Modified: hive/trunk/ql/src/test/results/clientpositive/groupby_mutli_insert_common_distinct.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby_mutli_insert_common_distinct.q.out?rev=1451259&r1=1451258&r2=1451259&view=diff ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/groupby_mutli_insert_common_distinct.q.out (original) +++ hive/trunk/ql/src/test/results/clientpositive/groupby_mutli_insert_common_distinct.q.out Thu Feb 28 17:20:46 2013 @@ -1,504 +0,0 @@ -PREHOOK: query: create table dest1(key int, cnt int) -PREHOOK: type: CREATETABLE -POSTHOOK: query: create table dest1(key int, cnt int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: default@dest1 -PREHOOK: query: create table dest2(key int, cnt int) -PREHOOK: type: CREATETABLE -POSTHOOK: query: create table dest2(key int, cnt int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: default@dest2 -PREHOOK: query: explain -from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -PREHOOK: type: QUERY -POSTHOOK: query: explain -from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -POSTHOOK: type: QUERY -ABSTRACT SYNTAX TREE: - (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL value)))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest2))) (TOK_SELECT (TOK_SELEXPR (+ (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL key))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL value)))) (TOK_GROUPBY (+ (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL key))))) - -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-1 depends on stages: Stage-5 - Stage-6 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Alias -> Map Operator Tree: - src - TableScan - alias: src - Reduce Output Operator - key expressions: - expr: value - type: string - sort order: + - Map-reduce partition columns: - expr: value - type: string - tag: -1 - value expressions: - expr: key - type: string - expr: (key + key) - type: double - Reduce Operator Tree: - Forward - Group By Operator - aggregations: - expr: count(DISTINCT KEY._col0) - bucketGroup: false - keys: - expr: VALUE._col0 - type: string - mode: hash - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - GlobalTableId: 0 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - Group By Operator - aggregations: - expr: count(DISTINCT KEY._col0) - bucketGroup: false - keys: - expr: VALUE._col1 - type: double - mode: hash - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - GlobalTableId: 0 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - - Stage: Stage-3 - Map Reduce - Alias -> Map Operator Tree: -#### A masked pattern was here #### - Reduce Output Operator - key expressions: - expr: _col0 - type: string - sort order: + - Map-reduce partition columns: - expr: _col0 - type: string - tag: -1 - value expressions: - expr: _col1 - type: bigint - Reduce Operator Tree: - Group By Operator - aggregations: - expr: count(VALUE._col0) - bucketGroup: false - keys: - expr: KEY._col0 - type: string - mode: final - outputColumnNames: _col0, _col1 - Select Operator - expressions: - expr: UDFToInteger(_col0) - type: int - expr: UDFToInteger(_col1) - type: int - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - GlobalTableId: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - - Stage: Stage-4 - Stats-Aggr Operator - - Stage: Stage-5 - Map Reduce - Alias -> Map Operator Tree: -#### A masked pattern was here #### - Reduce Output Operator - key expressions: - expr: _col0 - type: double - sort order: + - Map-reduce partition columns: - expr: _col0 - type: double - tag: -1 - value expressions: - expr: _col1 - type: bigint - Reduce Operator Tree: - Group By Operator - aggregations: - expr: count(VALUE._col0) - bucketGroup: false - keys: - expr: KEY._col0 - type: double - mode: final - outputColumnNames: _col0, _col1 - Select Operator - expressions: - expr: UDFToInteger(_col0) - type: int - expr: UDFToInteger(_col1) - type: int - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - GlobalTableId: 2 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - - Stage: Stage-6 - Stats-Aggr Operator - - -PREHOOK: query: from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1 -PREHOOK: Output: default@dest2 -POSTHOOK: query: from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1 -POSTHOOK: Output: default@dest2 -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -PREHOOK: query: select * from dest1 where key < 10 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest1 where key < 10 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -0 1 -2 1 -4 1 -5 1 -8 1 -9 1 -PREHOOK: query: select * from dest2 where key < 20 order by key limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest2 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest2 where key < 20 order by key limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest2 -#### A masked pattern was here #### -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -0 1 -4 1 -8 1 -10 1 -16 1 -18 1 -PREHOOK: query: -- no need to spray by distinct key first -explain -from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -PREHOOK: type: QUERY -POSTHOOK: query: -- no need to spray by distinct key first -explain -from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -POSTHOOK: type: QUERY -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -ABSTRACT SYNTAX TREE: - (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL value)))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest2))) (TOK_SELECT (TOK_SELEXPR (+ (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL key))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL value)))) (TOK_GROUPBY (+ (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL key))))) - -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Alias -> Map Operator Tree: - src - TableScan - alias: src - Select Operator - expressions: - expr: key - type: string - expr: value - type: string - outputColumnNames: key, value - Group By Operator - aggregations: - expr: count(DISTINCT value) - bucketGroup: false - keys: - expr: key - type: string - expr: value - type: string - mode: hash - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: - expr: _col0 - type: string - expr: _col1 - type: string - sort order: ++ - Map-reduce partition columns: - expr: _col0 - type: string - tag: -1 - value expressions: - expr: _col2 - type: bigint - Select Operator - expressions: - expr: key - type: string - expr: value - type: string - outputColumnNames: key, value - Group By Operator - aggregations: - expr: count(DISTINCT value) - bucketGroup: false - keys: - expr: (key + key) - type: double - expr: value - type: string - mode: hash - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 0 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - Reduce Operator Tree: - Group By Operator - aggregations: - expr: count(DISTINCT KEY._col1:0._col0) - bucketGroup: false - keys: - expr: KEY._col0 - type: string - mode: mergepartial - outputColumnNames: _col0, _col1 - Select Operator - expressions: - expr: UDFToInteger(_col0) - type: int - expr: UDFToInteger(_col1) - type: int - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - GlobalTableId: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - - Stage: Stage-3 - Stats-Aggr Operator - - Stage: Stage-4 - Map Reduce - Alias -> Map Operator Tree: -#### A masked pattern was here #### - Reduce Output Operator - key expressions: - expr: _col0 - type: double - expr: _col1 - type: string - sort order: ++ - Map-reduce partition columns: - expr: _col0 - type: double - tag: -1 - value expressions: - expr: _col2 - type: bigint - Reduce Operator Tree: - Group By Operator - aggregations: - expr: count(DISTINCT KEY._col1:0._col0) - bucketGroup: false - keys: - expr: KEY._col0 - type: double - mode: mergepartial - outputColumnNames: _col0, _col1 - Select Operator - expressions: - expr: UDFToInteger(_col0) - type: int - expr: UDFToInteger(_col1) - type: int - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - GlobalTableId: 2 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - - Stage: Stage-5 - Stats-Aggr Operator - - -PREHOOK: query: from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1 -PREHOOK: Output: default@dest2 -POSTHOOK: query: from src -insert overwrite table dest1 select key, count(distinct value) group by key -insert overwrite table dest2 select key+key, count(distinct value) group by key+key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1 -POSTHOOK: Output: default@dest2 -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -PREHOOK: query: select * from dest1 where key < 10 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest1 where key < 10 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -0 1 -2 1 -4 1 -5 1 -8 1 -9 1 -PREHOOK: query: select * from dest2 where key < 20 order by key limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest2 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest2 where key < 20 order by key limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest2 -#### A masked pattern was here #### -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -0 1 -4 1 -8 1 -10 1 -16 1 -18 1
