Index: ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out (working copy) @@ -62,15 +62,15 @@ Reduce Operator Tree: Group By Operator aggregations: - expr: sum(KEY._col0:2._col0) - expr: avg(KEY._col0:2._col0) + expr: sum(KEY._col0:0._col0) + expr: avg(KEY._col0:0._col0) expr: avg(DISTINCT KEY._col0:0._col0) - expr: max(KEY._col0:2._col0) - expr: min(KEY._col0:2._col0) - expr: std(KEY._col0:2._col0) - expr: stddev_samp(KEY._col0:2._col0) - expr: variance(KEY._col0:2._col0) - expr: var_samp(KEY._col0:2._col0) + expr: max(KEY._col0:0._col0) + expr: min(KEY._col0:0._col0) + expr: std(KEY._col0:0._col0) + expr: stddev_samp(KEY._col0:0._col0) + expr: variance(KEY._col0:0._col0) + expr: var_samp(KEY._col0:0._col0) expr: sum(DISTINCT KEY._col0:1._col0) expr: count(DISTINCT KEY._col0:2._col0) bucketGroup: false @@ -181,34 +181,34 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-11_371_9192473715365716502/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-33-53_226_9120252787207521913/-mr-10000 POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-11_371_9192473715365716502/-mr-10000 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.null, ] +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-33-53_226_9120252787207521913/-mr-10000 +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] 130091.0 260.182 256.10355987055016 98.0 0.0 142.92680950752379 143.06995106518903 20428.07287599999 20469.010897795582 79136.0 309.0 Index: ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out (working copy) @@ -51,7 +51,7 @@ Group By Operator aggregations: expr: count(DISTINCT KEY._col1:0._col0) - expr: sum(KEY._col1:1._col0) + expr: sum(KEY._col1:0._col0) expr: sum(DISTINCT KEY._col1:1._col0) expr: count(VALUE._col0) bucketGroup: false @@ -121,21 +121,21 @@ POSTHOOK: Output: default@dest_g2 POSTHOOK: Lineage: dest_g2.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_g2.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_g2.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_g2.c4 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest_g2.c3 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest_g2.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_g2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest_g2.* FROM dest_g2 PREHOOK: type: QUERY PREHOOK: Input: default@dest_g2 -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-04-17_707_2990757298865083943/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-32-48_837_3420714805170634461/-mr-10000 POSTHOOK: query: SELECT dest_g2.* FROM dest_g2 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_g2 -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-04-17_707_2990757298865083943/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-32-48_837_3420714805170634461/-mr-10000 POSTHOOK: Lineage: dest_g2.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_g2.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_g2.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_g2.c4 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest_g2.c3 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest_g2.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_g2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] 0 1 00.0 0 3 1 71 116414.0 10044 115 Index: ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out (working copy) @@ -141,21 +141,21 @@ POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-03-34_053_4042312084657375262/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-32-18_639_8999476029269552023/-mr-10000 POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-03-34_053_4042312084657375262/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-32-18_639_8999476029269552023/-mr-10000 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] 0 1 00.0 0 3 1 71 116414.0 10044 115 Index: ql/src/test/results/clientpositive/join18_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/join18_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/join18_multi_distinct.q.out (working copy) @@ -84,7 +84,7 @@ expr: count(DISTINCT KEY._col1:1._col0) bucketGroup: false keys: - expr: KEY._col1:1._col0 + expr: KEY._col0 type: string mode: mergepartial outputColumnNames: _col0, _col1, _col2 @@ -246,7 +246,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-06-44_648_893234056742394843/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_22-04-24_444_4240775356684711538/-mr-10000 POSTHOOK: query: SELECT a.key, a.value, b.key, b.value1, b.value2 FROM ( @@ -262,11 +262,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-06-44_648_893234056742394843/-mr-10000 -NULL NULL 1 0 -NULL NULL 1 0 -NULL NULL 1 0 -NULL NULL 1 1 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_22-04-24_444_4240775356684711538/-mr-10000 +NULL NULL 7 1 0 3 NULL NULL NULL 10 1 NULL NULL NULL 100 2 NULL NULL NULL @@ -284,7 +281,7 @@ 120 2 NULL NULL NULL 125 2 NULL NULL NULL 126 1 NULL NULL NULL -128 3 128 0 1 +128 3 128 1 1 129 2 NULL NULL NULL 131 1 NULL NULL NULL 133 1 NULL NULL NULL @@ -294,10 +291,10 @@ 138 4 NULL NULL NULL 143 1 NULL NULL NULL 145 1 NULL NULL NULL -146 2 146 0 1 +146 2 146 1 1 149 2 NULL NULL NULL 15 2 NULL NULL NULL -150 1 150 0 1 +150 1 150 1 1 152 2 NULL NULL NULL 153 1 NULL NULL NULL 155 1 NULL NULL NULL @@ -349,7 +346,7 @@ 207 2 NULL NULL NULL 208 3 NULL NULL NULL 209 2 NULL NULL NULL -213 2 213 0 1 +213 2 213 1 1 214 1 NULL NULL NULL 216 2 NULL NULL NULL 217 2 NULL NULL NULL @@ -358,7 +355,7 @@ 221 2 NULL NULL NULL 222 1 NULL NULL NULL 223 2 NULL NULL NULL -224 2 224 0 1 +224 2 224 1 1 226 1 NULL NULL NULL 228 1 NULL NULL NULL 229 2 NULL NULL NULL @@ -366,7 +363,7 @@ 233 2 NULL NULL NULL 235 1 NULL NULL NULL 237 2 NULL NULL NULL -238 2 238 0 1 +238 2 238 1 1 239 2 NULL NULL NULL 24 2 NULL NULL NULL 241 1 NULL NULL NULL @@ -376,7 +373,7 @@ 248 1 NULL NULL NULL 249 1 NULL NULL NULL 252 1 NULL NULL NULL -255 2 255 0 1 +255 2 255 1 1 256 2 NULL NULL NULL 257 1 NULL NULL NULL 258 1 NULL NULL NULL @@ -388,11 +385,11 @@ 266 1 NULL NULL NULL 27 1 NULL NULL NULL 272 2 NULL NULL NULL -273 3 273 0 1 +273 3 273 1 1 274 1 NULL NULL NULL 275 1 NULL NULL NULL 277 4 NULL NULL NULL -278 2 278 0 1 +278 2 278 1 1 28 1 NULL NULL NULL 280 2 NULL NULL NULL 281 2 NULL NULL NULL @@ -416,7 +413,7 @@ 308 1 NULL NULL NULL 309 2 NULL NULL NULL 310 1 NULL NULL NULL -311 3 311 0 1 +311 3 311 1 1 315 1 NULL NULL NULL 316 3 NULL NULL NULL 317 2 NULL NULL NULL @@ -451,7 +448,7 @@ 366 1 NULL NULL NULL 367 2 NULL NULL NULL 368 1 NULL NULL NULL -369 3 369 0 1 +369 3 369 1 1 37 2 NULL NULL NULL 373 1 NULL NULL NULL 374 1 NULL NULL NULL @@ -472,11 +469,11 @@ 399 2 NULL NULL NULL 4 1 NULL NULL NULL 400 1 NULL NULL NULL -401 5 401 0 1 +401 5 401 1 1 402 1 NULL NULL NULL 403 3 NULL NULL NULL 404 2 NULL NULL NULL -406 4 406 0 1 +406 4 406 1 1 407 1 NULL NULL NULL 409 3 NULL NULL NULL 41 1 NULL NULL NULL @@ -552,7 +549,7 @@ 58 2 NULL NULL NULL 64 1 NULL NULL NULL 65 1 NULL NULL NULL -66 1 66 0 1 +66 1 66 1 1 67 2 NULL NULL NULL 69 1 NULL NULL NULL 70 3 NULL NULL NULL @@ -575,22 +572,4 @@ 95 2 NULL NULL NULL 96 1 NULL NULL NULL 97 2 NULL NULL NULL -98 2 98 0 1 -NULL NULL val_146 1 0 -NULL NULL val_150 1 0 -NULL NULL val_165 1 0 -NULL NULL val_193 1 0 -NULL NULL val_213 1 0 -NULL NULL val_238 1 0 -NULL NULL val_255 1 0 -NULL NULL val_265 1 0 -NULL NULL val_27 1 0 -NULL NULL val_273 1 0 -NULL NULL val_278 1 0 -NULL NULL val_311 1 0 -NULL NULL val_401 1 0 -NULL NULL val_406 1 0 -NULL NULL val_409 1 0 -NULL NULL val_484 1 0 -NULL NULL val_66 1 0 -NULL NULL val_98 1 0 +98 2 98 1 1 Index: ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out (working copy) @@ -85,10 +85,10 @@ type: bigint Needs Tagging: false Path -> Alias: - pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 [src] - pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 [src] + pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 [src] + pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 [src] Path -> Partition: - pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 + pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 Partition base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat @@ -102,13 +102,13 @@ columns.types string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart + location pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 name srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1288389287 + transient_lastDdlTime 1298001479 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat @@ -119,17 +119,17 @@ columns.types string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart + location pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart name srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1288389287 + transient_lastDdlTime 1298001479 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: srcpart name: srcpart - pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 + pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 Partition base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat @@ -143,13 +143,13 @@ columns.types string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart + location pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 name srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1288389287 + transient_lastDdlTime 1298001479 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat @@ -160,13 +160,13 @@ columns.types string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/srcpart + location pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/srcpart name srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1288389287 + transient_lastDdlTime 1298001479 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: srcpart name: srcpart @@ -212,9 +212,9 @@ File Output Operator compressed: false GlobalTableId: 1 - directory: pfile:/data/users/sdong/www/hive-trunk/build/ql/scratchdir/hive_2010-10-29_15-22-56_775_8999038142394451962/-ext-10000 + directory: pfile:/home/shaojie/source/hive/build/ql/scratchdir/hive_2011-02-17_21-41-44_080_5611294958146561766/-ext-10000 NumFilesPerFileSink: 1 - Stats Publishing Key Prefix: pfile:/data/users/sdong/www/hive-trunk/build/ql/scratchdir/hive_2010-10-29_15-22-56_775_8999038142394451962/-ext-10000/ + Stats Publishing Key Prefix: pfile:/home/shaojie/source/hive/build/ql/scratchdir/hive_2011-02-17_21-41-44_080_5611294958146561766/-ext-10000/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -224,12 +224,12 @@ columns.types string:int:string:int:int file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/dest1 + location pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/dest1 name dest1 serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1288390976 + transient_lastDdlTime 1298007704 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest1 TotalFiles: 1 @@ -240,7 +240,7 @@ Move Operator tables: replace: true - source: pfile:/data/users/sdong/www/hive-trunk/build/ql/scratchdir/hive_2010-10-29_15-22-56_775_8999038142394451962/-ext-10000 + source: pfile:/home/shaojie/source/hive/build/ql/scratchdir/hive_2011-02-17_21-41-44_080_5611294958146561766/-ext-10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -250,19 +250,19 @@ columns.types string:int:string:int:int file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - location pfile:/data/users/sdong/www/hive-trunk/build/ql/test/data/warehouse/dest1 + location pfile:/home/shaojie/source/hive/build/ql/test/data/warehouse/dest1 name dest1 serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - transient_lastDdlTime 1288390976 + transient_lastDdlTime 1298007704 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest1 - tmp directory: pfile:/data/users/sdong/www/hive-trunk/build/ql/scratchdir/hive_2010-10-29_15-22-56_775_8999038142394451962/-ext-10001 + tmp directory: pfile:/home/shaojie/source/hive/build/ql/scratchdir/hive_2011-02-17_21-41-44_080_5611294958146561766/-ext-10001 Stage: Stage-2 Stats-Aggr Operator - Stats Aggregation Key Prefix: pfile:/data/users/sdong/www/hive-trunk/build/ql/scratchdir/hive_2010-10-29_15-22-56_775_8999038142394451962/-ext-10000/ + Stats Aggregation Key Prefix: pfile:/home/shaojie/source/hive/build/ql/scratchdir/hive_2011-02-17_21-41-44_080_5611294958146561766/-ext-10000/ PREHOOK: query: FROM srcpart src @@ -285,20 +285,20 @@ POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 -PREHOOK: Output: file:/tmp/sdong/hive_2010-10-29_15-23-02_962_6408764044075057620/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-41-58_982_5935093483663045333/-mr-10000 POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 -POSTHOOK: Output: file:/tmp/sdong/hive_2010-10-29_15-23-02_962_6408764044075057620/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-41-58_982_5935093483663045333/-mr-10000 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ] 0 1 00.0 0 1 Index: ql/src/test/results/clientpositive/count.q.out =================================================================== --- ql/src/test/results/clientpositive/count.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/count.q.out (working copy) @@ -11,11 +11,11 @@ PREHOOK: query: select * from abcd PREHOOK: type: QUERY PREHOOK: Input: default@abcd -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_523_248548306762990690/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-20-58_430_4917517383401708915/-mr-10000 POSTHOOK: query: select * from abcd POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_523_248548306762990690/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-20-58_430_4917517383401708915/-mr-10000 NULL 35 23 6 10 1000 50 1 100 100 10 3 @@ -125,11 +125,11 @@ PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY PREHOOK: Input: default@abcd -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_925_5142539455043997266/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-20-59_176_8515784089648919771/-mr-10000 POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_925_5142539455043997266/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-20-59_176_8515784089648919771/-mr-10000 NULL 1 1 6 10 2 2 10 12 1 2 9 @@ -340,11 +340,11 @@ PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd PREHOOK: type: QUERY PREHOOK: Input: default@abcd -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-15_550_8269692453214848200/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-21-03_522_2469259469702404049/-mr-10000 POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-15_550_8269692453214848200/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-21-03_522_2469259469702404049/-mr-10000 7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4 PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY @@ -429,11 +429,11 @@ PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY PREHOOK: Input: default@abcd -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-18_476_7776659377634244729/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-21-08_253_2120418685375345146/-mr-10000 POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-18_476_7776659377634244729/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-21-08_253_2120418685375345146/-mr-10000 NULL 1 1 6 10 2 2 10 12 1 2 9 @@ -487,10 +487,10 @@ aggregations: expr: count(VALUE._col0) expr: count() - expr: count(KEY._col0:14._col0) - expr: count(KEY._col0:14._col1) - expr: count(KEY._col0:14._col2) - expr: count(KEY._col0:14._col3) + expr: count(KEY._col0:0._col0) + expr: count(KEY._col0:1._col0) + expr: count(KEY._col0:2._col0) + expr: count(KEY._col0:3._col0) expr: count(DISTINCT KEY._col0:0._col0) expr: count(DISTINCT KEY._col0:1._col0) expr: count(DISTINCT KEY._col0:2._col0) @@ -569,9 +569,9 @@ PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd PREHOOK: type: QUERY PREHOOK: Input: default@abcd -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-20_818_3596074897102517680/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-21-12_527_4494720248052024934/-mr-10000 POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-20_818_3596074897102517680/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-21-12_527_4494720248052024934/-mr-10000 7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4 Index: ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out (working copy) @@ -149,7 +149,7 @@ Group By Operator aggregations: expr: count(DISTINCT KEY._col1:0._col0) - expr: sum(KEY._col1:1._col0) + expr: sum(KEY._col1:0._col0) expr: sum(DISTINCT KEY._col1:1._col0) expr: count(DISTINCT KEY._col1:2._col0) bucketGroup: false Index: ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out (working copy) @@ -85,7 +85,7 @@ expr: count(DISTINCT KEY._col1:1._col0) bucketGroup: false keys: - expr: KEY._col1:1._col0 + expr: KEY._col0 type: string mode: mergepartial outputColumnNames: _col0, _col1, _col2 @@ -178,7 +178,7 @@ Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: - file:/tmp/liyintang/hive_2010-11-15_16-46-38_518_4441580357260614840/-mr-10003 + file:/tmp/shaojie/hive_2011-02-17_20-08-05_464_8040500473325095506/-mr-10003 Reduce Output Operator sort order: tag: -1 @@ -282,7 +282,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 -PREHOOK: Output: file:/tmp/liyintang/hive_2010-11-15_16-46-38_684_1519279081596807783/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_20-08-05_723_4919019446656039746/-mr-10000 POSTHOOK: query: SELECT sum(hash(a.key, a.value, b.key, b.value1, b.value2)) FROM ( @@ -298,5 +298,5 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 -POSTHOOK: Output: file:/tmp/liyintang/hive_2010-11-15_16-46-38_684_1519279081596807783/-mr-10000 -14748607855 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_20-08-05_723_4919019446656039746/-mr-10000 +40694575227 Index: ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out =================================================================== --- ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out (revision 1071122) +++ ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out (working copy) @@ -224,8 +224,8 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] @@ -237,14 +237,14 @@ PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 -PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-52_499_6413045004889165690/-mr-10000 +PREHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-33-20_740_6192899893312247896/-mr-10000 POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 -POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-52_499_6413045004889165690/-mr-10000 +POSTHOOK: Output: file:/tmp/shaojie/hive_2011-02-17_21-33-20_740_6192899893312247896/-mr-10000 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] Index: ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java =================================================================== --- ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java (revision 1071122) +++ ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java (working copy) @@ -2678,7 +2678,9 @@ + ":" + i + "." + name; ColumnInfo colInfo = new ColumnInfo(field, expr.getTypeInfo(), null, false); - reduceSinkOutputRowResolver.putExpression(parameter, colInfo); + if (reduceSinkOutputRowResolver.getExpression(parameter) == null) { + reduceSinkOutputRowResolver.putExpression(parameter, colInfo); + } numExprs++; } distinctColIndices.add(distinctIndices);