http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/join6.q.out b/ql/src/test/results/clientpositive/join6.q.out index 8d6578a..989ae2a 100644 --- a/ql/src/test/results/clientpositive/join6.q.out +++ b/ql/src/test/results/clientpositive/join6.q.out @@ -39,7 +39,8 @@ 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 @@ -98,6 +99,21 @@ 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: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: c1, c2, c3, c4 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 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 @@ -112,6 +128,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3, c4 + Column Types: int, 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: 1728 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,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,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), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 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 ( FROM
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/join7.q.out b/ql/src/test/results/clientpositive/join7.q.out index f1af54a..f34df53 100644 --- a/ql/src/test/results/clientpositive/join7.q.out +++ b/ql/src/test/results/clientpositive/join7.q.out @@ -49,7 +49,8 @@ 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 @@ -126,6 +127,21 @@ 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: string), _col2 (type: int), _col3 (type: string), _col4 (type: int), _col5 (type: string) + outputColumnNames: c1, c2, c3, c4, c5, c6 + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 2592 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 @@ -140,6 +156,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3, c4, c5, c6 + Column Types: int, string, int, 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: 2592 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,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,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col5 (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), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2640 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 ( FROM http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/join8.q.out b/ql/src/test/results/clientpositive/join8.q.out index ce5a5d4..bfe4fd8 100644 --- a/ql/src/test/results/clientpositive/join8.q.out +++ b/ql/src/test/results/clientpositive/join8.q.out @@ -39,7 +39,8 @@ 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 @@ -101,6 +102,21 @@ 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: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: c1, c2, c3, c4 + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 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 @@ -115,6 +131,32 @@ STAGE PLANS: Stage: Stage-2 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3, c4 + Column Types: int, 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: 1728 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,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,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), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 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 ( FROM http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/join9.q.out b/ql/src/test/results/clientpositive/join9.q.out index 58f8d7d..6db5185 100644 --- a/ql/src/test/results/clientpositive/join9.q.out +++ b/ql/src/test/results/clientpositive/join9.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 @@ -210,6 +211,33 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + 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 + 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 + 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 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> + 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 Stage: Stage-0 Move Operator @@ -243,6 +271,80 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.dest1 + Is Table Level Stats: true + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + GatherStats: false + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + tag: -1 + 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>) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10002 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> + 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 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> + 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: + 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 + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false PREHOOK: query: FROM srcpart src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest1 SELECT src1.key, src2.value where src1.ds = '2008-04-08' and src1.hr = '12' http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join_map_ppr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/join_map_ppr.q.out b/ql/src/test/results/clientpositive/join_map_ppr.q.out index 6eb9889..c5acb9b 100644 --- a/ql/src/test/results/clientpositive/join_map_ppr.q.out +++ b/ql/src/test/results/clientpositive/join_map_ppr.q.out @@ -131,6 +131,22 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -186,6 +202,35 @@ STAGE PLANS: name: default.srcpart Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [z] + Needs Tagging: false + 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: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-9 Conditional Operator @@ -228,6 +273,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j1 + Is Table Level Stats: true Stage: Stage-5 Map Reduce @@ -689,7 +739,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -710,6 +760,22 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -765,6 +831,35 @@ STAGE PLANS: name: default.srcpart Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [z] + Needs Tagging: false + 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: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-9 Conditional Operator @@ -784,7 +879,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -807,6 +902,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j1 + Is Table Level Stats: true Stage: Stage-5 Map Reduce @@ -822,7 +922,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -852,7 +952,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -873,7 +973,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -909,7 +1009,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -939,7 +1039,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -960,7 +1060,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/lb_fs_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/lb_fs_stats.q.out b/ql/src/test/results/clientpositive/lb_fs_stats.q.out index 3309089..6595364 100644 --- a/ql/src/test/results/clientpositive/lb_fs_stats.q.out +++ b/ql/src/test/results/clientpositive/lb_fs_stats.q.out @@ -44,7 +44,7 @@ Database: default Table: test_tab #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 2 numRows 500 rawDataSize 4812 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out index 7d0abfd..7bcde29 100644 --- a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out +++ b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out @@ -226,10 +226,12 @@ 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-7 Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 + Stage-6 depends on stages: Stage-1, Stage-4, Stage-7 + Stage-5 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-2 @@ -269,6 +271,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_2 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, c1 + 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') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 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(VALUE._col0) keys: KEY._col0 (type: string) @@ -298,6 +315,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, c1 + Column Types: string, int + Table: default.dest_2 Stage: Stage-4 Map Reduce @@ -305,8 +326,37 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: + Statistics: Num rows: 1 Data size: 864 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>) + 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 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, c1 + Column Types: string, int + Table: default.dest_3 + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.3 value expressions: _col0 (type: string), _col1 (type: double) Reduce Operator Tree: Select Operator @@ -328,6 +378,21 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, c1 + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + 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 @@ -339,7 +404,25 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_3 - Stage: Stage-5 - Stats Work - Basic Stats Work: + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 864 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>) + 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 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/lineage1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/lineage1.q.out b/ql/src/test/results/clientpositive/lineage1.q.out index 7d6af3e..beee129 100644 --- a/ql/src/test/results/clientpositive/lineage1.q.out +++ b/ql/src/test/results/clientpositive/lineage1.q.out @@ -111,6 +111,19 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_l1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 1100 Data size: 11686 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: 864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 864 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,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) TableScan Union Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE @@ -126,6 +139,32 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_l1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 1100 Data size: 11686 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: 864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 864 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,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) + 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 Stage: Stage-8 Conditional Operator @@ -149,6 +188,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.dest_l1 Stage: Stage-4 Map Reduce http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out index 2eca946..6901a8e 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out @@ -65,6 +65,25 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -167,6 +186,40 @@ STAGE PLANS: Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [srcpart] /srcpart/ds=2008-04-08/hr=12 [srcpart] + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Move Operator @@ -200,6 +253,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.list_bucketing_dynamic_part + Is Table Level Stats: false PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08' PREHOOK: type: QUERY @@ -239,7 +297,7 @@ Database: default Table: list_bucketing_dynamic_part #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 2 numRows 500 rawDataSize 5312 @@ -282,7 +340,7 @@ Database: default Table: list_bucketing_dynamic_part #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 2 numRows 500 rawDataSize 5312 @@ -354,7 +412,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 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 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out index 6b34745..872dd14 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out @@ -69,6 +69,25 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -120,6 +139,40 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [src] + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Move Operator @@ -153,6 +206,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.list_bucketing_static_part + Is Table Level Stats: false PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') select key, value from src @@ -194,7 +252,7 @@ Database: default Table: list_bucketing_static_part #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 4 numRows 500 rawDataSize 4812 @@ -237,7 +295,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 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 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out index a0bc3e9..09d4718 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out @@ -69,6 +69,25 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), '2008-04-08' (type: string), '11' (type: string) + outputColumnNames: col1, col2, col3, col4, col5, ds, hr + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll'), compute_stats(col4, 'hll'), compute_stats(col5, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -120,6 +139,40 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [src] + Needs Tagging: false + 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) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col6 (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, _col4, _col5, _col6 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Move Operator @@ -153,6 +206,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: col1, col2, col3, col4, col5 + Column Types: string, string, string, string, string + Table: default.list_bucketing_mul_col + Is Table Level Stats: false PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11') select 1, key, 1, value, 1 from src @@ -200,7 +258,7 @@ Database: default Table: list_bucketing_mul_col #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\",\"col4\":\"true\",\"col5\":\"true\"}} numFiles 4 numRows 500 rawDataSize 6312 @@ -245,7 +303,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"col1":"true","col2":"true","col3":"true","col4":"true","col5":"true"}} bucket_count -1 column.name.delimiter , columns col1,col2,col3,col4,col5 @@ -337,7 +395,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"col1":"true","col2":"true","col3":"true","col4":"true","col5":"true"}} bucket_count -1 column.name.delimiter , columns col1,col2,col3,col4,col5 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out index df8717b..becdf67 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out @@ -69,6 +69,25 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string) + outputColumnNames: col1, col2, col3, col4, col5, ds, hr + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll'), compute_stats(col4, 'hll'), compute_stats(col5, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -120,6 +139,40 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [src] + Needs Tagging: false + 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) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + 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>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col6 (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, _col4, _col5, _col6 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Move Operator @@ -153,6 +206,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: col1, col2, col3, col4, col5 + Column Types: string, string, string, string, string + Table: default.list_bucketing_mul_col + Is Table Level Stats: false PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99') select 1, key, 1, value, 1 from src @@ -200,7 +258,7 @@ Database: default Table: list_bucketing_mul_col #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\",\"col4\":\"true\",\"col5\":\"true\"}} numFiles 4 numRows 500 rawDataSize 6312 @@ -245,7 +303,7 @@ STAGE PLANS: ds 2008-04-08 hr 2013-01-23+18:00:99 properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"col1":"true","col2":"true","col3":"true","col4":"true","col5":"true"}} bucket_count -1 column.name.delimiter , columns col1,col2,col3,col4,col5 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out index 6b48f3d..b6f6540 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out @@ -65,6 +65,22 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 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: 880 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -116,6 +132,35 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [src] + Needs Tagging: false + 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 + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Move Operator @@ -149,6 +194,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.list_bucketing + Is Table Level Stats: true PREHOOK: query: insert overwrite table list_bucketing select * from src PREHOOK: type: QUERY @@ -177,7 +227,7 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 2 numRows 500 rawDataSize 5312 @@ -283,7 +333,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 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 @@ -304,7 +354,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 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 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out index 512aeab..0280c02 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out @@ -69,6 +69,25 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -171,6 +190,40 @@ STAGE PLANS: Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [srcpart] /srcpart/ds=2008-04-08/hr=12 [srcpart] + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Move Operator @@ -204,6 +257,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.list_bucketing_static_part + Is Table Level Stats: false PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') select key, value from srcpart where ds = '2008-04-08' @@ -249,7 +307,7 @@ Database: default Table: list_bucketing_static_part #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 6 numRows 1000 rawDataSize 9624 @@ -310,7 +368,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 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 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out index e86bf0a..b556890 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out @@ -59,6 +59,25 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -161,6 +180,40 @@ STAGE PLANS: Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [srcpart] /srcpart/ds=2008-04-08/hr=12 [srcpart] + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Move Operator @@ -194,6 +247,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.list_bucketing_static_part + Is Table Level Stats: false PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds='2008-04-08', hr='11') select key, value from srcpart where ds='2008-04-08' PREHOOK: type: QUERY @@ -230,7 +288,7 @@ Database: default Table: list_bucketing_static_part #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} numFiles 4 numRows 1000 rawDataSize 10624 @@ -302,7 +360,7 @@ STAGE PLANS: ds 2008-04-08 hr 11 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
