql/src/test/results/clientpositive/vectorization_pushdown.q.out +++ ql/src/test/results/clientpositive/vectorization_pushdown.q.out @@ -13,17 +13,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - filterExpr: (cbigint < cdouble) (type: boolean) + filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cbigint < cdouble) (type: boolean) + predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: cbigint + outputColumnNames: _col0 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cbigint) + aggregations: avg(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git ql/src/test/results/clientpositive/vectorization_short_regress.q.out ql/src/test/results/clientpositive/vectorization_short_regress.q.out index 34394c5..02ceb28 100644 --- ql/src/test/results/clientpositive/vectorization_short_regress.q.out +++ ql/src/test/results/clientpositive/vectorization_short_regress.q.out @@ -143,14 +143,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((762 = cbigint) or ((csmallint < cfloat) and ((ctimestamp2 > -5) and (cdouble <> cint)))) or (cstring1 = 'a')) or ((cbigint <= -1.389) and ((cstring2 <> 'a') and ((79.553 <> cint) and (cboolean2 <> cboolean1))))) (type: boolean) + predicate: ((762 = cbigint) or (((UDFToFloat(csmallint) < cfloat) and ((UDFToDouble(ctimestamp2) > -5.0) and (cdouble <> UDFToDouble(cint)))) or ((cstring1 = 'a') or ((UDFToDouble(cbigint) <= -1.389) and ((cstring2 <> 'a') and ((79.553 <> UDFToDouble(cint)) and (cboolean2 <> cboolean1))))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: cint, cdouble, csmallint, cfloat, ctinyint + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) + aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) 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 @@ -166,7 +166,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 68 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (_col0 + -3728) (type: double), (- (_col0 + -3728)) (type: double), (- (- (_col0 + -3728))) (type: double), ((- (- (_col0 + -3728))) * (_col0 + -3728)) (type: double), _col1 (type: double), (- _col0) (type: double), _col2 (type: double), (((- (- (_col0 + -3728))) * (_col0 + -3728)) * (- (- (_col0 + -3728)))) (type: double), _col3 (type: double), (- _col2) (type: double), (_col2 - (- (- (_col0 + -3728)))) (type: double), ((_col2 - (- (- (_col0 + -3728)))) * _col2) (type: double), _col4 (type: double), _col5 (type: double), (10.175 - _col4) (type: double), (- (10.175 - _col4)) (type: double), ((- _col2) / -563) (type: double), _col6 (type: double), (- ((- _col2) / -563)) (type: double), (_col0 / _col1) (type: double), _col7 (type: tinyint), _col8 (type: bigint), (_col7 / ((- _col2) / -563)) (type: double), (- (_col0 / _col1)) (type: double) + 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 File Output Operator @@ -349,14 +349,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((cbigint <= 197) and (cint < cbigint)) or ((cdouble >= -26.28) and (csmallint > cdouble))) or ((ctinyint > cfloat) and (cstring1 rlike '.*ss.*'))) or ((cfloat > 79.553) and (cstring2 like '10%'))) (type: boolean) + predicate: (((cbigint <= 197) and (UDFToLong(cint) < cbigint)) or (((cdouble >= -26.28) and (UDFToDouble(csmallint) > cdouble)) or (((UDFToFloat(ctinyint) > cfloat) and (cstring1 rlike '.*ss.*')) or ((cfloat > 79.553) and (cstring2 like '10%'))))) (type: boolean) Statistics: Num rows: 6826 Data size: 209555 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: cint, cbigint, csmallint, cdouble, ctinyint + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) + aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) 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 @@ -372,7 +372,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), (_col0 / -3728) (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), ((_col0 * -3728) % (_col2 - 10.175)) (type: double), (- _col3) (type: double), _col6 (type: double), (_col3 % -26.28) (type: double), _col7 (type: double), (- (_col0 / -3728)) (type: double), ((- (_col0 * -3728)) % (-563 % (_col0 * -3728))) (type: int), ((_col0 / -3728) - _col4) (type: double), (- (_col0 * -3728)) (type: int), _col8 (type: double) + 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 File Output Operator @@ -546,14 +546,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((ctimestamp1 = ctimestamp2) or (762.0 = cfloat)) or (cstring1 = 'ss')) or ((csmallint <= cbigint) and (1 = cboolean2))) or (cboolean1 is not null and (ctimestamp2 is not null and (cstring2 > 'a')))) (type: boolean) + predicate: ((ctimestamp1 = ctimestamp2) or ((762.0 = cfloat) or ((cstring1 = 'ss') or (((UDFToLong(csmallint) <= cbigint) and (1 = cboolean2)) or (cboolean1 is not null and (ctimestamp2 is not null and (cstring2 > 'a'))))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: cbigint, ctinyint, csmallint, cint, cdouble + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) + aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -569,7 +569,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (- _col0) (type: double), (_col0 - (- _col0)) (type: double), _col1 (type: bigint), (_col1 % 79.553) (type: double), _col2 (type: tinyint), (_col1 - (- _col0)) (type: double), (- (- _col0)) (type: double), (-1 % (- _col0)) (type: double), _col1 (type: bigint), (- _col1) (type: bigint), _col3 (type: double), (- (- (- _col0))) (type: double), (762 * (- _col1)) (type: bigint), _col4 (type: int), (_col2 + (762 * (- _col1))) (type: bigint), ((- _col0) + _col4) (type: double), _col5 (type: double), ((- _col1) % _col1) (type: bigint), _col6 (type: bigint), _col7 (type: double), (-3728 % (_col2 + (762 * (- _col1)))) (type: bigint) + 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 File Output Operator @@ -722,14 +722,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((ctimestamp2 <= ctimestamp1) and ((cbigint <> cdouble) and ('ss' <= cstring1))) or ((csmallint < ctinyint) and (ctimestamp1 >= 0))) or (cfloat = 17.0)) (type: boolean) + predicate: (((ctimestamp2 <= ctimestamp1) and ((UDFToDouble(cbigint) <> cdouble) and ('ss' <= cstring1))) or (((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0)) or (cfloat = 17.0))) (type: boolean) Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) - outputColumnNames: ctinyint, cbigint, cint, cfloat + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) + aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -745,7 +745,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (_col0 + 6981) (type: double), ((_col0 + 6981) + _col0) (type: double), _col1 (type: bigint), (((_col0 + 6981) + _col0) / _col0) (type: double), (- (_col0 + 6981)) (type: double), _col2 (type: double), (_col0 % (- (_col0 + 6981))) (type: double), _col3 (type: double), _col4 (type: double), (- _col1) (type: bigint), ((- _col1) / _col2) (type: double), _col5 (type: float), (_col4 * -26.28) (type: double) + 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 File Output Operator @@ -904,10 +904,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((cstring1 rlike 'a.*') and (cstring2 like '%ss%')) or ((1 <> cboolean2) and ((csmallint < 79.553) and (-257 <> ctinyint)))) or ((cdouble > ctinyint) and (cfloat >= cint))) or ((cint < cbigint) and (ctinyint > cbigint))) (type: boolean) + predicate: (((cstring1 rlike 'a.*') and (cstring2 like '%ss%')) or (((1 <> cboolean2) and ((UDFToDouble(csmallint) < 79.553) and (-257 <> UDFToInteger(ctinyint)))) or (((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or ((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint))))) (type: boolean) Statistics: Num rows: 9898 Data size: 303864 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 - cint) (type: double), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (cint / cint) (type: double), ((-863.257 - cint) - -26.28) (type: double), (- cfloat) (type: float), (cdouble * -89010) (type: double), (ctinyint / 988888) (type: double), (- ctinyint) (type: tinyint), (79.553 / ctinyint) (type: double) + 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 Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE Limit @@ -1142,10 +1142,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((197.0 > ctinyint) and (cint = cbigint)) or (cbigint = 359)) or (cboolean1 < 0)) or ((cstring1 like '%ss') and (cfloat <= ctinyint))) (type: boolean) + predicate: (((197.0 > UDFToDouble(ctinyint)) and (UDFToLong(cint) = cbigint)) or ((cbigint = 359) or ((cboolean1 < 0) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint)))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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), (cint / cbigint) (type: double), (cbigint % 79.553) (type: double), (- (cint / cbigint)) (type: double), (10.175 % cfloat) (type: double), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432) (type: float), (cdouble * csmallint) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (cfloat - (cint / cbigint)) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359 - cdouble) (type: double), (- csmallint) (type: smallint) + 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 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Limit @@ -1331,10 +1331,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((csmallint > -26.28) and (cstring2 like 'ss')) or ((cdouble <= cbigint) and ((cstring1 >= 'ss') and (cint <> cdouble)))) or (ctinyint = -89010)) or ((cbigint <= cfloat) and (-26.28 <= csmallint))) (type: boolean) + predicate: (((UDFToDouble(csmallint) > -26.28) and (cstring2 like 'ss')) or (((cdouble <= UDFToDouble(cbigint)) and ((cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble))) or ((UDFToInteger(ctinyint) = -89010) or ((UDFToFloat(cbigint) <= cfloat) and (-26.28 <= UDFToDouble(csmallint)))))) (type: boolean) Statistics: Num rows: 10922 Data size: 335301 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 + csmallint) (type: int), (cbigint - ctinyint) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - ctinyint) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), ((cint + csmallint) * (- cbigint)) (type: bigint), ((- cdouble) + cbigint) (type: double), (-1.389 / ctinyint) (type: double), (cbigint % cdouble) (type: double), (- csmallint) (type: smallint), (csmallint + (cint + csmallint)) (type: int) + 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 Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -1590,10 +1590,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((-1.389 >= cint) and ((csmallint < ctinyint) and (-6432 > csmallint))) or ((cdouble >= cfloat) and (cstring2 <= 'a'))) or ((cstring1 like 'ss%') and (10.175 > cbigint))) (type: boolean) + predicate: (((-1.389 >= UDFToDouble(cint)) and ((csmallint < UDFToShort(ctinyint)) and (-6432 > UDFToInteger(csmallint)))) or (((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (10.175 > UDFToDouble(cbigint))))) (type: boolean) Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), (cdouble * 10.175) (type: double), ((-6432 * cfloat) / cfloat) (type: double), (- cfloat) (type: float), (cint % csmallint) (type: int), (cdouble * (- cdouble)) (type: double), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (cbigint / 3569) (type: double), (-257 - csmallint) (type: int), (-6432 * cfloat) (type: float), (- cdouble) (type: double) + expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (cdouble * (- cdouble)) (type: double), 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) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col15, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -1791,15 +1791,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint >= -257) and ((-6432 = csmallint) or ((cint >= cdouble) and (ctinyint <= cint)))) (type: boolean) + predicate: ((UDFToInteger(csmallint) >= -257) and ((-6432 = UDFToInteger(csmallint)) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint)))) (type: boolean) Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) - outputColumnNames: csmallint, cbigint, ctinyint + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() - keys: csmallint (type: smallint) + aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() + keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE @@ -1818,7 +1818,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: smallint), (_col0 % -75) (type: int), _col1 (type: double), (-1.389 / _col0) (type: double), _col2 (type: bigint), ((_col0 % -75) / _col2) (type: double), (- (_col0 % -75)) (type: int), _col3 (type: double), (- (- (_col0 % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) + 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 Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2002,15 +2002,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble > 2563.58) and (((cbigint >= cint) and ((csmallint < cint) and (cfloat < -5638.15))) or ((cdouble <= cbigint) and (-5638.15 > cbigint)))) (type: boolean) + predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and ((UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15))) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) - outputColumnNames: cdouble, cfloat + outputColumnNames: _col0, _col1 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) - keys: cdouble (type: double) + aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) + keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE @@ -2029,7 +2029,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762)) (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) + 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 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2257,15 +2257,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((ctimestamp1 <> 0) and (((((((-257 <> ctinyint) and cboolean2 is not null) and ((cstring1 rlike '.*ss') and (-3 < ctimestamp1))) or (ctimestamp2 = -5)) or ((ctimestamp1 < 0) and (cstring2 like '%b%'))) or (cdouble = cint)) or (cboolean1 is null and (cfloat < cint)))) (type: boolean) + predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and (cboolean2 is not null and ((cstring1 rlike '.*ss') and (-3.0 < UDFToDouble(ctimestamp1))))) or ((UDFToDouble(ctimestamp2) = -5.0) or (((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or ((cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint)))))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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: ctimestamp1, cstring1, cint, csmallint, ctinyint, cfloat, cdouble + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) - keys: ctimestamp1 (type: timestamp), cstring1 (type: string) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -2284,7 +2284,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 6144 Data size: 188618 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)) * (- _col4)) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) (type: double), (- (- _col2)) (type: double), ((- _col4) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) - (((-26.28 - _col2) * (- _col2)) * (- _col4))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) - (((-26.28 - _col2) * (- _col2)) * (- _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 / (- _col5)) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) % -26.28) (type: double) + 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 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Limit @@ -2570,15 +2570,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cboolean1 is not null and (((((cdouble < csmallint) and ((cboolean2 = cboolean1) and (cbigint <= -863.257))) or ((cint >= -257) and (cstring1 is not null and (cboolean1 >= 1)))) or (cstring2 rlike 'b')) or ((csmallint >= ctinyint) and ctimestamp2 is null))) (type: boolean) + predicate: (cboolean1 is not null and (((cdouble < UDFToDouble(csmallint)) and ((cboolean2 = cboolean1) and (UDFToDouble(cbigint) <= -863.257))) or (((cint >= -257) and (cstring1 is not null and (cboolean1 >= 1))) or ((cstring2 rlike 'b') or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null))))) (type: boolean) Statistics: Num rows: 4778 Data size: 146682 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: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) - keys: cboolean1 (type: boolean) + 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) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE @@ -2597,7 +2597,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: float), ((_col2 - 10.175) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + (- _col1))) (type: double), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * _col5) (type: double), (- _col1) (type: float), (_col7 - (-1.389 * _col5)) (type: double), _col9 (type: double), (- (_col7 - (-1.389 * _col5))) (type: double), _col10 (type: double), (- _col10) (type: double), (_col10 * _col7) (type: double), (-26.28 / _col1) (type: double), _col2 (type: bigint), (_col2 - 10.175) (type: double), _col3 (type: double), (_col3 % _col1) (type: double), (10.175 + (- _col1)) (type: double), _col4 (type: double) + 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 Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2813,10 +2813,10 @@ STAGE PLANS: Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: i + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(i) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -2985,10 +2985,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: ctinyint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(ctinyint) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3049,10 +3049,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: cint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cint) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3113,10 +3113,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: cfloat + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cfloat) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3177,10 +3177,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: cstring1 + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cstring1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3241,10 +3241,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean) - outputColumnNames: cboolean1 + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cboolean1) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vectorized_case.q.out ql/src/test/results/clientpositive/vectorized_case.q.out index bec3de1..1aede37 100644 --- ql/src/test/results/clientpositive/vectorized_case.q.out +++ ql/src/test/results/clientpositive/vectorized_case.q.out @@ -46,7 +46,7 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((csmallint = 418) or (csmallint = 12205)) or (csmallint = 10583)) (type: boolean) + predicate: ((csmallint = 418) or ((csmallint = 12205) or (csmallint = 10583))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 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) diff --git ql/src/test/results/clientpositive/vectorized_casts.q.out ql/src/test/results/clientpositive/vectorized_casts.q.out index 8ce937f..8de66fb 100644 --- ql/src/test/results/clientpositive/vectorized_casts.q.out +++ ql/src/test/results/clientpositive/vectorized_casts.q.out @@ -161,7 +161,7 @@ STAGE PLANS: predicate: ((cbigint % 250) = 0) (type: boolean) Statistics: Num rows: 6144 Data size: 188618 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), UDFToFloat(UDFToInteger(cfloat)) (type: float), UDFToDouble((cint * 2)) (type: double), UDFToString(sin(cfloat)) (type: string), (UDFToFloat(cint) + UDFToDouble(cboolean1)) (type: double) + 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), 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 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/vectorized_date_funcs.q.out ql/src/test/results/clientpositive/vectorized_date_funcs.q.out index bf4230f..2d17e84 100644 --- ql/src/test/results/clientpositive/vectorized_date_funcs.q.out +++ ql/src/test/results/clientpositive/vectorized_date_funcs.q.out @@ -466,7 +466,7 @@ STAGE PLANS: alias: date_udf_flight_orc 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), CAST( fl_date AS 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) + 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 Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -691,7 +691,7 @@ STAGE PLANS: alias: date_udf_flight_orc 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) = CAST( fl_date AS 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) + 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 Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out index e19186f..3601c7f 100644 --- ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out +++ 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: a + outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT a), count(DISTINCT a) + aggregations: sum(DISTINCT _col0), count(DISTINCT _col0) bucketGroup: true - keys: a (type: int) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -97,11 +97,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: cint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT cint), count(DISTINCT cint), avg(DISTINCT cint), std(DISTINCT cint) - keys: cint (type: int) + aggregations: sum(DISTINCT _col0), count(DISTINCT _col0), avg(DISTINCT _col0), std(DISTINCT _col0) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vectorized_mapjoin.q.out ql/src/test/results/clientpositive/vectorized_mapjoin.q.out index da1a838..1049109 100644 --- ql/src/test/results/clientpositive/vectorized_mapjoin.q.out +++ ql/src/test/results/clientpositive/vectorized_mapjoin.q.out @@ -15,58 +15,66 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - t1 + $hdt$_0:$hdt$_0:$hdt$_0:t1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - t1 + $hdt$_0:$hdt$_0:$hdt$_0:t1 TableScan alias: t1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 - 1 {cint} - keys: - 0 cint (type: int) - 1 cint (type: int) + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 + 1 {_col0} + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: t2 + alias: t1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {cint} - 1 {cint} - keys: - 0 cint (type: int) - 1 cint (type: int) - outputColumnNames: _col2, _col17 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: int), _col17 (type: int) - outputColumnNames: _col2, _col17 + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col0} + 1 {_col0} + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col2), max(_col17), min(_col2), avg((_col2 + _col17)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), _col3 (type: struct) + 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: int), _col2 (type: int), _col3 (type: struct) Local Work: Map Reduce Local Work Execution mode: vectorized diff --git ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out index ed7e595..ce1b8d3 100644 --- ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out +++ ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out @@ -11,69 +11,78 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - t1:v1 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:v1 Fetch Operator limit: -1 - v3 + $hdt$_0:$hdt$_0:$hdt$_1:v1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - t1:v1 + $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:v1 TableScan alias: v1 Statistics: Num rows: 12288 Data size: 377237 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: 94309 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 {csmallint} {cdouble} - 1 {ctinyint} - keys: - 0 ctinyint (type: tinyint) - 1 ctinyint (type: tinyint) - v3 + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col1} {_col2} + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + $hdt$_0:$hdt$_0:$hdt$_1:v1 TableScan - alias: v3 + alias: v1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: csmallint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - condition expressions: - 0 {_col1} - 1 - keys: - 0 _col0 (type: smallint) - 1 csmallint (type: smallint) + Select Operator + expressions: csmallint (type: smallint) + outputColumnNames: _col0 + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + condition expressions: + 0 {_col1} + 1 + keys: + 0 _col0 (type: smallint) + 1 _col0 (type: smallint) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: v2 + alias: v1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {ctinyint} {csmallint} {cdouble} - 1 {ctinyint} - keys: - 0 ctinyint (type: tinyint) - 1 ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col5, _col15 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = _col15) (type: boolean) - Statistics: Num rows: 3379 Data size: 103739 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {_col1} {_col2} + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: smallint), _col5 (type: double) + expressions: _col1 (type: smallint), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3379 Data size: 103739 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -82,15 +91,15 @@ STAGE PLANS: 1 keys: 0 _col0 (type: smallint) - 1 csmallint (type: smallint) + 1 _col0 (type: smallint) outputColumnNames: _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vectorized_parquet.q.out ql/src/test/results/clientpositive/vectorized_parquet.q.out index a81a9b3..3cdd9c8 100644 --- ql/src/test/results/clientpositive/vectorized_parquet.q.out +++ ql/src/test/results/clientpositive/vectorized_parquet.q.out @@ -147,11 +147,11 @@ 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: ctinyint, cint, csmallint, cstring1, cfloat, cdouble + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(cint), min(csmallint), count(cstring1), avg(cfloat), stddev_pop(cdouble) - keys: ctinyint (type: tinyint) + aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5) + keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out index f621927..3b8031d 100644 --- ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out +++ ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out @@ -16,27 +16,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t2 + alias: t1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: cint (type: int) - sort order: + - Map-reduce partition columns: cint (type: int) + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 Statistics: Num rows: 6144 Data size: 188618 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE TableScan alias: t1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: cint (type: int) - sort order: + - Map-reduce partition columns: cint (type: int) + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 Statistics: Num rows: 6144 Data size: 188618 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Join Operator @@ -45,14 +53,14 @@ STAGE PLANS: condition expressions: 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} - outputColumnNames: _col2, _col17 + outputColumnNames: _col0, _col1 Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: int), _col17 (type: int) - outputColumnNames: _col2, _col17 + expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col2), max(_col17), min(_col2), avg((_col2 + _col17)) + aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out index efde414..7a89552 100644 --- ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out +++ ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out @@ -609,10 +609,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: ctimestamp1 + outputColumnNames: _col0 Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() + aggregations: min(_col0), max(_col0), count(_col0), count() mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE @@ -687,10 +687,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: ctimestamp1 + outputColumnNames: _col0 Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(ctimestamp1) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -770,10 +770,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: ctimestamp1 + outputColumnNames: _col0 Statistics: Num rows: 40 Data size: 5694 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(ctimestamp1), variance(ctimestamp1), var_pop(ctimestamp1), var_samp(ctimestamp1), std(ctimestamp1), stddev(ctimestamp1), stddev_pop(ctimestamp1), stddev_samp(ctimestamp1) + aggregations: avg(_col0), variance(_col0), var_pop(_col0), var_samp(_col0), std(_col0), stddev(_col0), stddev_pop(_col0), stddev_samp(_col0) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git ql/src/test/results/clientpositive/windowing_streaming.q.out ql/src/test/results/clientpositive/windowing_streaming.q.out index d43c699..6be6c38 100644 --- ql/src/test/results/clientpositive/windowing_streaming.q.out +++ ql/src/test/results/clientpositive/windowing_streaming.q.out @@ -107,19 +107,23 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_name (type: string) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_name (type: string), p_mfgr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string), p_mfgr (type: string) + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE PTF Operator Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _wcol0 (type: int) + expressions: _col1 (type: string), _wcol0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -157,13 +161,17 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_name (type: string) - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) + Select Operator + expressions: p_name (type: string), p_mfgr (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.8 - value expressions: p_name (type: string), p_mfgr (type: string) + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.8 + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE @@ -173,7 +181,7 @@ STAGE PLANS: predicate: (_wcol0 < 4) (type: boolean) Statistics: Num rows: 5 Data size: 1057 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _wcol0 (type: int) + expressions: _col1 (type: string), _wcol0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 1057 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -306,13 +314,17 @@ STAGE PLANS: TableScan alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: ctinyint (type: tinyint), cdouble (type: double) - sort order: ++ - Map-reduce partition columns: ctinyint (type: tinyint) + Select Operator + expressions: ctinyint (type: tinyint), cdouble (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.8 - value expressions: ctinyint (type: tinyint), cdouble (type: double) + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: double) + sort order: ++ + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.8 + value expressions: _col0 (type: tinyint), _col1 (type: double) Reduce Operator Tree: Extract Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -322,7 +334,7 @@ STAGE PLANS: predicate: (_wcol0 < 5) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: tinyint), _col5 (type: double), _wcol0 (type: int) + expressions: _col0 (type: tinyint), _col1 (type: double), _wcol0 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE File Output Operator