http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out index 5560226..18d79d3 100644 --- a/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/spark/join18_multi_distinct.q.out @@ -50,11 +50,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 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 @@ -71,11 +71,11 @@ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join29.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join29.q.out b/ql/src/test/results/clientpositive/spark/join29.q.out index 0b4284c..9479dd1 100644 --- a/ql/src/test/results/clientpositive/spark/join29.q.out +++ b/ql/src/test/results/clientpositive/spark/join29.q.out @@ -36,10 +36,10 @@ STAGE PLANS: Stage: Stage-3 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 2) + Reducer 4 <- Map 3 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 3 Map Operator Tree: TableScan alias: x @@ -47,19 +47,23 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 2 + 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) + Reducer 4 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -77,10 +81,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 4 <- Map 3 (GROUP, 2) + Reducer 2 <- Map 1 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 3 + Map 1 Map Operator Tree: TableScan alias: y @@ -88,19 +92,23 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string) + outputColumnNames: _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) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 4 + 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) + Reducer 2 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -116,12 +124,12 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col1, _col2, _col3 input vertices: - 0 Reducer 2 + 1 Reducer 4 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col3) (type: int) + expressions: _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join31.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join31.q.out b/ql/src/test/results/clientpositive/spark/join31.q.out index a52a8b6..108a1ea 100644 --- a/ql/src/test/results/clientpositive/spark/join31.q.out +++ b/ql/src/test/results/clientpositive/spark/join31.q.out @@ -38,10 +38,10 @@ STAGE PLANS: Stage: Stage-3 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 2) + Reducer 5 <- Map 4 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 4 Map Operator Tree: TableScan alias: x @@ -49,45 +49,42 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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) + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 2 + 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 5 Local Work: Map Reduce Local Work 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: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Stage: Stage-1 Spark Edges: - Reducer 4 <- Map 3 (GROUP, 2) - Reducer 5 <- Reducer 4 (GROUP, 2) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 3 + Map 1 Map Operator Tree: TableScan alias: y @@ -95,41 +92,42 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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) + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 4 + 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 Local Work: Map Reduce Local Work 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 + input vertices: + 1 Reducer 5 + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string) outputColumnNames: _col0 - input vertices: - 0 Reducer 2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) @@ -143,7 +141,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Reducer 5 + Reducer 3 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -195,7 +193,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, (src)y.null, ] +POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, ] POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join34.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join34.q.out b/ql/src/test/results/clientpositive/spark/join34.q.out index 8a1ba8d..09b8b6b 100644 --- a/ql/src/test/results/clientpositive/spark/join34.q.out +++ b/ql/src/test/results/clientpositive/spark/join34.q.out @@ -158,7 +158,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - 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), value (type: string) @@ -224,12 +224,12 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: x1 + alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - 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) @@ -291,7 +291,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [x1] + /src [x] Map 4 Map Operator Tree: TableScan @@ -300,16 +300,20 @@ STAGE PLANS: 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 - value expressions: value (type: string) - auto parallelism: false + predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) + Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 8 Data size: 61 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: @@ -367,7 +371,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 key (type: string) + 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -452,7 +456,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), (src)x1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), (src)x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join35.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join35.q.out b/ql/src/test/results/clientpositive/spark/join35.q.out index 1ed9c90..e84c860 100644 --- a/ql/src/test/results/clientpositive/spark/join35.q.out +++ b/ql/src/test/results/clientpositive/spark/join35.q.out @@ -168,22 +168,26 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - 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 - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -236,27 +240,31 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: x1 + alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - 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 - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -305,7 +313,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [x1] + /src [x] Map 6 Map Operator Tree: TableScan @@ -314,16 +322,20 @@ STAGE PLANS: 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 - value expressions: value (type: string) - auto parallelism: false + predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) + Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 8 Data size: 61 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: @@ -398,7 +410,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 key (type: string) + 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -500,7 +512,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.null, (src)x1.null, ] +POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.null, (src)x.null, ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join4.q.out b/ql/src/test/results/clientpositive/spark/join4.q.out index eddcf07..55b3a18 100644 --- a/ql/src/test/results/clientpositive/spark/join4.q.out +++ b/ql/src/test/results/clientpositive/spark/join4.q.out @@ -58,7 +58,7 @@ 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)) (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 Select Operator expressions: key (type: string), value (type: string) @@ -73,20 +73,20 @@ STAGE PLANS: Map 3 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)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: @@ -158,8 +158,8 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join40.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join40.q.out b/ql/src/test/results/clientpositive/spark/join40.q.out index 08695ff..02c11cd 100644 --- a/ql/src/test/results/clientpositive/spark/join40.q.out +++ b/ql/src/test/results/clientpositive/spark/join40.q.out @@ -22,10 +22,25 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: src + 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: _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) + Map 3 + Map Operator Tree: + TableScan + 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) @@ -37,38 +52,23 @@ STAGE PLANS: 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) - Map 3 - Map Operator Tree: - 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) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 key (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - 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) - outputColumnNames: _col0, _col1, _col2, _col3 + File Output Operator + compressed: false Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -677,37 +677,45 @@ 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) Map 3 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) + 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 Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col6 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _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 @@ -3762,32 +3770,40 @@ 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 Map 4 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 Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 key (type: string) - 1 key (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join5.q.out b/ql/src/test/results/clientpositive/spark/join5.q.out index d645e89..1914ad0 100644 --- a/ql/src/test/results/clientpositive/spark/join5.q.out +++ b/ql/src/test/results/clientpositive/spark/join5.q.out @@ -58,7 +58,7 @@ 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)) (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 Select Operator expressions: key (type: string), value (type: string) @@ -73,33 +73,33 @@ STAGE PLANS: Map 3 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)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: - Right Outer Join0 to 1 + Left Outer Join0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(_col2) (type: int), _col3 (type: string), UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -158,8 +158,8 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join6.q.out b/ql/src/test/results/clientpositive/spark/join6.q.out index 4770770..5f2a85a 100644 --- a/ql/src/test/results/clientpositive/spark/join6.q.out +++ b/ql/src/test/results/clientpositive/spark/join6.q.out @@ -58,7 +58,7 @@ 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)) (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 Select Operator expressions: key (type: string), value (type: string) @@ -73,10 +73,10 @@ STAGE PLANS: Map 3 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)) (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 Select Operator expressions: key (type: string), value (type: string) @@ -158,8 +158,8 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join8.q.out b/ql/src/test/results/clientpositive/spark/join8.q.out index d242c10..e3fac82 100644 --- a/ql/src/test/results/clientpositive/spark/join8.q.out +++ b/ql/src/test/results/clientpositive/spark/join8.q.out @@ -58,7 +58,7 @@ 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) + predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -73,20 +73,20 @@ STAGE PLANS: Map 3 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) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: @@ -102,7 +102,7 @@ STAGE PLANS: predicate: _col2 is null (type: boolean) Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(null) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -161,8 +161,8 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join9.q.out b/ql/src/test/results/clientpositive/spark/join9.q.out index 92f0237..c7440da 100644 --- a/ql/src/test/results/clientpositive/spark/join9.q.out +++ b/ql/src/test/results/clientpositive/spark/join9.q.out @@ -94,13 +94,17 @@ 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -162,14 +166,18 @@ 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), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -226,12 +234,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col8 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col4 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col8 (type: string) + expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out b/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out index dabdcb8..f34153d 100644 --- a/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out +++ b/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[4][tables = [p1, p2]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select p1.p_name, p2.p_name from part p1 , part p2 PREHOOK: type: QUERY @@ -21,19 +21,27 @@ STAGE PLANS: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: p_name (type: string) + outputColumnNames: _col0 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: p_name (type: string) + outputColumnNames: _col0 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: p_name (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -42,19 +50,15 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col1, _col13 + outputColumnNames: _col0, _col1 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col13 (type: string) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/join_vc.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join_vc.q.out b/ql/src/test/results/clientpositive/spark/join_vc.q.out index 8b25d4f..27265a6 100644 --- a/ql/src/test/results/clientpositive/spark/join_vc.q.out +++ b/ql/src/test/results/clientpositive/spark/join_vc.q.out @@ -157,39 +157,47 @@ STAGE PLANS: 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 + 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) Map 4 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) + outputColumnNames: _col0 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 Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col7 + 0 _col0 (type: string) + 1 _col0 (type: string) + 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 Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out b/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out index e95d2ab..c6f9039 100644 --- a/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out +++ b/ql/src/test/results/clientpositive/spark/limit_partition_metadataonly.q.out @@ -555,10 +555,10 @@ 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 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out b/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out index 1efa9e7..7101beb 100644 --- a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/spark/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 @@ -289,12 +289,12 @@ 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 @@ -384,10 +384,10 @@ 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 @@ -564,10 +564,10 @@ 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 - keys: ctinyint (type: tinyint), cdouble (type: double) + keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -780,11 +780,11 @@ 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 @@ -883,10 +883,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1) - Reducer 5 <- Map 4 (GROUP, 2) - Reducer 6 <- Reducer 5 (GROUP, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -896,11 +896,11 @@ 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(1) - 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 @@ -911,18 +911,18 @@ 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 + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - 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 @@ -942,18 +942,32 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + 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: Join Operator condition map: @@ -961,19 +975,23 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 4 + Select Operator + 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 - File Output Operator - compressed: false + Limit + Number of rows: 4 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 5 + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -982,30 +1000,16 @@ 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 + Number of rows: 2 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + 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: 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) Stage: Stage-0 @@ -1039,16 +1043,16 @@ 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 @@ -1293,15 +1297,15 @@ 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 - value expressions: key (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/load_dyn_part13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/load_dyn_part13.q.out b/ql/src/test/results/clientpositive/spark/load_dyn_part13.q.out index 3285ad9..4480310 100644 --- a/ql/src/test/results/clientpositive/spark/load_dyn_part13.q.out +++ b/ql/src/test/results/clientpositive/spark/load_dyn_part13.q.out @@ -72,7 +72,7 @@ STAGE PLANS: alias: src 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), value (type: string), '22' (type: string) @@ -92,7 +92,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 20) and (key < 40)) (type: boolean) + predicate: ((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 40.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '33' (type: string)