http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/outer_join_ppr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.out new file mode 100644 index 0000000..cf20851 --- /dev/null +++ b/ql/src/test/results/clientpositive/outer_join_ppr.q.out @@ -0,0 +1,683 @@ +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: _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 {"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 [$hdt$_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 {"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 [$hdt$_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/22541610/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out b/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out deleted file mode 100644 index 825e668..0000000 --- a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out +++ /dev/null @@ -1,70 +0,0 @@ -PREHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values --- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE IF EXISTS avro_table -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values --- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE IF EXISTS avro_table -POSTHOOK: type: DROPTABLE -PREHOOK: query: DROP TABLE IF EXISTS parquet_table -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS parquet_table -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@avro_table -POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@avro_table -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@avro_table -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@avro_table -PREHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@avro_table -PREHOOK: Output: database:default -PREHOOK: Output: default@parquet_table -POSTHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@avro_table -POSTHOOK: Output: database:default -POSTHOOK: Output: default@parquet_table -POSTHOOK: Lineage: parquet_table.avreau_col_1 SIMPLE [(avro_table)avro_table.FieldSchema(name:avreau_col_1, type:map<string,string>, comment:), ] -PREHOOK: query: SELECT * FROM parquet_table -PREHOOK: type: QUERY -PREHOOK: Input: default@parquet_table -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM parquet_table -POSTHOOK: type: QUERY -POSTHOOK: Input: default@parquet_table -#### A masked pattern was here #### -{"key4":null,"key3":"val3"} -{"key4":null,"key3":"val3"} -{"key2":"val2","key1":null} -{"key4":null,"key3":"val3"} -{"key4":null,"key3":"val3"} -PREHOOK: query: DROP TABLE avro_table -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@avro_table -PREHOOK: Output: default@avro_table -POSTHOOK: query: DROP TABLE avro_table -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@avro_table -POSTHOOK: Output: default@avro_table -PREHOOK: query: DROP TABLE parquet_table -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@parquet_table -PREHOOK: Output: default@parquet_table -POSTHOOK: query: DROP TABLE parquet_table -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@parquet_table -POSTHOOK: Output: default@parquet_table http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out b/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out deleted file mode 100644 index 1462cc2..0000000 --- a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out +++ /dev/null @@ -1,70 +0,0 @@ -PREHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values --- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE IF EXISTS avro_table -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values --- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE IF EXISTS avro_table -POSTHOOK: type: DROPTABLE -PREHOOK: query: DROP TABLE IF EXISTS parquet_table -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS parquet_table -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@avro_table -POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@avro_table -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@avro_table -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@avro_table -PREHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@avro_table -PREHOOK: Output: database:default -PREHOOK: Output: default@parquet_table -POSTHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@avro_table -POSTHOOK: Output: database:default -POSTHOOK: Output: default@parquet_table -POSTHOOK: Lineage: parquet_table.avreau_col_1 SIMPLE [(avro_table)avro_table.FieldSchema(name:avreau_col_1, type:map<string,string>, comment:), ] -PREHOOK: query: SELECT * FROM parquet_table -PREHOOK: type: QUERY -PREHOOK: Input: default@parquet_table -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM parquet_table -POSTHOOK: type: QUERY -POSTHOOK: Input: default@parquet_table -#### A masked pattern was here #### -{"key3":"val3","key4":null} -{"key3":"val3","key4":null} -{"key1":null,"key2":"val2"} -{"key3":"val3","key4":null} -{"key3":"val3","key4":null} -PREHOOK: query: DROP TABLE avro_table -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@avro_table -PREHOOK: Output: default@avro_table -POSTHOOK: query: DROP TABLE avro_table -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@avro_table -POSTHOOK: Output: default@avro_table -PREHOOK: query: DROP TABLE parquet_table -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@parquet_table -PREHOOK: Output: default@parquet_table -POSTHOOK: query: DROP TABLE parquet_table -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@parquet_table -POSTHOOK: Output: default@parquet_table http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/parquet_map_null.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/parquet_map_null.q.out b/ql/src/test/results/clientpositive/parquet_map_null.q.out new file mode 100644 index 0000000..d1357c1 --- /dev/null +++ b/ql/src/test/results/clientpositive/parquet_map_null.q.out @@ -0,0 +1,68 @@ +PREHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values + +DROP TABLE IF EXISTS avro_table +PREHOOK: type: DROPTABLE +POSTHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values + +DROP TABLE IF EXISTS avro_table +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE IF EXISTS parquet_table +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS parquet_table +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@avro_table +POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@avro_table +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@avro_table +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@avro_table +PREHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@avro_table +PREHOOK: Output: database:default +PREHOOK: Output: default@parquet_table +POSTHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@avro_table +POSTHOOK: Output: database:default +POSTHOOK: Output: default@parquet_table +POSTHOOK: Lineage: parquet_table.avreau_col_1 SIMPLE [(avro_table)avro_table.FieldSchema(name:avreau_col_1, type:map<string,string>, comment:), ] +PREHOOK: query: SELECT * FROM parquet_table +PREHOOK: type: QUERY +PREHOOK: Input: default@parquet_table +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM parquet_table +POSTHOOK: type: QUERY +POSTHOOK: Input: default@parquet_table +#### A masked pattern was here #### +{"key3":"val3","key4":null} +{"key3":"val3","key4":null} +{"key1":null,"key2":"val2"} +{"key3":"val3","key4":null} +{"key3":"val3","key4":null} +PREHOOK: query: DROP TABLE avro_table +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@avro_table +PREHOOK: Output: default@avro_table +POSTHOOK: query: DROP TABLE avro_table +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@avro_table +POSTHOOK: Output: default@avro_table +PREHOOK: query: DROP TABLE parquet_table +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@parquet_table +PREHOOK: Output: default@parquet_table +POSTHOOK: query: DROP TABLE parquet_table +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@parquet_table +POSTHOOK: Output: default@parquet_table http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/plan_json.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/plan_json.q.java1.7.out b/ql/src/test/results/clientpositive/plan_json.q.java1.7.out deleted file mode 100644 index dda4adc..0000000 --- a/ql/src/test/results/clientpositive/plan_json.q.java1.7.out +++ /dev/null @@ -1,13 +0,0 @@ -PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query - --- JAVA_VERSION_SPECIFIC_OUTPUT - -EXPLAIN FORMATTED SELECT count(1) FROM src -PREHOOK: type: QUERY -POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query - --- JAVA_VERSION_SPECIFIC_OUTPUT - -EXPLAIN FORMATTED SELECT count(1) FROM src -POSTHOOK: type: QUERY -{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Group By Operator":{"aggregations:":["count(1)"],"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)"}}}}}}}}],"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","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-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}} http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/plan_json.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/plan_json.q.java1.8.out b/ql/src/test/results/clientpositive/plan_json.q.java1.8.out deleted file mode 100644 index dda4adc..0000000 --- a/ql/src/test/results/clientpositive/plan_json.q.java1.8.out +++ /dev/null @@ -1,13 +0,0 @@ -PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query - --- JAVA_VERSION_SPECIFIC_OUTPUT - -EXPLAIN FORMATTED SELECT count(1) FROM src -PREHOOK: type: QUERY -POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query - --- JAVA_VERSION_SPECIFIC_OUTPUT - -EXPLAIN FORMATTED SELECT count(1) FROM src -POSTHOOK: type: QUERY -{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Group By Operator":{"aggregations:":["count(1)"],"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)"}}}}}}}}],"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","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-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}} http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/plan_json.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/plan_json.q.out b/ql/src/test/results/clientpositive/plan_json.q.out new file mode 100644 index 0000000..98c6626 --- /dev/null +++ b/ql/src/test/results/clientpositive/plan_json.q.out @@ -0,0 +1,11 @@ +PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query + + +EXPLAIN FORMATTED SELECT count(1) FROM src +PREHOOK: type: QUERY +POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query + + +EXPLAIN FORMATTED SELECT count(1) FROM src +POSTHOOK: type: QUERY +{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Group By Operator":{"aggregations:":["count(1)"],"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)"}}}}}}}}],"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","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-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}} http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out b/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out deleted file mode 100644 index b3a58d0..0000000 --- a/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out +++ /dev/null @@ -1,238 +0,0 @@ -Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Map 4 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - sort order: ++++ - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 182 Data size: 1939 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: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product -PREHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -#### A masked pattern was here #### -Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product -PREHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 9 val_9 -0 val_0 9 val_9 -0 val_0 9 val_9 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 2 val_2 -2 val_2 4 val_4 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 8 val_8 -2 val_2 9 val_9 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 2 val_2 -4 val_4 4 val_4 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 8 val_8 -4 val_4 9 val_9 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 9 val_9 -5 val_5 9 val_9 -5 val_5 9 val_9 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 2 val_2 -8 val_8 4 val_4 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 8 val_8 -8 val_8 9 val_9 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 2 val_2 -9 val_9 4 val_4 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 8 val_8 -9 val_9 9 val_9 http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out b/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out deleted file mode 100644 index 7acd108..0000000 --- a/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out +++ /dev/null @@ -1,238 +0,0 @@ -Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Map 4 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - sort order: ++++ - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product -PREHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -#### A masked pattern was here #### -Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product -PREHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 9 val_9 -0 val_0 9 val_9 -0 val_0 9 val_9 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 2 val_2 -2 val_2 4 val_4 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 8 val_8 -2 val_2 9 val_9 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 2 val_2 -4 val_4 4 val_4 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 8 val_8 -4 val_4 9 val_9 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 9 val_9 -5 val_5 9 val_9 -5 val_5 9 val_9 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 2 val_2 -8 val_8 4 val_4 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 8 val_8 -8 val_8 9 val_9 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 2 val_2 -9 val_9 4 val_4 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 8 val_8 -9 val_9 9 val_9 http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/spark/join0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/join0.q.out b/ql/src/test/results/clientpositive/spark/join0.q.out index 56b154f..bc98bb4 100644 --- a/ql/src/test/results/clientpositive/spark/join0.q.out +++ b/ql/src/test/results/clientpositive/spark/join0.q.out @@ -1,5 +1,7 @@ Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product -PREHOOK: query: EXPLAIN +PREHOOK: query: -- SORT_QUERY_RESULTS + +EXPLAIN SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM (SELECT * FROM src WHERE src.key < 10) src1 @@ -7,7 +9,9 @@ SELECT src1.key as k1, src1.value as v1, (SELECT * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN +POSTHOOK: query: -- SORT_QUERY_RESULTS + +EXPLAIN SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM (SELECT * FROM src WHERE src.key < 10) src1 @@ -24,7 +28,7 @@ STAGE PLANS: Spark Edges: Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (SORT, 1) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 4) #### A masked pattern was here #### Vertices: Map 1 @@ -64,9 +68,9 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - condition expressions: - 0 {VALUE._col0} {VALUE._col1} - 1 {VALUE._col0} {VALUE._col1} + keys: + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -83,8 +87,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out b/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out deleted file mode 100644 index 3040544..0000000 --- a/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out +++ /dev/null @@ -1,252 +0,0 @@ -PREHOOK: query: -- run this test case in minimr to ensure it works in cluster --- JAVA_VERSION_SPECIFIC_OUTPUT - --- list bucketing DML: static partition. multiple skewed columns. --- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: --- 5263 000000_0 --- 5263 000001_0 --- ds=2008-04-08/hr=11/key=103/value=val_103: --- 99 000000_0 --- 99 000001_0 --- ds=2008-04-08/hr=11/key=484/value=val_484: --- 87 000000_0 --- 87 000001_0 - --- create a skewed table -create table list_bucketing_static_part (key String, value String) - partitioned by (ds String, hr String) - skewed by (key) on ('484','51','103') - stored as DIRECTORIES - STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@list_bucketing_static_part -POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster --- JAVA_VERSION_SPECIFIC_OUTPUT - --- list bucketing DML: static partition. multiple skewed columns. --- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: --- 5263 000000_0 --- 5263 000001_0 --- ds=2008-04-08/hr=11/key=103/value=val_103: --- 99 000000_0 --- 99 000001_0 --- ds=2008-04-08/hr=11/key=484/value=val_484: --- 87 000000_0 --- 87 000001_0 - --- create a skewed table -create table list_bucketing_static_part (key String, value String) - partitioned by (ds String, hr String) - skewed by (key) on ('484','51','103') - stored as DIRECTORIES - STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@list_bucketing_static_part -PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. -explain extended -insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') -select key, value from src -PREHOOK: type: QUERY -POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. -explain extended -insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') -select key, value from src -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - 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 - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.list_bucketing_static_part - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct list_bucketing_static_part { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.list_bucketing_static_part - TotalFiles: 1 - GatherStats: true - MultiFileSpray: 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 - Truncated Path -> Alias: - /src [src] - - Stage: Stage-0 - Move Operator - tables: - partition: - ds 2008-04-08 - hr 11 - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.list_bucketing_static_part - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct list_bucketing_static_part { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.list_bucketing_static_part - - Stage: Stage-2 - Stats-Aggr Operator -#### A masked pattern was here #### - -PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') -select key, value from src -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 -POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') -select key, value from src -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 -POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: -- check DML result -show partitions list_bucketing_static_part -PREHOOK: type: SHOWPARTITIONS -PREHOOK: Input: default@list_bucketing_static_part -POSTHOOK: query: -- check DML result -show partitions list_bucketing_static_part -POSTHOOK: type: SHOWPARTITIONS -POSTHOOK: Input: default@list_bucketing_static_part -ds=2008-04-08/hr=11 -PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@list_bucketing_static_part -POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@list_bucketing_static_part -# col_name data_type comment - -key string -value string - -# Partition Information -# col_name data_type comment - -ds string -hr string - -# Detailed Partition Information -Partition Value: [2008-04-08, 11] -Database: default -Table: list_bucketing_static_part -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 4 - numRows 500 - rawDataSize 4812 - totalSize 5520 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe -InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat -Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] -Stored As SubDirectories: Yes -Skewed Columns: [key] -Skewed Values: [[484], [51], [103]] -#### A masked pattern was here #### -Skewed Value to Truncated Path: {[484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484, [103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51} -Storage Desc Params: - serialization.format 1
