http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/mapjoin47.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mapjoin47.q.out b/ql/src/test/results/clientpositive/mapjoin47.q.out index d3e61f8..dadac0d 100644 --- a/ql/src/test/results/clientpositive/mapjoin47.q.out +++ b/ql/src/test/results/clientpositive/mapjoin47.q.out @@ -385,8 +385,8 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -400,8 +400,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -409,19 +409,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - residual filter predicates: {((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0D AND 102.0D or UDFToDouble(_col3) BETWEEN 100.0D AND 102.0D)} - Statistics: Num rows: 9026 Data size: 173876 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 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {((_col0 = _col3) or _col2 or _col5)} + Statistics: Num rows: 12500 Data size: 240800 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: 12500 Data size: 240800 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 @@ -501,8 +505,8 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -516,8 +520,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -525,19 +529,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - residual filter predicates: {((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D)} {((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {((_col2 + _col5) >= 100.0D)} {((_col2 + _col5) <= 102.0D)} Statistics: Num rows: 1388 Data size: 26738 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: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1388 Data size: 26738 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 @@ -611,8 +619,8 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -626,8 +634,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -635,19 +643,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - residual filter predicates: {(((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D) or ((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D))} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {(((_col2 + _col5) >= 100.0D) or ((_col2 + _col5) <= 102.0D))} Statistics: Num rows: 8332 Data size: 160507 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: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 8332 Data size: 160507 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 @@ -723,8 +735,8 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -738,8 +750,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -747,19 +759,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - residual filter predicates: {(struct(UDFToDouble(_col0),UDFToDouble(_col2))) IN (const struct(100.0D,100.0D), const struct(101.0D,101.0D), const struct(102.0D,102.0D))} - Statistics: Num rows: 6250 Data size: 120400 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 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {(struct(_col2,_col5)) IN (const struct(100.0D,100.0D), const struct(101.0D,101.0D), const struct(102.0D,102.0D))} + Statistics: Num rows: 9375 Data size: 180600 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: 9375 Data size: 180600 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 @@ -840,8 +856,8 @@ STAGE PLANS: alias: a Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -855,8 +871,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -864,7 +880,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -872,11 +888,11 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) >= 100.0D)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + residual filter predicates: {((_col7 + _col2) >= 100.0D)} Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col2 (type: string), _col3 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE Limit @@ -981,8 +997,8 @@ STAGE PLANS: alias: b Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -996,8 +1012,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -1005,7 +1021,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -1013,19 +1029,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + residual filter predicates: {((_col7 + _col2) <= 102.0D)} Statistics: Num rows: 4583 Data size: 88285 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: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 4583 Data size: 88285 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 @@ -1064,7 +1084,7 @@ POSTHOOK: Input: default@src1 4 val_4 NULL NULL 66 val_66 35 val_35 NULL NULL 66 val_66 12 val_12 NULL NULL 66 val_66 -Warning: Map Join MAPJOIN[26][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Stage-7:MAPRED' is a cross product PREHOOK: query: EXPLAIN SELECT * FROM src @@ -1098,17 +1118,17 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:a + $hdt$_0:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:a + $hdt$_0:$hdt$_1:a TableScan alias: a Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -1122,8 +1142,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -1131,15 +1151,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {((_col5 + _col2) >= 100.0D)} Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1241,7 +1265,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[26][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Stage-7:MAPRED' is a cross product PREHOOK: query: SELECT * FROM src JOIN src1 a ON (a.key+src.key >= 100) @@ -1312,8 +1336,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -1324,8 +1348,8 @@ STAGE PLANS: alias: b Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -1348,7 +1372,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -1356,19 +1380,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + residual filter predicates: {((_col7 + _col2) <= 102.0D)} Statistics: Num rows: 4583 Data size: 88285 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: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 4583 Data size: 88285 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 @@ -1397,7 +1425,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 #### A masked pattern was here #### -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: EXPLAIN SELECT * FROM src @@ -1427,17 +1455,17 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:a + $hdt$_0:$hdt$_1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:a + $hdt$_0:$hdt$_1:a TableScan alias: a Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -1464,8 +1492,8 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -1473,15 +1501,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {((_col5 + _col2) >= 100.0D)} Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1510,7 +1542,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT * FROM src JOIN src1 a ON (a.key+src.key >= 100) @@ -1574,15 +1606,15 @@ 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: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string), _col2 (type: double) TableScan alias: a Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1603,7 +1635,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1624,8 +1656,8 @@ STAGE PLANS: alias: b Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -1642,19 +1674,23 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + residual filter predicates: {((_col7 + _col2) <= 102.0D)} Statistics: Num rows: 4583 Data size: 88285 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: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 4583 Data size: 88285 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 @@ -1727,10 +1763,10 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:t3 + $hdt$_0:t5 Fetch Operator limit: -1 - $hdt$_1:t5 + $hdt$_1:t3 Fetch Operator limit: -1 $hdt$_2:t4 @@ -1740,13 +1776,13 @@ STAGE PLANS: Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:t3 + $hdt$_0:t5 TableScan - alias: t3 + alias: t5 Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string), (c_int = 42) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -1754,9 +1790,9 @@ STAGE PLANS: 1 2 3 - $hdt$_1:t5 + $hdt$_1:t3 TableScan - alias: t5 + alias: t3 Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) @@ -1823,11 +1859,11 @@ STAGE PLANS: 1 2 3 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - residual filter predicates: {((_col6 = _col24) or ((_col28 = _col16) and (_col8 = 42)))} {((_col12 = _col24) or ((_col27 = _col15) and (_col13 = _col25)))} {((_col0 = _col24) or ((_col1 = _col25) and (_col26 = _col20)))} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30 + residual filter predicates: {((_col0 = _col25) or ((_col29 = _col17) and _col6))} {((_col13 = _col25) or ((_col28 = _col16) and (_col14 = _col26)))} {((_col7 = _col25) or ((_col8 = _col26) and (_col27 = _col21)))} Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col18 (type: string), _col19 (type: string), _col20 (type: int), _col21 (type: float), _col22 (type: boolean), _col23 (type: string), _col24 (type: string), _col25 (type: string), _col26 (type: int), _col27 (type: float), _col28 (type: boolean), _col29 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: float), _col16 (type: boolean), _col17 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) + expressions: _col19 (type: string), _col20 (type: string), _col21 (type: int), _col22 (type: float), _col23 (type: boolean), _col24 (type: string), _col25 (type: string), _col26 (type: string), _col27 (type: int), _col28 (type: float), _col29 (type: boolean), _col30 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: float), _col11 (type: boolean), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: int), _col16 (type: float), _col17 (type: boolean), _col18 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE Limit
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/masking_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/masking_1.q.out b/ql/src/test/results/clientpositive/masking_1.q.out index 95ed32a..ec83e0c 100644 --- a/ql/src/test/results/clientpositive/masking_1.q.out +++ b/ql/src/test/results/clientpositive/masking_1.q.out @@ -259,13 +259,13 @@ STAGE PLANS: predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), reverse(value) (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int), reverse(value) (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col2 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col2 (type: double) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan @@ -276,13 +276,13 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col4 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col4 (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: @@ -290,17 +290,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + 0 _col2 (type: double) + 1 _col4 (type: double) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2200 Data size: 23372 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: 2200 Data size: 23372 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 http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/masking_12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/masking_12.q.out b/ql/src/test/results/clientpositive/masking_12.q.out index 21bfd07..9ecd981 100644 --- a/ql/src/test/results/clientpositive/masking_12.q.out +++ b/ql/src/test/results/clientpositive/masking_12.q.out @@ -162,12 +162,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -180,20 +184,20 @@ 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: 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: string) TableScan 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: @@ -201,21 +205,25 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1 + 0 _col1 (type: double) + 1 _col1 (type: double) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: int) - mode: hash + Select Operator + expressions: _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + keys: _col0 (type: string), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce
