hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From kgyrtk...@apache.org
Subject [21/54] [partial] hive git commit: HIVE-17550: Remove unreferenced q.out-s (Zoltan Haindrich, reviewed by Ashutosh Chauhan)
Date Thu, 21 Sep 2017 09:06:58 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/correlationoptimizer1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/correlationoptimizer1.q.out b/ql/src/test/results/clientpositive/correlationoptimizer1.q.out
deleted file mode 100644
index 65b0ca5..0000000
--- a/ql/src/test/results/clientpositive/correlationoptimizer1.q.out
+++ /dev/null
@@ -1,3091 +0,0 @@
-PREHOOK: query: -- This query has a GroupByOperator folling JoinOperator and they share the same keys.
--- When Correlation Optimizer is turned off, three MR jobs will be generated.
--- When Correlation Optimizer is turned on, two MR jobs will be generated
--- and JoinOperator (on the column of key) and GroupByOperator (also on the column
--- of key) will be executed in the first MR job.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- This query has a GroupByOperator folling JoinOperator and they share the same keys.
--- When Correlation Optimizer is turned off, three MR jobs will be generated.
--- When Correlation Optimizer is turned on, two MR jobs will be generated
--- and JoinOperator (on the column of key) and GroupByOperator (also on the column
--- of key) will be executed in the first MR job.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(1)
-            keys: _col0 (type: string)
-            mode: hash
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	37
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Join Operator
-            condition map:
-                 Inner Join 0 to 1
-            keys:
-              0 _col0 (type: string)
-              1 _col0 (type: string)
-            outputColumnNames: _col0
-            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                aggregations: count(1)
-                keys: _col0 (type: string)
-                mode: complete
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1)
-                    mode: hash
-                    outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	37
-PREHOOK: query: -- Enable hive.auto.convert.join.
--- Correlation Optimizer will detect that the join will be converted to a Map-join,
--- so it will not try to optimize this query.
--- We should generate 1 MR job for subquery tmp.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- Enable hive.auto.convert.join.
--- Correlation Optimizer will detect that the join will be converted to a Map-join,
--- so it will not try to optimize this query.
--- We should generate 1 MR job for subquery tmp.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-6 is a root stage
-  Stage-2 depends on stages: Stage-6
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-6
-    Map Reduce Local Work
-      Alias -> Map Local Tables:
-        $hdt$_0:$hdt$_0:$hdt$_0:x 
-          Fetch Operator
-            limit: -1
-      Alias -> Map Local Operator Tree:
-        $hdt$_0:$hdt$_0:$hdt$_0:x 
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                HashTable Sink Operator
-                  keys:
-                    0 _col0 (type: string)
-                    1 _col0 (type: string)
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Map Join Operator
-                  condition map:
-                       Inner Join 0 to 1
-                  keys:
-                    0 _col0 (type: string)
-                    1 _col0 (type: string)
-                  outputColumnNames: _col0
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count(1)
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: _col0 (type: string)
-                      sort order: +
-                      Map-reduce partition columns: _col0 (type: string)
-                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col1 (type: bigint)
-      Local Work:
-        Map Reduce Local Work
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	37
-PREHOOK: query: -- If the key of a GroupByOperator is the left table's key in
--- a Left Semi Join, these two operators will be executed in
--- the same MR job when Correlation Optimizer is enabled.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- If the key of a GroupByOperator is the left table's key in
--- a Left Semi Join, these two operators will be executed in
--- the same MR job when Correlation Optimizer is enabled.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Group By Operator
-                  keys: _col0 (type: string)
-                  mode: hash
-                  outputColumnNames: _col0
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Semi Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(1)
-            keys: _col0 (type: string)
-            mode: hash
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	15
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: key is not null (type: boolean)
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Group By Operator
-                  keys: _col0 (type: string)
-                  mode: hash
-                  outputColumnNames: _col0
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Join Operator
-            condition map:
-                 Left Semi Join 0 to 1
-            keys:
-              0 _col0 (type: string)
-              1 _col0 (type: string)
-            outputColumnNames: _col0
-            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                aggregations: count(1)
-                keys: _col0 (type: string)
-                mode: complete
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1)
-                    mode: hash
-                    outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	15
-PREHOOK: query: -- If the key of a GroupByOperator is the left table's key in
--- a Left Outer Join, these two operators will be executed in
--- the same MR job when Correlation Optimizer is enabled.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- If the key of a GroupByOperator is the left table's key in
--- a Left Outer Join, these two operators will be executed in
--- the same MR job when Correlation Optimizer is enabled.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Outer Join0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(1)
-            keys: _col0 (type: string)
-            mode: hash
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	47
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Join Operator
-            condition map:
-                 Left Outer Join0 to 1
-            keys:
-              0 _col0 (type: string)
-              1 _col0 (type: string)
-            outputColumnNames: _col0
-            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                aggregations: count(1)
-                keys: _col0 (type: string)
-                mode: complete
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1)
-                    mode: hash
-                    outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	47
-PREHOOK: query: -- If the key of a GroupByOperator is the right table's key in
--- a Left Outer Join, we cannot use a single MR to execute these two
--- operators because those keys with a null value are not grouped.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- If the key of a GroupByOperator is the right table's key in
--- a Left Outer Join, we cannot use a single MR to execute these two
--- operators because those keys with a null value are not grouped.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Outer Join0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col1
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col1 (type: string)
-            outputColumnNames: _col0
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: count(1)
-              keys: _col0 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	47
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Outer Join0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col1
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col1 (type: string)
-            outputColumnNames: _col0
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: count(1)
-              keys: _col0 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	47
-PREHOOK: query: -- If a column of the key of a GroupByOperator is the right table's key in
--- a Left Outer Join, we cannot use a single MR to execute these two
--- operators because those keys with a null value are not grouped.
-EXPLAIN
-SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-PREHOOK: type: QUERY
-POSTHOOK: query: -- If a column of the key of a GroupByOperator is the right table's key in
--- a Left Outer Join, we cannot use a single MR to execute these two
--- operators because those keys with a null value are not grouped.
-EXPLAIN
-SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string), _col1 (type: string)
-                sort order: ++
-                Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            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), _col1 (type: string)
-                sort order: ++
-                Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Outer Join0 to 1
-          keys:
-            0 _col0 (type: string), _col1 (type: string)
-            1 _col0 (type: string), _col1 (type: string)
-          outputColumnNames: _col0, _col3
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col0 (type: string), _col3 (type: string)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: count(1)
-              keys: _col0 (type: string), _col1 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1, _col2
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string), _col1 (type: string)
-              sort order: ++
-              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col2 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string), KEY._col1 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 275 Data size: 2921 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
-
-PREHOOK: query: SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-	NULL	10
-128	NULL	1
-146	val_146	2
-150	val_150	1
-213	val_213	2
-224	NULL	1
-238	val_238	2
-255	val_255	2
-273	val_273	3
-278	val_278	2
-311	val_311	3
-369	NULL	1
-401	val_401	5
-406	val_406	4
-66	val_66	1
-98	val_98	2
-PREHOOK: query: EXPLAIN
-SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string), _col1 (type: string)
-                sort order: ++
-                Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            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), _col1 (type: string)
-                sort order: ++
-                Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Outer Join0 to 1
-          keys:
-            0 _col0 (type: string), _col1 (type: string)
-            1 _col0 (type: string), _col1 (type: string)
-          outputColumnNames: _col0, _col3
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col0 (type: string), _col3 (type: string)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: count(1)
-              keys: _col0 (type: string), _col1 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1, _col2
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string), _col1 (type: string)
-              sort order: ++
-              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col2 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string), KEY._col1 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 275 Data size: 2921 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
-
-PREHOOK: query: SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT x.key, y.value, count(1) AS cnt
-FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value)
-GROUP BY x.key, y.value
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-	NULL	10
-128	NULL	1
-146	val_146	2
-150	val_150	1
-213	val_213	2
-224	NULL	1
-238	val_238	2
-255	val_255	2
-273	val_273	3
-278	val_278	2
-311	val_311	3
-369	NULL	1
-401	val_401	5
-406	val_406	4
-66	val_66	1
-98	val_98	2
-PREHOOK: query: -- If the key of a GroupByOperator is the right table's key in
--- a Right Outer Join, these two operators will be executed in
--- the same MR job when Correlation Optimizer is enabled.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- If the key of a GroupByOperator is the right table's key in
--- a Right Outer Join, these two operators will be executed in
--- the same MR job when Correlation Optimizer is enabled.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Right Outer Join0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col1
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col1 (type: string)
-            outputColumnNames: _col0
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: count(1)
-              keys: _col0 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-12744278	500
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Join Operator
-            condition map:
-                 Right Outer Join0 to 1
-            keys:
-              0 _col0 (type: string)
-              1 _col0 (type: string)
-            outputColumnNames: _col1
-            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-            Select Operator
-              expressions: _col1 (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Mux Operator
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Group By Operator
-                  aggregations: count(1)
-                  keys: _col0 (type: string)
-                  mode: complete
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                  Select Operator
-                    expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-                    outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-                    Group By Operator
-                      aggregations: sum(_col0), sum(_col1)
-                      mode: hash
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT y.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY y.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-12744278	500
-PREHOOK: query: -- If the key of a GroupByOperator is the left table's key in
--- a Right Outer Join, we cannot use a single MR to execute these two 
--- operators because those keys with a null value are not grouped.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- If the key of a GroupByOperator is the left table's key in
--- a Right Outer Join, we cannot use a single MR to execute these two 
--- operators because those keys with a null value are not grouped.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
-  Stage-3 depends on stages: Stage-2
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            alias: y
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: _col0
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Reduce Output Operator
-                key expressions: _col0 (type: string)
-                sort order: +
-                Map-reduce partition columns: _col0 (type: string)
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Right Outer Join0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0
-          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(1)
-            keys: _col0 (type: string)
-            mode: hash
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1
-          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 16 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
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT x.key AS key, count(1) AS cnt
-      FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
-      GROUP BY x.key) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was he

<TRUNCATED>

Mime
View raw message