http://git-wip-us.apache.org/repos/asf/hive/blob/0d21998e/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out deleted file mode 100644 index 5c40dc4..0000000 --- a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out +++ /dev/null @@ -1,693 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS --- JAVA_VERSION_SPECIFIC_OUTPUT - -EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -POSTHOOK: query: -- SORT_QUERY_RESULTS --- JAVA_VERSION_SPECIFIC_OUTPUT - -EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - 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: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - 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 - TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Select Operator - expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: key, value, ds - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - 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: -#### 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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 -#### 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 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 -#### A masked pattern was here #### - Partition - 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 12 - properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 -#### 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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 -#### A masked pattern was here #### - Partition - 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 12 - properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 - Truncated Path -> Alias: - /src [a] - /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] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Outer Join 0 to 1 - filter mappings: - 1 [0, 1] - filter predicates: - 0 - 1 {(VALUE.ds = '2008-04-08')} - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) - outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 27 Data size: 286 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 key,value,key0,value0 - columns.types string:string: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 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -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 - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -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 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19 -PREHOOK: query: EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - 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: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - 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 - TableScan - alias: b - Statistics: Num rows: 1000 Data size: 10624 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - 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: -#### 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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 -#### 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 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 -#### A masked pattern was here #### - Partition - 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 12 - properties: - COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 - Truncated Path -> Alias: - /src [a] - /srcpart/ds=2008-04-08/hr=11 [b] - /srcpart/ds=2008-04-08/hr=12 [b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) - outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns key,value,key0,value0 - columns.types string:string: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 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -PREHOOK: type: QUERY -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 -#### A masked pattern was here #### -POSTHOOK: query: FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -POSTHOOK: type: QUERY -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 -#### A masked pattern was here #### -17 val_17 17 val_17 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19
http://git-wip-us.apache.org/repos/asf/hive/blob/0d21998e/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out new file mode 100644 index 0000000..200b8ee --- /dev/null +++ b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out @@ -0,0 +1,691 @@ +PREHOOK: query: -- SORT_QUERY_RESULTS + +EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +POSTHOOK: query: -- SORT_QUERY_RESULTS + +EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + 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: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + 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 + TableScan + alias: b + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + 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: +#### 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 +#### 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 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 +#### A masked pattern was here #### + Partition + 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 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 +#### 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 +#### A masked pattern was here #### + Partition + 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 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 + Truncated Path -> Alias: + /src [a] + /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] + Needs Tagging: true + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + filter mappings: + 1 [0, 1] + filter predicates: + 0 + 1 {(VALUE.ds = '2008-04-08')} + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 27 Data size: 286 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 key,value,key0,value0 + columns.types string:string: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 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +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 + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +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 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 +PREHOOK: query: EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + 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: key, value + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + 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 + TableScan + alias: b + Statistics: Num rows: 1000 Data size: 10624 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + 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: +#### 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 +#### 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 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 +#### A masked pattern was here #### + Partition + 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 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 + Truncated Path -> Alias: + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Needs Tagging: true + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + 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.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string: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 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +PREHOOK: type: QUERY +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 +#### A masked pattern was here #### +POSTHOOK: query: FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +POSTHOOK: type: QUERY +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 +#### A masked pattern was here #### +17 val_17 17 val_17 +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 http://git-wip-us.apache.org/repos/asf/hive/blob/0d21998e/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out b/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out deleted file mode 100644 index ee1c2ae..0000000 --- a/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out +++ /dev/null @@ -1,463 +0,0 @@ -PREHOOK: query: drop table char_udf_1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table char_udf_1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@char_udf_1 -POSTHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@char_udf_1 -PREHOOK: query: insert overwrite table char_udf_1 - select key, value, key, value from src where key = '238' limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@char_udf_1 -POSTHOOK: query: insert overwrite table char_udf_1 - select key, value, key, value from src where key = '238' limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@char_udf_1 -POSTHOOK: Lineage: char_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: char_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: char_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: char_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - --- UDFs with char support -select - concat(c1, c2), - concat(c3, c4), - concat(c1, c2) = concat(c3, c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - --- UDFs with char support -select - concat(c1, c2), - concat(c3, c4), - concat(c1, c2) = concat(c3, c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -238val_238 238val_238 true -PREHOOK: query: select - upper(c2), - upper(c4), - upper(c2) = upper(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - upper(c2), - upper(c4), - upper(c2) = upper(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -VAL_238 VAL_238 true -PREHOOK: query: select - lower(c2), - lower(c4), - lower(c2) = lower(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - lower(c2), - lower(c4), - lower(c2) = lower(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 true -PREHOOK: query: -- Scalar UDFs -select - ascii(c2), - ascii(c4), - ascii(c2) = ascii(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: -- Scalar UDFs -select - ascii(c2), - ascii(c4), - ascii(c2) = ascii(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -118 118 true -PREHOOK: query: select - concat_ws('|', c1, c2), - concat_ws('|', c3, c4), - concat_ws('|', c1, c2) = concat_ws('|', c3, c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - concat_ws('|', c1, c2), - concat_ws('|', c3, c4), - concat_ws('|', c1, c2) = concat_ws('|', c3, c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -238|val_238 238|val_238 true -PREHOOK: query: select - decode(encode(c2, 'US-ASCII'), 'US-ASCII'), - decode(encode(c4, 'US-ASCII'), 'US-ASCII'), - decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - decode(encode(c2, 'US-ASCII'), 'US-ASCII'), - decode(encode(c4, 'US-ASCII'), 'US-ASCII'), - decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 true -PREHOOK: query: select - instr(c2, '_'), - instr(c4, '_'), - instr(c2, '_') = instr(c4, '_') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - instr(c2, '_'), - instr(c4, '_'), - instr(c2, '_') = instr(c4, '_') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -4 4 true -PREHOOK: query: select - length(c2), - length(c4), - length(c2) = length(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - length(c2), - length(c4), - length(c2) = length(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -7 7 true -PREHOOK: query: select - locate('a', 'abcdabcd', 3), - locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3), - locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - locate('a', 'abcdabcd', 3), - locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3), - locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -5 5 true -PREHOOK: query: select - lpad(c2, 15, ' '), - lpad(c4, 15, ' '), - lpad(c2, 15, ' ') = lpad(c4, 15, ' ') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - lpad(c2, 15, ' '), - lpad(c4, 15, ' '), - lpad(c2, 15, ' ') = lpad(c4, 15, ' ') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### - val_238 val_238 true -PREHOOK: query: select - ltrim(c2), - ltrim(c4), - ltrim(c2) = ltrim(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - ltrim(c2), - ltrim(c4), - ltrim(c2) = ltrim(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 true -PREHOOK: query: -- In hive wiki page https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF --- we only allow A regexp B, not regexp (A,B). - -select - c2 regexp 'val', - c4 regexp 'val', - (c2 regexp 'val') = (c4 regexp 'val') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: -- In hive wiki page https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF --- we only allow A regexp B, not regexp (A,B). - -select - c2 regexp 'val', - c4 regexp 'val', - (c2 regexp 'val') = (c4 regexp 'val') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -true true true -PREHOOK: query: select - regexp_extract(c2, 'val_([0-9]+)', 1), - regexp_extract(c4, 'val_([0-9]+)', 1), - regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - regexp_extract(c2, 'val_([0-9]+)', 1), - regexp_extract(c4, 'val_([0-9]+)', 1), - regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -238 238 true -PREHOOK: query: select - regexp_replace(c2, 'val', 'replaced'), - regexp_replace(c4, 'val', 'replaced'), - regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - regexp_replace(c2, 'val', 'replaced'), - regexp_replace(c4, 'val', 'replaced'), - regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -replaced_238 replaced_238 true -PREHOOK: query: select - reverse(c2), - reverse(c4), - reverse(c2) = reverse(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - reverse(c2), - reverse(c4), - reverse(c2) = reverse(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -832_lav 832_lav true -PREHOOK: query: select - rpad(c2, 15, ' '), - rpad(c4, 15, ' '), - rpad(c2, 15, ' ') = rpad(c4, 15, ' ') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - rpad(c2, 15, ' '), - rpad(c4, 15, ' '), - rpad(c2, 15, ' ') = rpad(c4, 15, ' ') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 true -PREHOOK: query: select - rtrim(c2), - rtrim(c4), - rtrim(c2) = rtrim(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - rtrim(c2), - rtrim(c4), - rtrim(c2) = rtrim(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 true -PREHOOK: query: select - sentences('See spot run. See jane run.'), - sentences(cast('See spot run. See jane run.' as char(50))) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - sentences('See spot run. See jane run.'), - sentences(cast('See spot run. See jane run.' as char(50))) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -[["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]] -PREHOOK: query: select - split(c2, '_'), - split(c4, '_') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - split(c2, '_'), - split(c4, '_') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -["val","238"] ["val","238"] -PREHOOK: query: select - str_to_map('a:1,b:2,c:3',',',':'), - str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':') -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - str_to_map('a:1,b:2,c:3',',',':'), - str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':') -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -{"b":"2","a":"1","c":"3"} {"b":"2","a":"1","c":"3"} -PREHOOK: query: select - substr(c2, 1, 3), - substr(c4, 1, 3), - substr(c2, 1, 3) = substr(c4, 1, 3) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - substr(c2, 1, 3), - substr(c4, 1, 3), - substr(c2, 1, 3) = substr(c4, 1, 3) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val val true -PREHOOK: query: select - trim(c2), - trim(c4), - trim(c2) = trim(c4) -from char_udf_1 limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - trim(c2), - trim(c4), - trim(c2) = trim(c4) -from char_udf_1 limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 true -PREHOOK: query: -- Aggregate Functions -select - compute_stats(c2, 16), - compute_stats(c4, 16) -from char_udf_1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: -- Aggregate Functions -select - compute_stats(c2, 16), - compute_stats(c4, 16) -from char_udf_1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"} {"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"} -PREHOOK: query: select - min(c2), - min(c4) -from char_udf_1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - min(c2), - min(c4) -from char_udf_1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 -PREHOOK: query: select - max(c2), - max(c4) -from char_udf_1 -PREHOOK: type: QUERY -PREHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -POSTHOOK: query: select - max(c2), - max(c4) -from char_udf_1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@char_udf_1 -#### A masked pattern was here #### -val_238 val_238 -PREHOOK: query: drop table char_udf_1 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@char_udf_1 -PREHOOK: Output: default@char_udf_1 -POSTHOOK: query: drop table char_udf_1 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@char_udf_1 -POSTHOOK: Output: default@char_udf_1