http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/auto_join27.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join27.q.out b/ql/src/test/results/clientpositive/spark/auto_join27.q.out index 1722837..43313e0 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join27.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join27.q.out @@ -41,7 +41,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 200) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -58,25 +58,29 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 200) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: string), value (type: string) - mode: hash + Select Operator + expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 200) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string)
http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/auto_join4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join4.q.out b/ql/src/test/results/clientpositive/spark/auto_join4.q.out index 3366f75..7cf582c 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join4.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join4.q.out @@ -50,15 +50,15 @@ STAGE PLANS: Map 2 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 Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -76,7 +76,7 @@ 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) @@ -154,8 +154,8 @@ 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 sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) 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/auto_join5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join5.q.out b/ql/src/test/results/clientpositive/spark/auto_join5.q.out index b6d8798..08e9ae6 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join5.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join5.q.out @@ -47,18 +47,18 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 1 + Map 2 Map Operator Tree: TableScan 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) - 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 Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -70,13 +70,13 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 2 + Map 1 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) @@ -84,16 +84,16 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Map 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 input vertices: - 0 Map 1 + 1 Map 2 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 @@ -154,8 +154,8 @@ 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 sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) 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/auto_join6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join6.q.out b/ql/src/test/results/clientpositive/spark/auto_join6.q.out index 2ca2674..5b7e904 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join6.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join6.q.out @@ -54,7 +54,7 @@ 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) @@ -69,10 +69,10 @@ 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) @@ -154,8 +154,8 @@ 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 sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) 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/auto_join8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join8.q.out b/ql/src/test/results/clientpositive/spark/auto_join8.q.out index e0df9a2..e77817a 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join8.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join8.q.out @@ -50,15 +50,15 @@ STAGE PLANS: Map 2 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 Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -76,7 +76,7 @@ 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) @@ -96,7 +96,7 @@ 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 @@ -157,8 +157,8 @@ 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 sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) 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/auto_join9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join9.q.out b/ql/src/test/results/clientpositive/spark/auto_join9.q.out index 6daf348..568891b 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join9.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join9.q.out @@ -33,10 +33,14 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 key (type: string) - 1 key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) Local Work: Map Reduce Local Work @@ -52,28 +56,32 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col8 - input vertices: - 1 Map 2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col8 (type: string) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col4 + input vertices: + 1 Map 2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Local Work: Map Reduce Local Work http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out b/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out index 8934433..b6b89c1 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out @@ -44,7 +44,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 -Warning: Shuffle Join JOIN[4][tables = [a, b]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -330,7 +330,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Shuffle Join JOIN[10][tables = [a, b]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out b/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out index 1f37c75..4b809ce 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[11][bigTable=a] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -24,7 +24,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 13630578 -Warning: Map Join MAPJOIN[11][bigTable=a] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -34,7 +34,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 13630578 -Warning: Map Join MAPJOIN[11][bigTable=b] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out index c3d5225..72f60d0 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out @@ -24,33 +24,41 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) 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) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 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/cbo_subq_in.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/cbo_subq_in.q.out b/ql/src/test/results/clientpositive/spark/cbo_subq_in.q.out index c1f3de7..f6bfad2 100644 --- a/ql/src/test/results/clientpositive/spark/cbo_subq_in.q.out +++ b/ql/src/test/results/clientpositive/spark/cbo_subq_in.q.out @@ -69,6 +69,7 @@ select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) + order by p.p_partkey PREHOOK: type: QUERY PREHOOK: Input: default@lineitem #### A masked pattern was here #### @@ -77,6 +78,7 @@ select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) + order by p.p_partkey POSTHOOK: type: QUERY POSTHOOK: Input: default@lineitem #### A masked pattern was here #### http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out b/ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out index 602de6e..665bfce 100644 --- a/ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out +++ b/ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out @@ -23,39 +23,45 @@ STAGE PLANS: alias: src1 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '100' (type: string) - sort order: + - Map-reduce partition columns: '100' (type: string) + Select Operator + expressions: value (type: string) + outputColumnNames: _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: '100' (type: string) + sort order: + + Map-reduce partition columns: '100' (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 = 100) (type: boolean) + predicate: (UDFToDouble(key) = 100.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '100' (type: string) - sort order: + - Map-reduce partition columns: '100' (type: string) + Select Operator Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator + key expressions: '100' (type: string) + sort order: + + Map-reduce partition columns: '100' (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: _col6 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '100' (type: string), 101.0 (type: double), _col6 (type: string) + expressions: '100' (type: string), 101.0 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -115,53 +121,57 @@ STAGE PLANS: alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_orderkey is not null and l_linenumber is not null) and (l_linenumber = 1)) (type: boolean) - Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: l_orderkey (type: int), l_linenumber (type: int) - sort order: ++ - Map-reduce partition columns: l_orderkey (type: int), l_linenumber (type: int) - Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE - value expressions: l_partkey (type: int), l_suppkey (type: int) + predicate: ((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), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col3 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col3 (type: int) + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int) Map 3 Map Operator Tree: TableScan - alias: lineitem + alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((l_shipmode = 'AIR') and l_orderkey is not null) and l_linenumber is not null) and (l_linenumber = 1)) (type: boolean) - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + predicate: (((l_shipmode = 'AIR') and l_orderkey is not null) and l_linenumber is not null) (type: boolean) + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: l_orderkey (type: int), 1 (type: int) + expressions: l_orderkey (type: int), l_linenumber (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 l_orderkey (type: int), l_linenumber (type: int) + 0 _col0 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 13 Data size: 1582 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1582 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 1582 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3298 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/330c31ae/ql/src/test/results/clientpositive/spark/count.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/count.q.out b/ql/src/test/results/clientpositive/spark/count.q.out index cb9eda5..b2e9ffb 100644 --- a/ql/src/test/results/clientpositive/spark/count.q.out +++ b/ql/src/test/results/clientpositive/spark/count.q.out @@ -53,11 +53,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) - keys: a (type: int), b (type: int), c (type: int) + aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) + keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -188,14 +188,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: a, b, c, d + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: a (type: int), b (type: int), c (type: int) + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ - Map-reduce partition columns: a (type: int) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: d (type: int) + value expressions: _col3 (type: int) Reducer 2 Reduce Operator Tree: Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/cross_join.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/cross_join.q.out b/ql/src/test/results/clientpositive/spark/cross_join.q.out index bb25e21..2fb6b21 100644 --- a/ql/src/test/results/clientpositive/spark/cross_join.q.out +++ b/ql/src/test/results/clientpositive/spark/cross_join.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[4][tables = [src, src2]] 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: -- current explain select src.key from src join src src2 PREHOOK: type: QUERY @@ -21,18 +21,24 @@ STAGE PLANS: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Map 3 Map Operator Tree: TableScan - alias: src2 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reducer 2 Reduce Operator Tree: Join Operator @@ -57,7 +63,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[4][tables = [src, src2]] 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: -- ansi cross join explain select src.key from src cross join src src2 PREHOOK: type: QUERY @@ -80,18 +86,24 @@ STAGE PLANS: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) Map 3 Map Operator Tree: TableScan - alias: src2 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reducer 2 Reduce Operator Tree: Join Operator @@ -141,32 +153,40 @@ 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 3 Map Operator Tree: TableScan - alias: src2 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE 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) outputColumnNames: _col0 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/cross_product_check_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out b/ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out index ff58910..c228f0b 100644 --- a/ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out +++ b/ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Shuffle Join JOIN[4][tables = [a, b]] 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 * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -49,19 +49,27 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Map 3 Map Operator Tree: TableScan alias: b Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -70,19 +78,15 @@ STAGE PLANS: keys: 0 1 - 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 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out b/ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out index 6c4e659..ab062ad 100644 --- a/ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out +++ b/ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Map Join MAPJOIN[7][bigTable=a] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -48,10 +48,14 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 Local Work: Map Reduce Local Work @@ -64,19 +68,19 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col5, _col6 - input vertices: - 1 Map 2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/groupby1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby1.q.out b/ql/src/test/results/clientpositive/spark/groupby1.q.out index f661a62..8f60691 100644 --- a/ql/src/test/results/clientpositive/spark/groupby1.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby1.q.out @@ -35,15 +35,15 @@ 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: key (type: string), substr(value, 5) (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: key (type: string) + key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: substr(value, 5) (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/groupby4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby4.q.out b/ql/src/test/results/clientpositive/spark/groupby4.q.out index 87d2968..b764466 100644 --- a/ql/src/test/results/clientpositive/spark/groupby4.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby4.q.out @@ -37,11 +37,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: key + expressions: substr(key, 1, 1) (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: substr(key, 1, 1) (type: string) + key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/groupby_complex_types_multi_single_reducer.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby_complex_types_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/spark/groupby_complex_types_multi_single_reducer.q.out index 9fe3b72..65bdf2c 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_complex_types_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_complex_types_multi_single_reducer.q.out @@ -20,13 +20,13 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@DEST2 PREHOOK: query: EXPLAIN FROM SRC -INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 -INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 +INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key) as keyarray, COUNT(1) GROUP BY ARRAY(SRC.key) ORDER BY keyarray limit 10 +INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value) as kvmap, COUNT(1) GROUP BY MAP(SRC.key, SRC.value) ORDER BY kvmap limit 10 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FROM SRC -INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 -INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 +INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key) as keyarray, COUNT(1) GROUP BY ARRAY(SRC.key) ORDER BY keyarray limit 10 +INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value) as kvmap, COUNT(1) GROUP BY MAP(SRC.key, SRC.value) ORDER BY kvmap limit 10 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage @@ -41,8 +41,8 @@ STAGE PLANS: Edges: Reducer 2 <- Map 6 (GROUP, 2) Reducer 4 <- Map 7 (GROUP, 2) - Reducer 3 <- Reducer 2 (GROUP, 1) - Reducer 5 <- Reducer 4 (GROUP, 1) + Reducer 3 <- Reducer 2 (SORT, 1) + Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: Map 6 @@ -95,19 +95,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: array<string>), _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: array<string>) + sort order: + + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: array<string>), VALUE._col1 (type: bigint) + expressions: KEY.reducesinkkey0 (type: array<string>), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE @@ -127,19 +125,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: map<string,string>), _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: map<string,string>) + sort order: + + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reducer 5 Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: map<string,string>), VALUE._col1 (type: bigint) + expressions: KEY.reducesinkkey0 (type: map<string,string>), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE @@ -179,15 +175,15 @@ STAGE PLANS: Stats-Aggr Operator PREHOOK: query: FROM SRC -INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 -INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 +INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key) as keyarray, COUNT(1) GROUP BY ARRAY(SRC.key) ORDER BY keyarray limit 10 +INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value) as kvmap, COUNT(1) GROUP BY MAP(SRC.key, SRC.value) ORDER BY kvmap limit 10 PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@dest1 PREHOOK: Output: default@dest2 POSTHOOK: query: FROM SRC -INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 -INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 +INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key) as keyarray, COUNT(1) GROUP BY ARRAY(SRC.key) ORDER BY keyarray limit 10 +INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value) as kvmap, COUNT(1) GROUP BY MAP(SRC.key, SRC.value) ORDER BY kvmap limit 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 @@ -204,16 +200,16 @@ POSTHOOK: query: SELECT DEST1.* FROM DEST1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 #### A masked pattern was here #### -["118"] 2 -["180"] 1 -["201"] 1 -["202"] 1 -["238"] 2 -["273"] 3 -["282"] 2 -["419"] 1 -["432"] 1 -["467"] 1 +["0"] 3 +["10"] 1 +["100"] 2 +["103"] 2 +["104"] 2 +["105"] 1 +["11"] 1 +["111"] 1 +["113"] 2 +["114"] 1 PREHOOK: query: SELECT DEST2.* FROM DEST2 PREHOOK: type: QUERY PREHOOK: Input: default@dest2 @@ -223,12 +219,12 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@dest2 #### A masked pattern was here #### {"0":"val_0"} 3 -{"138":"val_138"} 4 -{"170":"val_170"} 1 -{"19":"val_19"} 1 -{"222":"val_222"} 1 -{"223":"val_223"} 2 -{"226":"val_226"} 1 -{"489":"val_489"} 4 -{"8":"val_8"} 1 -{"80":"val_80"} 1 +{"10":"val_10"} 1 +{"100":"val_100"} 2 +{"103":"val_103"} 2 +{"104":"val_104"} 2 +{"105":"val_105"} 1 +{"11":"val_11"} 1 +{"111":"val_111"} 1 +{"113":"val_113"} 2 +{"114":"val_114"} 1 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out b/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out index 42513a4..21c88b1 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_cube1.q.out @@ -42,11 +42,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: key, val + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: key (type: string), val (type: string), '0' (type: string) + keys: _col0 (type: string), _col1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -133,11 +133,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: key, val + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: key (type: string), val (type: string), '0' (type: string) + keys: _col0 (type: string), _col1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -223,11 +223,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: key, val + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT val) - keys: key (type: string), '0' (type: string), val (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), '0' (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -302,11 +302,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: key, val + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: key (type: string), val (type: string), '0' (type: string) + keys: _col0 (type: string), _col1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -407,11 +407,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: key, val + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT val) - keys: key (type: string), '0' (type: string), val (type: string) + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), '0' (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/groupby_position.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/groupby_position.q.out b/ql/src/test/results/clientpositive/spark/groupby_position.q.out index 16437d5..50d707d 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_position.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_position.q.out @@ -436,20 +436,24 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key <= 20) (type: boolean) + predicate: (UDFToDouble(key) <= 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - 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 - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator @@ -548,7 +552,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (GROUP, 2) Reducer 6 <- Map 5 (GROUP, 2) Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) Reducer 4 <- Reducer 3 (SORT, 1) @@ -560,55 +564,57 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key > 10) and (key < 20)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(DISTINCT substr(value, 5)) - keys: key (type: string), value (type: string), substr(value, 5) (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Map 5 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 - Group By Operator - keys: key (type: string), value (type: string) - mode: hash + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(DISTINCT KEY._col2:0._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reducer 3 Reduce Operator Tree: Join Operator @@ -617,25 +623,21 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - sort order: --++ - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order: --++ + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reducer 4 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -646,12 +648,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Stage: Stage-0
