http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out index 5f74166..a5d1724 100644 --- a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out +++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out @@ -145,7 +145,7 @@ STAGE PLANS: partition values: year 2000 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -190,7 +190,7 @@ STAGE PLANS: partition values: year 2001 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -235,7 +235,7 @@ STAGE PLANS: partition values: year 2002 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -280,7 +280,7 @@ STAGE PLANS: partition values: year 2003 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -322,12 +322,12 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_1d - Statistics: Num rows: 20 Data size: 1700 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: state (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 1700 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select state,locid from loc_orc_1d @@ -348,7 +348,7 @@ STAGE PLANS: partition values: year 2000 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -393,7 +393,7 @@ STAGE PLANS: partition values: year 2001 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -438,7 +438,7 @@ STAGE PLANS: partition values: year 2002 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -483,7 +483,7 @@ STAGE PLANS: partition values: year 2003 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -525,12 +525,12 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_1d - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: analyze table loc_orc_1d partition(year='2000') compute statistics for columns state @@ -579,7 +579,7 @@ STAGE PLANS: partition values: year 2000 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -624,7 +624,7 @@ STAGE PLANS: partition values: year 2001 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -669,7 +669,7 @@ STAGE PLANS: partition values: year 2002 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -714,7 +714,7 @@ STAGE PLANS: partition values: year 2003 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -782,7 +782,7 @@ STAGE PLANS: partition values: year 2000 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -827,7 +827,7 @@ STAGE PLANS: partition values: year 2001 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -872,7 +872,7 @@ STAGE PLANS: partition values: year 2002 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -917,7 +917,7 @@ STAGE PLANS: partition values: year 2003 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true","zip":"true"}} bucket_count -1 column.name.delimiter , columns state,locid,zip @@ -959,12 +959,12 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_1d - Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: create table if not exists loc_orc_2d ( @@ -1068,7 +1068,7 @@ STAGE PLANS: year 2001 zip 43201 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1114,7 +1114,7 @@ STAGE PLANS: year 2002 zip 43201 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1160,7 +1160,7 @@ STAGE PLANS: year 2003 zip 43201 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1206,7 +1206,7 @@ STAGE PLANS: year 2000 zip 94086 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1298,7 +1298,7 @@ STAGE PLANS: year 2002 zip 94086 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1344,7 +1344,7 @@ STAGE PLANS: year 2003 zip 94086 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1390,7 +1390,7 @@ STAGE PLANS: year 2000 zip 94087 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1436,7 +1436,7 @@ STAGE PLANS: year 2001 zip 94087 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1528,7 +1528,7 @@ STAGE PLANS: year 2003 zip 94087 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1570,12 +1570,12 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_2d - Statistics: Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: state (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select state,locid from loc_orc_2d @@ -1597,7 +1597,7 @@ STAGE PLANS: year 2001 zip 43201 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1643,7 +1643,7 @@ STAGE PLANS: year 2002 zip 43201 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1689,7 +1689,7 @@ STAGE PLANS: year 2003 zip 43201 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1735,7 +1735,7 @@ STAGE PLANS: year 2000 zip 94086 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1827,7 +1827,7 @@ STAGE PLANS: year 2002 zip 94086 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1873,7 +1873,7 @@ STAGE PLANS: year 2003 zip 94086 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1919,7 +1919,7 @@ STAGE PLANS: year 2000 zip 94087 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -1965,7 +1965,7 @@ STAGE PLANS: year 2001 zip 94087 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -2057,7 +2057,7 @@ STAGE PLANS: year 2003 zip 94087 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"locid":"true","state":"true"}} bucket_count -1 column.name.delimiter , columns state,locid @@ -2099,11 +2099,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_2d - Statistics: Num rows: 20 Data size: 1840 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1840 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE ListSink
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/filter_join_breaktask.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out index 9d00ce6..884bfcd 100644 --- a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out +++ b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out @@ -38,22 +38,22 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: g + alias: f Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (value <> '') (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false @@ -70,13 +70,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col0 (type: int) + value expressions: _col1 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -89,7 +89,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value @@ -129,16 +129,16 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [$hdt$_0:g, $hdt$_1:m] + /filter_join_breaktask/ds=2008-04-08 [$hdt$_1:f, $hdt$_2:m] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col2 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col3 Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -150,8 +150,8 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col2 - columns.types string,int + columns _col0,_col3 + columns.types int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -165,31 +165,31 @@ STAGE PLANS: TableScan GatherStats: false Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col3 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col2 (type: int) + Map-reduce partition columns: _col3 (type: string) Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col0 (type: string) + value expressions: _col0 (type: int) auto parallelism: false TableScan - alias: f + alias: g Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: (value <> '') (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false @@ -203,8 +203,8 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col2 - columns.types string,int + columns _col0,_col3 + columns.types int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -213,8 +213,8 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col2 - columns.types string,int + columns _col0,_col3 + columns.types int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -226,7 +226,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value @@ -266,7 +266,7 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [$hdt$_2:f] + /filter_join_breaktask/ds=2008-04-08 [$hdt$_0:g] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -274,12 +274,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) - 1 _col0 (type: int) + 0 _col3 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col5 Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: int), _col0 (type: string) + expressions: _col0 (type: int), _col5 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby10.q.out b/ql/src/test/results/clientpositive/groupby10.q.out index 9f90a2c..79e4fd2 100644 --- a/ql/src/test/results/clientpositive/groupby10.q.out +++ b/ql/src/test/results/clientpositive/groupby10.q.out @@ -44,11 +44,15 @@ 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-5 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-0, Stage-6, Stage-11 + Stage-5 depends on stages: Stage-3 Stage-6 depends on stages: Stage-5 - Stage-1 depends on stages: Stage-6 - Stage-7 depends on stages: Stage-1 + Stage-9 depends on stages: Stage-1, Stage-6, Stage-11 + Stage-7 depends on stages: Stage-2 + Stage-8 depends on stages: Stage-7 + Stage-1 depends on stages: Stage-8 + Stage-10 depends on stages: Stage-8 + Stage-11 depends on stages: Stage-10 STAGE PLANS: Stage: Stage-2 @@ -119,6 +123,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -133,12 +147,68 @@ STAGE PLANS: Stage: Stage-4 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: int, int, int + Table: default.dest1 Stage: Stage-5 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + sort order: + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + mode: partial1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + 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>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-9 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: int, int, int + Table: default.dest2 + + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator key expressions: key (type: int), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: int) @@ -157,7 +227,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-8 Map Reduce Map Operator Tree: TableScan @@ -186,6 +256,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Move Operator @@ -197,9 +277,49 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 - Stage: Stage-7 - Stats Work - Basic Stats Work: + Stage: Stage-10 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + mode: partial1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-11 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + 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>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM INPUT INSERT OVERWRITE TABLE dest1 SELECT INPUT.key, count(substr(INPUT.value,5)), count(distinct substr(INPUT.value,5)) GROUP BY INPUT.key @@ -291,11 +411,15 @@ 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-5 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-0, Stage-6, Stage-11 + Stage-5 depends on stages: Stage-3 Stage-6 depends on stages: Stage-5 - Stage-1 depends on stages: Stage-6 - Stage-7 depends on stages: Stage-1 + Stage-9 depends on stages: Stage-1, Stage-6, Stage-11 + Stage-7 depends on stages: Stage-2 + Stage-8 depends on stages: Stage-7 + Stage-1 depends on stages: Stage-8 + Stage-10 depends on stages: Stage-8 + Stage-11 depends on stages: Stage-10 STAGE PLANS: Stage: Stage-2 @@ -366,6 +490,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -380,12 +514,68 @@ STAGE PLANS: Stage: Stage-4 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: int, int, int + Table: default.dest1 Stage: Stage-5 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + sort order: + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + mode: partial1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + 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>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-9 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: int, int, int + Table: default.dest2 + + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator key expressions: key (type: int), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: int) @@ -404,7 +594,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-8 Map Reduce Map Operator Tree: TableScan @@ -433,6 +623,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Move Operator @@ -444,9 +644,49 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 - Stage: Stage-7 - Stats Work - Basic Stats Work: + Stage: Stage-10 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + mode: partial1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-11 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + 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>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM INPUT INSERT OVERWRITE TABLE dest1 SELECT INPUT.key, count(substr(INPUT.value,5)), count(distinct substr(INPUT.value,5)) GROUP BY INPUT.key @@ -537,9 +777,11 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 + Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 + Stage-4 depends on stages: Stage-2 + Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 Stage-1 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-1 + Stage-6 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-2 @@ -578,6 +820,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Group By Operator aggregations: sum(DISTINCT KEY._col1:0._col0), avg(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: int) @@ -596,6 +848,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -610,6 +872,40 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: int, int, int + Table: default.dest1 + + Stage: Stage-4 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: int, int, int + Table: default.dest2 Stage: Stage-1 Move Operator @@ -621,9 +917,27 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 - Stage: Stage-4 - Stats Work - Basic Stats Work: + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM INPUT INSERT OVERWRITE TABLE dest1 SELECT INPUT.key, sum(distinct substr(INPUT.value,5)), count(distinct substr(INPUT.value,5)) GROUP BY INPUT.key http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby11.q.out b/ql/src/test/results/clientpositive/groupby11.q.out index 2ab4c39..592be1d 100644 --- a/ql/src/test/results/clientpositive/groupby11.q.out +++ b/ql/src/test/results/clientpositive/groupby11.q.out @@ -32,11 +32,15 @@ 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-5 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-0, Stage-6, Stage-11 + Stage-5 depends on stages: Stage-3 Stage-6 depends on stages: Stage-5 - Stage-1 depends on stages: Stage-6 - Stage-7 depends on stages: Stage-1 + Stage-9 depends on stages: Stage-1, Stage-6, Stage-11 + Stage-7 depends on stages: Stage-2 + Stage-8 depends on stages: Stage-7 + Stage-1 depends on stages: Stage-8 + Stage-10 depends on stages: Stage-8 + Stage-11 depends on stages: Stage-10 STAGE PLANS: Stage: Stage-2 @@ -107,6 +111,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -123,12 +137,77 @@ STAGE PLANS: Stage: Stage-4 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: string, int, int + Table: default.dest1 Stage: Stage-5 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: '111' (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + keys: '111' (type: string) + mode: partial1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: '111' (type: string) + sort order: + + Map-reduce partition columns: '111' (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: '111' (type: string) + mode: final + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '111' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-9 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, val1, val2 + Column Types: string, int, int + Table: default.dest2 + + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator key expressions: substr(value, 5) (type: string), key (type: string) sort order: ++ Map-reduce partition columns: substr(value, 5) (type: string) @@ -147,7 +226,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-8 Map Reduce Map Operator Tree: TableScan @@ -176,6 +255,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) + outputColumnNames: key, val1, val2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Move Operator @@ -189,9 +278,58 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest2 - Stage: Stage-7 - Stats Work - Basic Stats Work: + Stage: Stage-10 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: '111' (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string), val1 (type: int), val2 (type: int) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') + keys: '111' (type: string) + mode: partial1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-11 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: '111' (type: string) + sort order: + + Map-reduce partition columns: '111' (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: '111' (type: string) + mode: final + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '111' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 partition(ds='111') http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby12.q.out b/ql/src/test/results/clientpositive/groupby12.q.out index 2f633f0..cd0b7fb 100644 --- a/ql/src/test/results/clientpositive/groupby12.q.out +++ b/ql/src/test/results/clientpositive/groupby12.q.out @@ -17,7 +17,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -54,6 +55,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -68,6 +79,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: string) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT COUNT(src.key), COUNT(DISTINCT value) GROUP BY src.key http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby1_map.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby1_map.q.out b/ql/src/test/results/clientpositive/groupby1_map.q.out index 337c2e0..82fe1f0 100644 --- a/ql/src/test/results/clientpositive/groupby1_map.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map.q.out @@ -15,7 +15,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -59,6 +60,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: double) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -73,6 +89,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, double + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + 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 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out index 337c2e0..82fe1f0 100644 --- a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out @@ -15,7 +15,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -59,6 +60,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: double) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -73,6 +89,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, double + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + 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 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby1_map_skew.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby1_map_skew.q.out b/ql/src/test/results/clientpositive/groupby1_map_skew.q.out index a140a02..44b4db7 100644 --- a/ql/src/test/results/clientpositive/groupby1_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map_skew.q.out @@ -16,7 +16,8 @@ STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 + Stage-3 depends on stages: Stage-0, Stage-4 + Stage-4 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 @@ -84,6 +85,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: int), _col1 (type: double) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -98,6 +114,32 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, double + Table: default.dest1 + + Stage: Stage-4 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby1_noskew.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby1_noskew.q.out b/ql/src/test/results/clientpositive/groupby1_noskew.q.out index 702ea3e..ba4366d 100644 --- a/ql/src/test/results/clientpositive/groupby1_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby1_noskew.q.out @@ -15,7 +15,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -53,6 +54,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_g1 + Select Operator + expressions: _col0 (type: int), _col1 (type: double) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -67,6 +78,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, double + Table: default.dest_g1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: double) + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest_g1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby2_map.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby2_map.q.out b/ql/src/test/results/clientpositive/groupby2_map.q.out index 427590d..262c5d8 100644 --- a/ql/src/test/results/clientpositive/groupby2_map.q.out +++ b/ql/src/test/results/clientpositive/groupby2_map.q.out @@ -17,7 +17,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -61,6 +62,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) + outputColumnNames: key, c1, c2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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: 1312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -75,6 +91,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, c1, c2 + Column Types: string, int, string + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + 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>) + Reduce Operator Tree: + Group By Operator + 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: 1328 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1) http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out index 0ab1985..581e958 100644 --- a/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out @@ -17,7 +17,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -61,6 +62,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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: 2160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -75,6 +91,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, c1, c2, c3, c4 + Column Types: string, int, string, int, int + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + 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>) + Reduce Operator Tree: + Group By Operator + 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: 2208 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1) @@ -120,7 +162,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0, Stage-3 + Stage-3 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 @@ -164,6 +207,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 + 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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: 2160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator @@ -178,6 +236,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, c1, c2, c3, c4 + Column Types: string, int, string, int, int + Table: default.dest1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + 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>) + Reduce Operator Tree: + Group By Operator + 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: 2208 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.key,1,1)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
