http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out index 78cd4bc..190485f 100644 --- a/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out @@ -118,29 +118,36 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: src + base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -148,11 +155,13 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src + name default.srcpart numFiles 1 numRows 500 + partition_columns ds/hr + partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct src { string key, string value} + serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -162,55 +171,29 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [a] - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: + name: default.srcpart + name: default.srcpart #### A masked pattern was here #### Partition - base file name: hr=11 + base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 - hr 11 + hr 12 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -249,14 +232,39 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: #### A masked pattern was here #### Partition - base file name: hr=12 + base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -264,13 +272,11 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart + name default.src numFiles 1 numRows 500 - partition_columns ds/hr - partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -280,41 +286,43 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: + COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + name: default.src + name: default.src Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [b] - /srcpart/ds=2008-04-08/hr=12 [b] + /src [a] Reducer 2 Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Right Outer Join0 to 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col5 > 15) and (_col5 < 25)) (type: boolean) + predicate: ((UDFToDouble(_col0) > 15.0) and (UDFToDouble(_col0) < 25.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -504,16 +512,20 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string), ds (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -714,16 +726,20 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -785,16 +801,16 @@ STAGE PLANS: 0 {(VALUE._col1 = '2008-04-08')} 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col7, _col8 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col7 > 15) and (_col7 < 25)) (type: boolean) + predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col7 (type: string), _col8 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -983,88 +999,25 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [a] - Map 3 - Map Operator Tree: - TableScan alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string), ds (type: string) - auto parallelism: false + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1160,60 +1113,39 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + Path -> Alias: #### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + Path -> Partition: #### A masked pattern was here #### Partition - base file name: hr=12 + base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -1221,13 +1153,11 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart + name default.src numFiles 1 numRows 500 - partition_columns ds/hr - partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -1237,66 +1167,62 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: + COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + name: default.src + name: default.src Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [b] - /srcpart/ds=2008-04-08/hr=12 [b] - /srcpart/ds=2008-04-09/hr=11 [b] - /srcpart/ds=2008-04-09/hr=12 [b] + /src [a] Reducer 2 Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Inner Join 0 to 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6, _col7 - Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: (((_col5 > 15) and (_col5 < 25)) and (_col7 = '2008-04-08')) (type: boolean) - Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels 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 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels 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 Fetch Operator @@ -1316,8 +1242,6 @@ PREHOOK: Input: default@src PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: FROM src a @@ -1331,8 +1255,6 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 17 val_17 17 val_17 17 val_17 17 val_17 @@ -1467,16 +1389,20 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1583,16 +1509,20 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((key > 10) and (key < 20)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1649,16 +1579,16 @@ STAGE PLANS: condition map: Left Outer Join0 to 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col7, _col8 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((_col7 > 15) and (_col7 < 25)) (type: boolean) + predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col7 (type: string), _col8 (type: string) + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/merge1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/merge1.q.out b/ql/src/test/results/clientpositive/spark/merge1.q.out index 41acbdb..e594d47 100644 --- a/ql/src/test/results/clientpositive/spark/merge1.q.out +++ b/ql/src/test/results/clientpositive/spark/merge1.q.out @@ -42,11 +42,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/merge2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/merge2.q.out b/ql/src/test/results/clientpositive/spark/merge2.q.out index edeebb7..63274eb 100644 --- a/ql/src/test/results/clientpositive/spark/merge2.q.out +++ b/ql/src/test/results/clientpositive/spark/merge2.q.out @@ -42,11 +42,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out index 0ccae50..18e1d4e 100644 --- a/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out @@ -200,10 +200,10 @@ STAGE PLANS: Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) - outputColumnNames: s, bo, bin, si, i, b + outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(s), count(bo), count(bin), count(si), max(i), min(b) + aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE @@ -256,10 +256,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) - outputColumnNames: s, bo, bin, si, i, b + outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(s), count(bo), count(bin), count(si), max(i), min(b) + aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE @@ -448,10 +448,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: ts + outputColumnNames: _col0 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(ts) + aggregations: count(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/order2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/order2.q.out b/ql/src/test/results/clientpositive/spark/order2.q.out index 22b1ddc..29eb835 100644 --- a/ql/src/test/results/clientpositive/spark/order2.q.out +++ b/ql/src/test/results/clientpositive/spark/order2.q.out @@ -43,7 +43,7 @@ STAGE PLANS: Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 < 10) (type: boolean) + predicate: (UDFToDouble(_col0) < 10.0) (type: boolean) Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out index 227886b..0614cb9 100644 --- a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out +++ b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out @@ -120,25 +120,32 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: src + base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -146,11 +153,13 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src + name default.srcpart numFiles 1 numRows 500 + partition_columns ds/hr + partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct src { string key, string value} + serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -160,51 +169,29 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [a] - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string), ds (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: + name: default.srcpart + name: default.srcpart #### A masked pattern was here #### Partition - base file name: hr=11 + base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 - hr 11 + hr 12 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -245,12 +232,12 @@ STAGE PLANS: name: default.srcpart #### A masked pattern was here #### Partition - base file name: hr=12 + base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: - ds 2008-04-08 - hr 12 + ds 2008-04-09 + hr 11 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -291,12 +278,12 @@ STAGE PLANS: name: default.srcpart #### A masked pattern was here #### Partition - base file name: hr=11 + base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-09 - hr 11 + hr 12 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -335,14 +322,37 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + /srcpart/ds=2008-04-09/hr=11 [b] + /srcpart/ds=2008-04-09/hr=12 [b] + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: #### A masked pattern was here #### Partition - base file name: hr=12 + base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -350,13 +360,11 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart + name default.src numFiles 1 numRows 500 - partition_columns ds/hr - partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -366,26 +374,26 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: + COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + name: default.src + name: default.src Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [b] - /srcpart/ds=2008-04-08/hr=12 [b] - /srcpart/ds=2008-04-09/hr=11 [b] - /srcpart/ds=2008-04-09/hr=12 [b] + /src [a] Reducer 2 Needs Tagging: true Reduce Operator Tree: @@ -393,21 +401,21 @@ STAGE PLANS: condition map: Outer Join 0 to 1 filter mappings: - 1 [0, 1] + 0 [1, 1] filter predicates: - 0 - 1 {(VALUE._col1 = '2008-04-08')} + 0 {(VALUE._col1 = '2008-04-08')} + 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((_col5 > 15) and (_col5 < 25)) and (_col0 > 10)) and (_col0 < 20)) (type: boolean) + predicate: ((((UDFToDouble(_col0) > 15.0) and (UDFToDouble(_col0) < 25.0)) and (UDFToDouble(_col3) > 10.0)) and (UDFToDouble(_col3) < 20.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -596,80 +604,25 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [a] - Map 3 - Map Operator Tree: - TableScan alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: string), ds (type: string) - auto parallelism: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -765,60 +718,39 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: false + Path -> Alias: #### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + Path -> Partition: #### A masked pattern was here #### Partition - base file name: hr=12 + base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -826,13 +758,11 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart + name default.src numFiles 1 numRows 500 - partition_columns ds/hr - partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -842,43 +772,43 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: + COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + name: default.src + name: default.src Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [b] - /srcpart/ds=2008-04-08/hr=12 [b] - /srcpart/ds=2008-04-09/hr=11 [b] - /srcpart/ds=2008-04-09/hr=12 [b] + /src [a] Reducer 2 Needs Tagging: true Reduce Operator Tree: Join Operator condition map: - Outer Join 0 to 1 + Left Outer Join0 to 1 keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6, _col7 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (((((_col5 > 15) and (_col5 < 25)) and (_col7 = '2008-04-08')) and (_col0 > 10)) and (_col0 < 20)) (type: boolean) + predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -921,8 +851,6 @@ PREHOOK: Input: default@src PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: FROM src a @@ -936,8 +864,6 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 17 val_17 17 val_17 17 val_17 17 val_17
