http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out b/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out index 062f8e7..764bcfe 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out @@ -30,6 +30,8 @@ POSTHOOK: query: create table t4 (id int, key string, value string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@t4 +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from t1 full outer join t2 on t1.id=t2.id join t3 on t2.id=t3.id where t3.id=20 PREHOOK: type: QUERY POSTHOOK: query: explain select * from t1 full outer join t2 on t1.id=t2.id join t3 on t2.id=t3.id where t3.id=20 @@ -42,7 +44,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -58,12 +61,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) - Map 3 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + Map 4 Map Operator Tree: TableScan alias: t2 @@ -72,16 +73,14 @@ STAGE PLANS: predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) - Map 4 + Map 5 Map Operator Tree: TableScan alias: t3 @@ -90,13 +89,11 @@ STAGE PLANS: predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Reducer 2 @@ -104,20 +101,39 @@ STAGE PLANS: Join Operator condition map: Right Outer Join0 to 1 - Inner Join 1 to 2 + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -125,6 +141,8 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t2.id=t3.id) where t2.id=20 PREHOOK: type: QUERY POSTHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t2.id=t3.id) where t2.id=20 @@ -137,7 +155,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -149,16 +168,14 @@ STAGE PLANS: predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) - Map 3 + Map 4 Map Operator Tree: TableScan alias: t2 @@ -167,16 +184,14 @@ STAGE PLANS: predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) - Map 4 + Map 5 Map Operator Tree: TableScan alias: t3 @@ -189,30 +204,44 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Left Outer Join1 to 2 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col1, _col2, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1, _col2, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -220,6 +249,8 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t1.id=t3.id) where t2.id=20 PREHOOK: type: QUERY POSTHOOK: query: explain select * from t1 join t2 on (t1.id=t2.id) left outer join t3 on (t1.id=t3.id) where t2.id=20 @@ -232,7 +263,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -244,16 +276,14 @@ STAGE PLANS: predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) - Map 3 + Map 4 Map Operator Tree: TableScan alias: t2 @@ -262,16 +292,14 @@ STAGE PLANS: predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) - Map 4 + Map 5 Map Operator Tree: TableScan alias: t3 @@ -284,30 +312,44 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Left Outer Join0 to 2 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col1, _col2, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1, _col2, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/semijoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/semijoin.q.out b/ql/src/test/results/clientpositive/spark/semijoin.q.out index c0f761a..3ed8c02 100644 --- a/ql/src/test/results/clientpositive/spark/semijoin.q.out +++ b/ql/src/test/results/clientpositive/spark/semijoin.q.out @@ -2520,7 +2520,7 @@ STAGE PLANS: 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) + predicate: ((key > 100) and value is not null) (type: boolean) Statistics: Num rows: 7 Data size: 51 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out index 6fdee3c..4b392ba 100644 --- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out +++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out @@ -46,6 +46,8 @@ POSTHOOK: query: load data local inpath '../../data/files/smbbucket_3.rc' overwr POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smb_bucket_3 +Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 6' is a cross product PREHOOK: query: explain select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5 PREHOOK: type: QUERY @@ -60,8 +62,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) - Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 2), Map 7 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1) Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: @@ -76,9 +78,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 5 (type: int) - sort order: + - Map-reduce partition columns: 5 (type: int) + sort order: Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: @@ -91,9 +91,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 5 (type: int) - sort order: + - Map-reduce partition columns: 5 (type: int) + sort order: Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: @@ -106,9 +104,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 5 (type: int) - sort order: + - Map-reduce partition columns: 5 (type: int) + sort order: Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: @@ -121,9 +117,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 5 (type: int) - sort order: + - Map-reduce partition columns: 5 (type: int) + sort order: Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: @@ -131,8 +125,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 + 1 Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 5 (type: int) @@ -145,8 +139,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 5 (type: int) + 1 5 (type: int) Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), 5 (type: int) @@ -165,8 +159,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 + 1 Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 5 (type: int) @@ -180,6 +174,8 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Map Join MAPJOIN[33][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- explain -- select * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join src c on a.key=c.value @@ -219,8 +215,8 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 5 (type: int) - 1 5 (type: int) + 0 + 1 Local Work: Map Reduce Local Work @@ -242,8 +238,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 5 (type: int) - 1 5 (type: int) + 0 + 1 input vertices: 1 Map 2 Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE @@ -265,8 +261,8 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 5 (type: int) - 1 5 (type: int) + 0 + 1 Local Work: Map Reduce Local Work @@ -288,8 +284,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 5 (type: int) - 1 5 (type: int) + 0 + 1 input vertices: 0 Map 3 Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE @@ -322,6 +318,8 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Map Join MAPJOIN[33][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5 PREHOOK: type: QUERY PREHOOK: Input: default@smb_bucket_1 http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/subquery_exists.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_exists.q.out b/ql/src/test/results/clientpositive/spark/subquery_exists.q.out index 22fb77e..0d89ec5 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_exists.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_exists.q.out @@ -41,7 +41,7 @@ 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 > 'val_9')) (type: boolean) + predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/subquery_in.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_in.q.out b/ql/src/test/results/clientpositive/spark/subquery_in.q.out index 66840ec..16b7684 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_in.q.out @@ -149,7 +149,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and (key > '9')) (type: boolean) + predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -629,7 +629,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and (key > '9')) (type: boolean) + predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -785,7 +785,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out b/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out index f2c7b08..bbf24fd 100644 --- a/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out @@ -509,7 +509,7 @@ Keys:val,key Table:default@t2 Keys:key -Operator:GBY_16 +Operator:GBY_17 Table:default@t3 Keys:val http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/union_remove_19.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/union_remove_19.q.out b/ql/src/test/results/clientpositive/spark/union_remove_19.q.out index df0fecd..4686b8e 100644 --- a/ql/src/test/results/clientpositive/spark/union_remove_19.q.out +++ b/ql/src/test/results/clientpositive/spark/union_remove_19.q.out @@ -248,25 +248,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1 - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '7' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -275,10 +275,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 14 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -291,10 +291,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 14 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out index 85cee4d..e3a0379 100644 --- a/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out @@ -100,7 +100,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) @@ -202,7 +202,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) @@ -262,7 +262,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out index b744927..f7eadaf 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out @@ -2678,7 +2678,7 @@ 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 < UDFToDouble(csmallint)) and (cboolean2 = cboolean1) and (UDFToDouble(cbigint) <= -863.257)) or ((cint >= -257) and cstring1 is not null and (cboolean1 >= 1)) or cstring2 regexp 'b' or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null))) (type: boolean) + predicate: ((((cdouble < UDFToDouble(csmallint)) and (cboolean2 = cboolean1) and (UDFToDouble(cbigint) <= -863.257)) or ((cint >= -257) and cstring1 is not null and (cboolean1 >= 1)) or cstring2 regexp 'b' or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null)) and cboolean1 is not null) (type: boolean) Statistics: Num rows: 10239 Data size: 314333 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) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/spark/vectorized_case.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out index 7d15136..c06ea94 100644 --- a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out @@ -52,7 +52,7 @@ STAGE PLANS: 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) + expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -166,7 +166,7 @@ STAGE PLANS: 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 (null) END (type: string), CASE (csmallint) WHEN (418) THEN ('a') WHEN (12205) THEN (null) ELSE ('c') END (type: string) + expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN (null) ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/subquery_exists.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/subquery_exists.q.out b/ql/src/test/results/clientpositive/subquery_exists.q.out index 26b9a38..1a17274 100644 --- a/ql/src/test/results/clientpositive/subquery_exists.q.out +++ b/ql/src/test/results/clientpositive/subquery_exists.q.out @@ -36,7 +36,7 @@ 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 > 'val_9')) (type: boolean) + predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/subquery_in.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/subquery_in.q.out b/ql/src/test/results/clientpositive/subquery_in.q.out index 8f5c43c..f75f7d8 100644 --- a/ql/src/test/results/clientpositive/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/subquery_in.q.out @@ -136,7 +136,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and (key > '9')) (type: boolean) + predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -669,7 +669,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and (key > '9')) (type: boolean) + predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -790,7 +790,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + predicate: (((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/subquery_notin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/subquery_notin.q.out b/ql/src/test/results/clientpositive/subquery_notin.q.out index 090bdec..f1fceba 100644 --- a/ql/src/test/results/clientpositive/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/subquery_notin.q.out @@ -1475,7 +1475,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE (key) END is null) (type: boolean) + predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (true) ELSE (key is null) END) (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 http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index 7aa2375..6f2e5ca 100644 --- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -52,7 +52,7 @@ STAGE PLANS: alias: src11 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (value1 is not null and (key1 > '9')) (type: boolean) + predicate: ((key1 > '9') and value1 is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key1 (type: string), value1 (type: string) @@ -122,7 +122,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and (key > '9')) (type: boolean) + predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -586,7 +586,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and (key > '9')) (type: boolean) + predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/a6d9bf76/ql/src/test/results/clientpositive/table_access_keys_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/table_access_keys_stats.q.out b/ql/src/test/results/clientpositive/table_access_keys_stats.q.out index f2c7b08..bbf24fd 100644 --- a/ql/src/test/results/clientpositive/table_access_keys_stats.q.out +++ b/ql/src/test/results/clientpositive/table_access_keys_stats.q.out @@ -509,7 +509,7 @@ Keys:val,key Table:default@t2 Keys:key -Operator:GBY_16 +Operator:GBY_17 Table:default@t3 Keys:val
