http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out b/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out new file mode 100644 index 0000000..f6ddfe9 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out @@ -0,0 +1,1697 @@ +PREHOOK: query: CREATE TABLE srcbucket_pruned(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 16 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_pruned +POSTHOOK: query: CREATE TABLE srcbucket_pruned(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 16 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_pruned +PREHOOK: query: -- cannot prune 2-key scenarios without a smarter optimizer +CREATE TABLE srcbucket_unpruned(key int, value string) partitioned by (ds string) CLUSTERED BY (key,value) INTO 16 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_unpruned +POSTHOOK: query: -- cannot prune 2-key scenarios without a smarter optimizer +CREATE TABLE srcbucket_unpruned(key int, value string) partitioned by (ds string) CLUSTERED BY (key,value) INTO 16 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_unpruned +PREHOOK: query: -- good cases + +explain extended +select * from srcbucket_pruned where key = 1 +PREHOOK: type: QUERY +POSTHOOK: query: -- good cases + +explain extended +select * from srcbucket_pruned where key = 1 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key = 1) (type: boolean) + buckets included: [1,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 1) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 1 (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 16 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 16 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key = 16) (type: boolean) + buckets included: [0,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 16) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 16 (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 17 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 17 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key = 17) (type: boolean) + buckets included: [1,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 17) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 17 (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 16+1 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 16+1 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key = 17) (type: boolean) + buckets included: [1,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 17) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 17 (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = '11' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = '11' +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key = 11) (type: boolean) + buckets included: [11,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 11) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 11 (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key = 1) and (ds = '2008-04-08')) (type: boolean) + buckets included: [1,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 1 (type: int), value (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 and ds='2008-04-08' and value='One' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 and ds='2008-04-08' and value='One' +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key = 1) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) + buckets included: [1,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 1 (type: int), 'One' (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where value='One' and key = 1 and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where value='One' and key = 1 and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((value = 'One') and (key = 1) and (ds = '2008-04-08')) (type: boolean) + buckets included: [1,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((value = 'One') and (key = 1) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 1 (type: int), 'One' (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key in (2,3) +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key in (2,3) +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key) IN (2, 3) (type: boolean) + buckets included: [2,3,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key) IN (2, 3) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key in (2,3) and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key in (2,3) and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key) IN (2, 3) and (ds = '2008-04-08')) (type: boolean) + buckets included: [2,3,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key) IN (2, 3) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key in (2,3) and ds='2008-04-08' and value='One' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key in (2,3) and ds='2008-04-08' and value='One' +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key) IN (2, 3) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) + buckets included: [2,3,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key) IN (2, 3) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where value='One' and key in (2,3) and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where value='One' and key in (2,3) and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key) IN (2, 3) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) + buckets included: [2,3,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key) IN (2, 3) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where (key=1 or key=2) and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where (key=1 or key=2) and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (((key = 1) or (key = 2)) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((key = 1) or (key = 2)) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where (key=1 or key=2) and value = 'One' and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where (key=1 or key=2) and value = 'One' and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (((key = 1) or (key = 2)) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((key = 1) or (key = 2)) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: -- compat case (-15 = 1 & 15) + +explain extended +select * from srcbucket_pruned where key = -15 +PREHOOK: type: QUERY +POSTHOOK: query: -- compat case (-15 = 1 & 15) + +explain extended +select * from srcbucket_pruned where key = -15 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key = -15) (type: boolean) + buckets included: [1,15,] of 16 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = -15) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: -15 (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: -- valid but irrelevant case (all buckets selected) + +explain extended +select * from srcbucket_pruned where key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) +PREHOOK: type: QUERY +POSTHOOK: query: -- valid but irrelevant case (all buckets selected) + +explain extended +select * from srcbucket_pruned where key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) and ds='2008-04-08' and value='One' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) and ds='2008-04-08' and value='One' +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where value='One' and key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) and ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where value='One' and key in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) and 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 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: -- valid, but unimplemented cases + +explain extended +select * from srcbucket_pruned where key = 1 and ds='2008-04-08' or key = 2 +PREHOOK: type: QUERY +POSTHOOK: query: -- valid, but unimplemented cases + +explain extended +select * from srcbucket_pruned where key = 1 and ds='2008-04-08' or key = 2 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: (((key = 1) and (ds = '2008-04-08')) or (key = 2)) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((key = 1) and (ds = '2008-04-08')) or (key = 2)) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 and ds='2008-04-08' and (value='One' or value = 'Two') +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 and ds='2008-04-08' and (value='One' or value = 'Two') +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key = 1) and (ds = '2008-04-08') and ((value = 'One') or (value = 'Two'))) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) and (ds = '2008-04-08') and ((value = 'One') or (value = 'Two'))) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 1 (type: int), value (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 or value = "One" or key = 2 and value = "Two" +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 or value = "One" or key = 2 and value = "Two" +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key = 1) or (value = 'One') or ((key = 2) and (value = 'Two'))) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) or (value = 'One') or ((key = 2) and (value = 'Two'))) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: -- Invalid cases + +explain extended +select * from srcbucket_pruned where key = 'x11' +PREHOOK: type: QUERY +POSTHOOK: query: -- Invalid cases + +explain extended +select * from srcbucket_pruned where key = 'x11' +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: false (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 or value = "One" +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 or value = "One" +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key = 1) or (value = 'One')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) or (value = 'One')) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 or value = "One" or key = 2 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_pruned where key = 1 or value = "One" or key = 2 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_pruned + filterExpr: ((key = 1) or (value = 'One') or (key = 2)) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) or (value = 'One') or (key = 2)) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_unpruned where key in (3, 5) +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_unpruned where key in (3, 5) +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_unpruned + filterExpr: (key) IN (3, 5) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key) IN (3, 5) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * from srcbucket_unpruned where key = 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from srcbucket_unpruned where key = 1 +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 #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcbucket_unpruned + filterExpr: (key = 1) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 1) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: 1 (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL +#### 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 + columns.types int: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 + Execution mode: llap + LLAP IO: unknown + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +
http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/column_names_with_leading_and_trailing_spaces.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/column_names_with_leading_and_trailing_spaces.q.out b/ql/src/test/results/clientpositive/llap/column_names_with_leading_and_trailing_spaces.q.out new file mode 100644 index 0000000..18314b5 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/column_names_with_leading_and_trailing_spaces.q.out @@ -0,0 +1,85 @@ +PREHOOK: query: create table space (` left` string, ` middle ` string, `right ` string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@space +POSTHOOK: query: create table space (` left` string, ` middle ` string, `right ` string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@space +PREHOOK: query: desc formatted space +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@space +POSTHOOK: query: desc formatted space +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@space +# col_name data_type comment + + left string + middle string +right string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 0 + numRows 0 + rawDataSize 0 + totalSize 0 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: insert into space values ("1", "2", "3") +PREHOOK: type: QUERY +PREHOOK: Input: default@values__tmp__table__1 +PREHOOK: Output: default@space +POSTHOOK: query: insert into space values ("1", "2", "3") +POSTHOOK: type: QUERY +POSTHOOK: Input: default@values__tmp__table__1 +POSTHOOK: Output: default@space +POSTHOOK: Lineage: space. left SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: space. middle SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: space.right SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col3, type:string, comment:), ] +PREHOOK: query: select * from space +PREHOOK: type: QUERY +PREHOOK: Input: default@space +#### A masked pattern was here #### +POSTHOOK: query: select * from space +POSTHOOK: type: QUERY +POSTHOOK: Input: default@space +#### A masked pattern was here #### +1 2 3 +PREHOOK: query: insert into space (` middle `) values("2") +PREHOOK: type: QUERY +PREHOOK: Input: default@values__tmp__table__2 +PREHOOK: Output: default@space +POSTHOOK: query: insert into space (` middle `) values("2") +POSTHOOK: type: QUERY +POSTHOOK: Input: default@values__tmp__table__2 +POSTHOOK: Output: default@space +POSTHOOK: Lineage: space. left SIMPLE [] +POSTHOOK: Lineage: space. middle SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: space.right SIMPLE [] +PREHOOK: query: select * from space order by ` left` +PREHOOK: type: QUERY +PREHOOK: Input: default@space +#### A masked pattern was here #### +POSTHOOK: query: select * from space order by ` left` +POSTHOOK: type: QUERY +POSTHOOK: Input: default@space +#### A masked pattern was here #### +NULL 2 NULL +1 2 3
