http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out index 3b7b68f..9724009 100644 --- a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out @@ -41,24 +41,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col1), sum(_col1), sum(DISTINCT _col1), count(DISTINCT _col2) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 491000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 491000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col4 (type: double) auto parallelism: false @@ -173,17 +173,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -214,12 +214,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -286,7 +286,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 2168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) auto parallelism: false @@ -324,13 +324,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 2216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out b/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out index 0824752..b21c079 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out @@ -46,32 +46,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value) keys: (key + key) (type: double), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -84,14 +84,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -100,12 +100,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -137,7 +137,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -145,10 +145,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -170,7 +170,7 @@ STAGE PLANS: key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -178,14 +178,14 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -194,12 +194,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -223,7 +223,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -231,10 +231,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out index 2999927..569f950 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out @@ -73,34 +73,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: substr(key, 1, 1) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -108,20 +108,20 @@ STAGE PLANS: name: default.dest_g4 Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -129,20 +129,20 @@ STAGE PLANS: name: default.dest_g2 Filter Operator predicate: (KEY._col0 < 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -317,21 +317,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: substr(key, 1, 1) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -341,20 +341,20 @@ STAGE PLANS: Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -362,20 +362,20 @@ STAGE PLANS: name: default.dest_g4 Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -383,20 +383,20 @@ STAGE PLANS: name: default.dest_g2 Filter Operator predicate: (KEY._col0 < 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -453,22 +453,22 @@ STAGE PLANS: key expressions: substr(key, 1, 1) (type: string), substr(key, 2, 1) (type: string), substr(value, 5) (type: string) sort order: +++ Map-reduce partition columns: substr(key, 1, 1) (type: string), substr(key, 2, 1) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0), sum(KEY._col2:0._col0), count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: bigint), concat(_col0, _col3) (type: string), _col3 (type: double), _col4 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -477,20 +477,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 76194 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0), sum(KEY._col2:0._col0), count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 65072 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col2) (type: int), concat(_col0, _col3) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 63080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 63080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -504,7 +504,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: string), _col3 (type: double), _col4 (type: bigint) Execution mode: vectorized @@ -512,17 +512,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: string), VALUE._col1 (type: double), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out index da7477e..ec7be0d 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out @@ -46,36 +46,36 @@ STAGE PLANS: TableScan alias: src filterExpr: ((substr(key, 1, 1) < 5) or (substr(key, 1, 1) >= 5)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((substr(key, 1, 1) < 5) or (substr(key, 1, 1) >= 5)) (type: boolean) - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(key, 1, 1) (type: string), key (type: string) sort order: ++ Map-reduce partition columns: substr(key, 1, 1) (type: string) - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 30250 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 19740 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 19740 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -84,12 +84,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, c1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 19740 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -98,20 +98,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 < 5) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 30250 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 21000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -120,12 +120,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) outputColumnNames: key, c1, c2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -157,7 +157,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -165,10 +165,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -198,7 +198,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -206,10 +206,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out index b6e9077..566bd2e 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out @@ -58,36 +58,36 @@ STAGE PLANS: TableScan alias: src filterExpr: ((((value = 'val_400') or (value = 'val_500')) and ((key = 400) or (key = 450))) or (((value = 'val_100') or (value = 'val_200') or (value = 'val_300')) and ((key = 100) or (key = 150) or (key = 200)))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((value = 'val_100') or (value = 'val_200') or (value = 'val_300')) and ((key = 100) or (key = 150) or (key = 200))) or (((value = 'val_400') or (value = 'val_500')) and ((key = 400) or (key = 450)))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((KEY._col0 = 100) or (KEY._col0 = 150) or (KEY._col0 = 200)) and ((VALUE._col0 = 'val_100') or (VALUE._col0 = 'val_200') or (VALUE._col0 = 'val_300'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -96,12 +96,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -110,20 +110,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (((KEY._col0 = 400) or (KEY._col0 = 450)) and ((VALUE._col0 = 'val_400') or (VALUE._col0 = 'val_500'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -132,12 +132,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -169,7 +169,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -177,10 +177,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -210,7 +210,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -218,10 +218,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -320,36 +320,36 @@ STAGE PLANS: TableScan alias: src filterExpr: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null)) or (((key + key) = 400) or (((key - 100) = 500) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -358,12 +358,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -372,20 +372,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((((VALUE._col0 - 100) = 500) and KEY._col0 is not null) or ((VALUE._col0 + VALUE._col0) = 400)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -394,12 +394,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -431,7 +431,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -439,10 +439,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -472,7 +472,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -480,10 +480,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -581,36 +581,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((value = 'val_100') or (value = 'val_200') or (value = 'val_300')) and ((key = 100) or (key = 150) or (key = 200))) or (((value = 'val_400') or (value = 'val_500')) and ((key = 400) or (key = 450)))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((KEY._col0 = 100) or (KEY._col0 = 150) or (KEY._col0 = 200)) and ((VALUE._col0 = 'val_100') or (VALUE._col0 = 'val_200') or (VALUE._col0 = 'val_300'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -619,12 +619,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -633,20 +633,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (((KEY._col0 = 400) or (KEY._col0 = 450)) and ((VALUE._col0 = 'val_400') or (VALUE._col0 = 'val_500'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -655,12 +655,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -692,7 +692,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -700,10 +700,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -733,7 +733,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -741,10 +741,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -842,36 +842,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null)) or (((key + key) = 400) or (((key - 100) = 500) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -880,12 +880,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -894,20 +894,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((((VALUE._col0 - 100) = 500) and KEY._col0 is not null) or ((VALUE._col0 + VALUE._col0) = 400)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -916,12 +916,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -953,7 +953,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -961,10 +961,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -994,7 +994,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -1002,10 +1002,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_multialias.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby_multialias.q.out b/ql/src/test/results/clientpositive/groupby_multialias.q.out index 66dad28..2bee356 100644 --- a/ql/src/test/results/clientpositive/groupby_multialias.q.out +++ b/ql/src/test/results/clientpositive/groupby_multialias.q.out @@ -30,22 +30,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n150 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: a - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(a) keys: a (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 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: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -54,10 +54,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat