http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out new file mode 100644 index 0000000..fc8eb1c --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out @@ -0,0 +1,216 @@ +PREHOOK: query: DROP TABLE over1k +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE over1k +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE over1korc +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE over1korc +POSTHOOK: type: DROPTABLE +PREHOOK: query: -- data setup +CREATE TABLE over1k(t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' +STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k +POSTHOOK: query: -- data setup +CREATE TABLE over1k(t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' +STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@over1k +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@over1k +PREHOOK: query: CREATE TABLE over1korc(t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) +STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1korc +POSTHOOK: query: CREATE TABLE over1korc(t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) +STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1korc +PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1korc +POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1korc +POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ] +POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ] +POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ] +POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ] +POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ] +POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ] +POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ] +PREHOOK: query: EXPLAIN SELECT + i, + AVG(CAST(50 AS INT)) AS `avg_int_ok`, + AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, + AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` + FROM over1korc GROUP BY i ORDER BY i LIMIT 10 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN SELECT + i, + AVG(CAST(50 AS INT)) AS `avg_int_ok`, + AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, + AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` + FROM over1korc GROUP BY i ORDER BY i LIMIT 10 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: over1korc + Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(50), avg(50.0), avg(50) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4)) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT + i, + AVG(CAST(50 AS INT)) AS `avg_int_ok`, + AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, + AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` + FROM over1korc GROUP BY i ORDER BY i LIMIT 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1korc +#### A masked pattern was here #### +POSTHOOK: query: SELECT + i, + AVG(CAST(50 AS INT)) AS `avg_int_ok`, + AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, + AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` + FROM over1korc GROUP BY i ORDER BY i LIMIT 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1korc +#### A masked pattern was here #### +65536 50.0 50.0 50.0000 +65537 50.0 50.0 50.0000 +65538 50.0 50.0 50.0000 +65539 50.0 50.0 50.0000 +65540 50.0 50.0 50.0000 +65541 50.0 50.0 50.0000 +65542 50.0 50.0 50.0000 +65543 50.0 50.0 50.0000 +65544 50.0 50.0 50.0000 +65545 50.0 50.0 50.0000
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out deleted file mode 100644 index 1312e53..0000000 --- a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out +++ /dev/null @@ -1,685 +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: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (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: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: 1 - 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 - 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 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1: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._col1 = '2008-04-08')} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 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 _col0,_col1,_col2,_col3 - 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: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (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: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 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: 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 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 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 _col0,_col1,_col2,_col3 - 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/9349b8e5/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out deleted file mode 100644 index b9c1a66..0000000 --- a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out +++ /dev/null @@ -1,855 +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 -ABSTRACT SYNTAX TREE: - -TOK_QUERY - TOK_FROM - TOK_FULLOUTERJOIN - TOK_TABREF - TOK_TABNAME - src - a - TOK_TABREF - TOK_TABNAME - srcpart - b - AND - = - . - TOK_TABLE_OR_COL - a - key - . - TOK_TABLE_OR_COL - b - key - = - . - TOK_TABLE_OR_COL - b - ds - '2008-04-08' - TOK_INSERT - TOK_DESTINATION - TOK_DIR - TOK_TMP_FILE - TOK_SELECT - TOK_SELEXPR - . - TOK_TABLE_OR_COL - a - key - TOK_SELEXPR - . - TOK_TABLE_OR_COL - a - value - TOK_SELEXPR - . - TOK_TABLE_OR_COL - b - key - TOK_SELEXPR - . - TOK_TABLE_OR_COL - b - value - TOK_WHERE - AND - AND - AND - > - . - TOK_TABLE_OR_COL - a - key - 10 - < - . - TOK_TABLE_OR_COL - a - key - 20 - > - . - TOK_TABLE_OR_COL - b - key - 15 - < - . - TOK_TABLE_OR_COL - b - key - 25 - - -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: 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: _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 - 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: 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 -#### 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 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 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 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 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 [$hdt$_0:$hdt$_1:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:b] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:$hdt$_0:b] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:$hdt$_0:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Outer Join 0 to 1 - filter mappings: - 0 [1, 1] - filter predicates: - 0 {(VALUE._col1 = '2008-04-08')} - 1 - keys: - 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: ((((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) and (UDFToDouble(_col0) > 15.0)) and (UDFToDouble(_col0) < 25.0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 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: 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 _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.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 - 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 -ABSTRACT SYNTAX TREE: - -TOK_QUERY - TOK_FROM - TOK_FULLOUTERJOIN - TOK_TABREF - TOK_TABNAME - src - a - TOK_TABREF - TOK_TABNAME - srcpart - b - = - . - TOK_TABLE_OR_COL - a - key - . - TOK_TABLE_OR_COL - b - key - TOK_INSERT - TOK_DESTINATION - TOK_DIR - TOK_TMP_FILE - TOK_SELECT - TOK_SELEXPR - . - TOK_TABLE_OR_COL - a - key - TOK_SELEXPR - . - TOK_TABLE_OR_COL - a - value - TOK_SELEXPR - . - TOK_TABLE_OR_COL - b - key - TOK_SELEXPR - . - TOK_TABLE_OR_COL - b - value - TOK_WHERE - AND - AND - AND - AND - > - . - TOK_TABLE_OR_COL - a - key - 10 - < - . - TOK_TABLE_OR_COL - a - key - 20 - > - . - TOK_TABLE_OR_COL - b - key - 15 - < - . - TOK_TABLE_OR_COL - b - key - 25 - = - . - TOK_TABLE_OR_COL - b - ds - '2008-04-08' - - -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: 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: _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 - 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 #### - 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 -#### 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 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 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 [$hdt$_0:$hdt$_1:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 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: ((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: _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 - 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 _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.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 - 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