http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out index 98789d7..ddb436b 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out @@ -187,25 +187,28 @@ STAGE PLANS: alias: test1_n5 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_1 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {_col0 BETWEEN 100 AND 102} + 0 {_col3} 1 keys: 0 _col1 (type: int) 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -283,7 +286,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {_col0 BETWEEN 100 AND 102} + 0 {_col3} 1 keys: 0 @@ -296,27 +299,31 @@ STAGE PLANS: alias: test1_n5 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_1 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {_col0 BETWEEN 100 AND 102} + 0 {_col3} 1 keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized Local Work: Map Reduce Local Work @@ -461,7 +468,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {_col0 BETWEEN 100 AND 102} + 0 {_col3} 1 keys: 0 @@ -474,27 +481,31 @@ STAGE PLANS: alias: test1_n5 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_1 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {_col0 BETWEEN 100 AND 102} + 0 {_col3} 1 keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized Local Work: Map Reduce Local Work @@ -586,8 +597,8 @@ STAGE PLANS: alias: test1_n5 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_1 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -595,16 +606,20 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + residual filter predicates: {((_col1 = _col5) or _col3 or _col4 BETWEEN 100 AND 102)} Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -698,8 +713,8 @@ STAGE PLANS: alias: test1_n5 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_1 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -707,16 +722,20 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + residual filter predicates: {((_col1 = _col5) or _col3)} Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -893,8 +912,8 @@ STAGE PLANS: alias: test1_n5 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_1 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: @@ -902,14 +921,17 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + residual filter predicates: {(_col3 or _col4 BETWEEN 100 AND 102)} + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -996,8 +1018,8 @@ STAGE PLANS: alias: test2_n3 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_2 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_2 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -1005,16 +1027,20 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col6)} Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -1215,8 +1241,8 @@ STAGE PLANS: alias: test2_n3 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_2 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_2 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -1224,16 +1250,20 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + residual filter predicates: {((_col1 = _col4) or _col6)} Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -1302,8 +1332,8 @@ STAGE PLANS: alias: test2_n3 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_2 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_2 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: @@ -1311,14 +1341,17 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col6)} + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out index 42940d9..0276595 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out @@ -404,8 +404,8 @@ STAGE PLANS: alias: test2_n5 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_2 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_2 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -419,8 +419,8 @@ STAGE PLANS: alias: test1_n8 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int), col_1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: int), col_1 (type: string), key BETWEEN 100 AND 102 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -428,19 +428,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + residual filter predicates: {((_col1 = _col5) or _col3 or _col7)} Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/auto_join13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join13.q.out b/ql/src/test/results/clientpositive/spark/auto_join13.q.out index bade284..0a0bdd3 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join13.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join13.q.out @@ -64,13 +64,13 @@ STAGE PLANS: predicate: (UDFToDouble(key) < 200.0D) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 1 _col0 (type: double) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -109,7 +109,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 1 _col0 (type: double) outputColumnNames: _col1, _col2 input vertices: 1 Map 4 http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/auto_join19.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join19.q.out b/ql/src/test/results/clientpositive/spark/auto_join19.q.out index b0d2552..9ab1b8b 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join19.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join19.q.out @@ -85,12 +85,12 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col4 + outputColumnNames: _col0, _col2 input vertices: 1 Map 2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) + expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/auto_join2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join2.q.out b/ql/src/test/results/clientpositive/spark/auto_join2.q.out index 32026e4..6aeadb5 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join2.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join2.q.out @@ -39,8 +39,8 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: @@ -59,13 +59,13 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) + expressions: value (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 (_col1 + _col3) (type: double) + 1 _col1 (type: double) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -84,8 +84,8 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -93,7 +93,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col3 input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -101,14 +101,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col3 + 0 (_col1 + _col3) (type: double) + 1 _col1 (type: double) + outputColumnNames: _col0, _col4 input vertices: 1 Map 3 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) + expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/auto_join32.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join32.q.out b/ql/src/test/results/clientpositive/spark/auto_join32.q.out index ed3dfbe..7f7b5e9 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join32.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join32.q.out @@ -499,10 +499,10 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3 + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: string), _col3 (type: string) + keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/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 ce0e92d..e14fb06 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join9.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join9.q.out @@ -77,12 +77,12 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col4 + outputColumnNames: _col0, _col2 input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) + expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/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 59cd394..b64241c 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 @@ -81,13 +81,13 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean) Execution mode: vectorized Map 4 Map Operator Tree: @@ -95,13 +95,13 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -109,15 +109,15 @@ STAGE PLANS: condition map: Full Outer Join 0 to 1 filter predicates: - 0 {(VALUE._col0 > 40)} {(VALUE._col1 > 50)} {(VALUE._col0 = VALUE._col1)} - 1 {(VALUE._col0 > 40)} {(VALUE._col1 > 50)} {(VALUE._col0 = VALUE._col1)} + 0 {VALUE._col2} {VALUE._col3} {VALUE._col4} + 1 {VALUE._col2} {VALUE._col3} {VALUE._col4} keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col5, _col6 Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3) (type: int) + expressions: hash(_col0,_col1,_col5,_col6) (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -331,15 +331,15 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: _col1 (type: int), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean) Execution mode: vectorized Map 4 Map Operator Tree: @@ -347,15 +347,15 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col0 (type: int), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -363,15 +363,15 @@ STAGE PLANS: condition map: Full Outer Join 0 to 1 filter predicates: - 0 {(KEY.reducesinkkey0 > 40)} {(VALUE._col0 > 50)} {(KEY.reducesinkkey0 = VALUE._col0)} - 1 {(VALUE._col0 > 40)} {(KEY.reducesinkkey0 > 50)} {(VALUE._col0 = KEY.reducesinkkey0)} + 0 {VALUE._col1} {VALUE._col2} {VALUE._col3} + 1 {VALUE._col1} {VALUE._col2} {VALUE._col3} keys: 0 _col0 (type: int) 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col5, _col6 Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3) (type: int) + expressions: hash(_col0,_col1,_col5,_col6) (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -763,15 +763,15 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: _col1 (type: int), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean) Execution mode: vectorized Map 4 Map Operator Tree: @@ -779,15 +779,15 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col0 (type: int), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -795,15 +795,15 @@ STAGE PLANS: condition map: Full Outer Join 0 to 1 filter predicates: - 0 {(KEY.reducesinkkey0 > 40)} {(VALUE._col0 > 50)} {(KEY.reducesinkkey0 = VALUE._col0)} - 1 {(VALUE._col0 > 40)} {(KEY.reducesinkkey0 > 50)} {(VALUE._col0 = KEY.reducesinkkey0)} + 0 {VALUE._col1} {VALUE._col2} {VALUE._col3} + 1 {VALUE._col1} {VALUE._col2} {VALUE._col3} keys: 0 _col0 (type: int) 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col5, _col6 Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3) (type: int) + expressions: hash(_col0,_col1,_col5,_col6) (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 242 Basic stats: COMPLETE Column stats: NONE Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out index e181ff2..a6d0922 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out @@ -52,13 +52,13 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 (_col1 + _col3) (type: double) + 1 _col1 (type: double) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -79,14 +79,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) 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: double) Execution mode: vectorized Map 3 Map Operator Tree: @@ -98,14 +99,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) 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: double) Execution mode: vectorized Reducer 2 Local Work: @@ -117,25 +119,29 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 + 0 (_col1 + _col3) (type: double) + 1 _col1 (type: double) + outputColumnNames: _col0, _col2, _col4 input vertices: 1 Map 4 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col2 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -211,14 +217,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - 2 UDFToDouble(_col0) (type: double) + 0 (_col1 + _col3) (type: double) + 1 _col0 (type: double) + 2 _col1 (type: double) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -232,14 +238,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - 2 UDFToDouble(_col0) (type: double) + 0 (_col1 + _col3) (type: double) + 1 _col0 (type: double) + 2 _col1 (type: double) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -260,14 +266,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) 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: double) Execution mode: vectorized Map 3 Map Operator Tree: @@ -279,14 +286,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) 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: double) Execution mode: vectorized Reducer 2 Local Work: @@ -298,23 +306,23 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - 2 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col3 + 0 (_col1 + _col3) (type: double) + 1 _col0 (type: double) + 2 _col1 (type: double) + outputColumnNames: _col0, _col2, _col5 input vertices: 1 Map 4 2 Map 5 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + expressions: _col0 (type: string), _col2 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out index 6fe4b10..fbcc489 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out @@ -45,8 +45,8 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: @@ -65,8 +65,8 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: @@ -90,8 +90,8 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -99,7 +99,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 2 Statistics: Num rows: 500 Data size: 155812 Basic stats: COMPLETE Column stats: NONE @@ -109,15 +109,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 1 Map 3 Statistics: Num rows: 550 Data size: 171393 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(_col2) + UDFToDouble(_col0)) = UDFToDouble(_col1)) (type: boolean) + predicate: ((_col5 + _col1) = _col3) (type: boolean) Statistics: Num rows: 275 Data size: 85696 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string) + expressions: _col4 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 85696 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -206,8 +206,8 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: @@ -226,14 +226,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - 2 UDFToDouble(_col0) (type: double) + 0 (_col1 + _col3) (type: double) + 1 _col0 (type: double) + 2 _col1 (type: double) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -247,14 +247,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - 2 UDFToDouble(_col0) (type: double) + 0 (_col1 + _col3) (type: double) + 1 _col0 (type: double) + 2 _col1 (type: double) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -273,8 +273,8 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -282,7 +282,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -291,16 +291,16 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - 2 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col3 + 0 (_col1 + _col3) (type: double) + 1 _col0 (type: double) + 2 _col1 (type: double) + outputColumnNames: _col0, _col2, _col5 input vertices: 1 Map 3 2 Map 4 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + expressions: _col0 (type: string), _col2 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out index 7491c7b..6fe72d7 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out @@ -558,13 +558,13 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 5 @@ -577,13 +577,13 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col1 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col1 (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized @@ -612,8 +612,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 _col0 (type: double) + 1 _col1 (type: double) outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -1071,13 +1071,13 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 5 @@ -1090,13 +1090,13 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col1 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col1 (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized @@ -1125,8 +1125,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 _col0 (type: double) + 1 _col1 (type: double) outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out index 80eefef..b951591 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out @@ -130,7 +130,7 @@ OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_n19` WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_2_n16` WHERE `ds` = '2008-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: @@ -461,7 +461,7 @@ OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_n19` WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_2_n16` WHERE `ds` = '2008-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out index 6f25359..7752b4c 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out @@ -114,7 +114,7 @@ OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_n12` WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_2_n10` WHERE `ds` = '2008-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: @@ -445,7 +445,7 @@ OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_n12` WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_2_n10` WHERE `ds` = '2008-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out index e6bc741..fe81ef5 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out @@ -114,7 +114,7 @@ OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_n4` WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_2_n3` WHERE `ds` = '2008-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: @@ -445,7 +445,7 @@ OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_n4` WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcbucket_mapjoin_part_2_n3` WHERE `ds` = '2008-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out index f072ab0..339fe44 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out @@ -74,7 +74,7 @@ POSTHOOK: Input: default@tbl1_n0 POSTHOOK: Input: default@tbl2_n0 POSTHOOK: Input: default@tbl3 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value` AS `val1`, `t4`.`value` AS `val2`, `t2`.`value` AS `val3` +OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t4`.`value` AS `value0`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`tbl1_n0` WHERE `key` IS NOT NULL AND `value` IS NOT NULL) AS `t0` @@ -474,7 +474,7 @@ POSTHOOK: Input: default@tbl1_n0 POSTHOOK: Input: default@tbl2_n0 POSTHOOK: Input: default@tbl3 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value` AS `val1`, `t4`.`value` AS `val2`, `t2`.`value` AS `val3` +OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t4`.`value` AS `value0`, `t2`.`value` AS `value1` FROM (SELECT `key`, `value` FROM `default`.`tbl1_n0` WHERE `key` IS NOT NULL AND `value` IS NOT NULL) AS `t0`
