http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/autoColumnStats_8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/autoColumnStats_8.q.out b/ql/src/test/results/clientpositive/autoColumnStats_8.q.out index 3c1fb82..613465e 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_8.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_8.q.out @@ -57,13 +57,11 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - Stage-4 depends on stages: Stage-0 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-1, Stage-5 Stage-5 depends on stages: Stage-2 - Stage-7 depends on stages: Stage-1, Stage-5 - Stage-6 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-2 @@ -71,71 +69,112 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.nzhang_part8 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct nzhang_part8 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part8 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) auto parallelism: false + Filter Operator + isSamplingPred: false + predicate: (ds > '2008-04-08') (type: boolean) + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - GlobalTableId: 0 + GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 + Static Partition Specification: ds=2008-12-31/ + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: + bucket_count -1 column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types string,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.nzhang_part8 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct nzhang_part8 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part8 TotalFiles: 1 - GatherStats: false + GatherStats: true MultiFileSpray: false - Filter Operator - isSamplingPred: false - predicate: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: '2008-12-31' (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -154,24 +193,6 @@ STAGE PLANS: TotalFiles: 1 GatherStats: false MultiFileSpray: false - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -383,17 +404,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -411,88 +432,44 @@ STAGE PLANS: GatherStats: false MultiFileSpray: false - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: + Stage: Stage-0 + Move Operator + tables: + partition: + ds + hr + replace: true #### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types string,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: + bucket_count -1 column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types string,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - Dp Sort State: PARTITION_SORTED - NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string + name default.nzhang_part8 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct nzhang_part8 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### - name default.nzhang_part8 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct nzhang_part8 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part8 + + Stage: Stage-3 + Stats Work + Basic Stats Work: #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part8 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Stage: Stage-0 + Stage: Stage-1 Move Operator tables: partition: - ds + ds 2008-12-31 hr replace: true #### A masked pattern was here #### @@ -520,6 +497,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.nzhang_part8 + Is Table Level Stats: false Stage: Stage-5 Map Reduce @@ -531,7 +513,7 @@ STAGE PLANS: null sort order: aa sort order: ++ Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) auto parallelism: false @@ -541,7 +523,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10005 + base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -570,17 +552,17 @@ STAGE PLANS: keys: '2008-12-31' (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '2008-12-31' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -598,122 +580,6 @@ STAGE PLANS: GatherStats: false MultiFileSpray: false - Stage: Stage-7 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.nzhang_part8 - Is Table Level Stats: false - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - key expressions: _col2 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col2 (type: string) - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10006 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 2 -#### A masked pattern was here #### - Dp Sort State: PARTITION_SORTED - NumFilesPerFileSink: 1 - Static Partition Specification: ds=2008-12-31/ - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.nzhang_part8 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct nzhang_part8 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part8 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - - Stage: Stage-1 - Move Operator - tables: - partition: - ds 2008-12-31 - hr - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.nzhang_part8 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct nzhang_part8 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part8 - PREHOOK: query: from srcpart insert overwrite table nzhang_part8 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08' insert overwrite table nzhang_part8 partition(ds='2008-12-31', hr) select key, value, hr where ds > '2008-04-08'
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out index c87eae1..90774c0 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out @@ -34,35 +34,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key 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 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 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -73,14 +73,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -89,12 +89,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, '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: @@ -133,10 +133,10 @@ STAGE PLANS: Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -145,12 +145,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, '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: @@ -184,7 +184,7 @@ 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -192,10 +192,10 @@ 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/auto_join0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join0.q.out b/ql/src/test/results/clientpositive/auto_join0.q.out index e68a27c..25c1e7f 100644 --- a/ql/src/test/results/clientpositive/auto_join0.q.out +++ b/ql/src/test/results/clientpositive/auto_join0.q.out @@ -46,24 +46,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (key < 10) (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 < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -99,12 +99,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -121,7 +121,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -129,10 +129,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -163,12 +163,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -185,12 +185,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -200,12 +200,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -219,24 +219,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (key < 10) (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 < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/auto_join1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join1.q.out b/ql/src/test/results/clientpositive/auto_join1.q.out index 3ea8e83..2a7d0d5 100644 --- a/ql/src/test/results/clientpositive/auto_join1.q.out +++ b/ql/src/test/results/clientpositive/auto_join1.q.out @@ -37,14 +37,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -56,14 +56,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key 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 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 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -71,14 +71,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -87,12 +87,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, '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: @@ -126,7 +126,7 @@ 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -134,10 +134,10 @@ 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/auto_join10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join10.q.out b/ql/src/test/results/clientpositive/auto_join10.q.out index f003e3c..356574f 100644 --- a/ql/src/test/results/clientpositive/auto_join10.q.out +++ b/ql/src/test/results/clientpositive/auto_join10.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key 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 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 Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,19 +69,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col1,_col2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -91,10 +91,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 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/auto_join11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join11.q.out b/ql/src/test/results/clientpositive/auto_join11.q.out index d8cf587..d280af6 100644 --- a/ql/src/test/results/clientpositive/auto_join11.q.out +++ b/ql/src/test/results/clientpositive/auto_join11.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (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: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,19 +69,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -91,10 +91,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 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/auto_join12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join12.q.out b/ql/src/test/results/clientpositive/auto_join12.q.out index 421f5ff..3ffd6ed 100644 --- a/ql/src/test/results/clientpositive/auto_join12.q.out +++ b/ql/src/test/results/clientpositive/auto_join12.q.out @@ -44,14 +44,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -61,14 +61,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -81,14 +81,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (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: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -98,19 +98,19 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -120,10 +120,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 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/auto_join13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join13.q.out b/ql/src/test/results/clientpositive/auto_join13.q.out index 60c087d..59e9c70 100644 --- a/ql/src/test/results/clientpositive/auto_join13.q.out +++ b/ql/src/test/results/clientpositive/auto_join13.q.out @@ -44,14 +44,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (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: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -79,14 +79,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -94,7 +94,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -102,19 +102,19 @@ STAGE PLANS: 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) 1 _col0 (type: double) outputColumnNames: _col1, _col2 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2,_col1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -124,10 +124,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 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/auto_join14.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join14.q.out b/ql/src/test/results/clientpositive/auto_join14.q.out index 30b6e2a..b6a631f 100644 --- a/ql/src/test/results/clientpositive/auto_join14.q.out +++ b/ql/src/test/results/clientpositive/auto_join14.q.out @@ -43,14 +43,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -62,14 +62,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (UDFToDouble(key) > 100.0D)) (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 Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -77,14 +77,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 30972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -93,12 +93,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: c1, c2 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, '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: @@ -132,7 +132,7 @@ 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,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: vectorized Reduce Operator Tree: @@ -140,10 +140,10 @@ 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/auto_join15.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join15.q.out b/ql/src/test/results/clientpositive/auto_join15.q.out index c711923..4ff0473 100644 --- a/ql/src/test/results/clientpositive/auto_join15.q.out +++ b/ql/src/test/results/clientpositive/auto_join15.q.out @@ -35,10 +35,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key 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 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 HashTable Sink Operator keys: 0 key (type: string) @@ -50,10 +50,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key 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 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -61,19 +61,19 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -83,10 +83,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 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/auto_join16.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_join16.q.out b/ql/src/test/results/clientpositive/auto_join16.q.out index dc0dfe1..9d8b220 100644 --- a/ql/src/test/results/clientpositive/auto_join16.q.out +++ b/ql/src/test/results/clientpositive/auto_join16.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (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: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string), _col1 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: tab filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (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: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,19 +69,19 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -91,10 +91,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat