hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From kgyrtk...@apache.org
Subject [20/54] [partial] hive git commit: HIVE-17550: Remove unreferenced q.out-s (Zoltan Haindrich, reviewed by Ashutosh Chauhan)
Date Thu, 21 Sep 2017 09:06:57 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/correlationoptimizer2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/correlationoptimizer2.q.out b/ql/src/test/results/clientpositive/correlationoptimizer2.q.out
deleted file mode 100644
index d1f4e05..0000000
--- a/ql/src/test/results/clientpositive/correlationoptimizer2.q.out
+++ /dev/null
@@ -1,2257 +0,0 @@
-PREHOOK: query: -- In this query, subquery a and b both have a GroupByOperator and the a and b will be
--- joined. The key of JoinOperator is the same with both keys of GroupByOperators in subquery
--- a and b. When Correlation Optimizer is turned off, we have four MR jobs.
--- When Correlation Optimizer is turned on, 2 MR jobs will be generated.
--- The first job will evaluate subquery tmp (including subquery a, b, and the JoinOperator on a
--- and b).
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- In this query, subquery a and b both have a GroupByOperator and the a and b will be
--- joined. The key of JoinOperator is the same with both keys of GroupByOperators in subquery
--- a and b. When Correlation Optimizer is turned off, we have four MR jobs.
--- When Correlation Optimizer is turned on, 2 MR jobs will be generated.
--- The first job will evaluate subquery tmp (including subquery a, b, and the JoinOperator on a
--- and b).
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-4
-  Stage-3 depends on stages: Stage-2
-  Stage-4 is a root stage
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            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
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  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: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-              mode: hash
-              outputColumnNames: _col0, _col1, _col2, _col3
-              Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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-4
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: y
-            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
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  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: 12 Data size: 91 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-0
-    Fetch Operator
-      limit: -1
-      Processor Tree:
-        ListSink
-
-PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	37	652447	15
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.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: 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
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: bigint)
-          TableScan
-            alias: y
-            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
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 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, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 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, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	37	652447	15
-PREHOOK: query: -- Left Outer Join should be handled.
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- Left Outer Join should be handled.
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-4
-  Stage-3 depends on stages: Stage-2
-  Stage-4 is a root stage
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  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: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Outer Join0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-              mode: hash
-              outputColumnNames: _col0, _col1, _col2, _col3
-              Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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-4
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  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: 12 Data size: 91 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-0
-    Fetch Operator
-      limit: -1
-      Processor Tree:
-        ListSink
-
-PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-12744278	500	652447	15
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: bigint)
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 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, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 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, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-12744278	500	652447	15
-PREHOOK: query: -- Right Outer Join should be handled.
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- Right Outer Join should be handled.
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-4
-  Stage-3 depends on stages: Stage-2
-  Stage-4 is a root stage
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  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: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Right Outer Join0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-              mode: hash
-              outputColumnNames: _col0, _col1, _col2, _col3
-              Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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-4
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  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: 12 Data size: 91 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-0
-    Fetch Operator
-      limit: -1
-      Processor Tree:
-        ListSink
-
-PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	37	652447	25
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: bigint)
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 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: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 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: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-652447	37	652447	25
-PREHOOK: query: -- Full Outer Join should be handled.
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- Full Outer Join should be handled.
-EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-4
-  Stage-3 depends on stages: Stage-2
-  Stage-4 is a root stage
-  Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  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: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Outer Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-              mode: hash
-              outputColumnNames: _col0, _col1, _col2, _col3
-              Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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-4
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  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: 12 Data size: 91 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-0
-    Fetch Operator
-      limit: -1
-      Processor Tree:
-        ListSink
-
-PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-12744278	500	652447	25
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: bigint)
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string), value (type: string)
-              outputColumnNames: key, value
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count(value)
-                keys: key (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1
-                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
-                  value expressions: _col1 (type: bigint)
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE
-              Join Operator
-                condition map:
-                     Outer Join 0 to 1
-                keys:
-                  0 _col0 (type: string)
-                  1 _col0 (type: string)
-                outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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
-          Group By Operator
-            aggregations: count(VALUE._col0)
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE
-              Join Operator
-                condition map:
-                     Outer Join 0 to 1
-                keys:
-                  0 _col0 (type: string)
-                  1 _col0 (type: string)
-                outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 1 Data size: 32 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: 32 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            Statistics: Num rows: 1 Data size: 32 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(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@src1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
-FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-12744278	500	652447	25
-PREHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT a.key AS key, count(1) AS cnt
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)
-      GROUP BY a.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT a.key AS key, count(1) AS cnt
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)
-      GROUP BY a.key) tmp
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
-  Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-5
-  Stage-3 depends on stages: Stage-2
-  Stage-4 depends on stages: Stage-3
-  Stage-5 is a root stage
-  Stage-0 depends on stages: Stage-4
-
-STAGE PLANS:
-  Stage: Stage-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: x
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: key
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: key (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:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Outer Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            aggregations: count(1)
-            keys: _col0 (type: string)
-            mode: hash
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 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
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 275 Data size: 2921 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: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: hash(_col0) (type: int), hash(_col1) (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 137 Data size: 1455 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-4
-    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-5
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: key
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: key (type: string)
-                mode: hash
-                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
-      Reduce Operator Tree:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 12 Data size: 91 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-0
-    Fetch Operator
-      limit: -1
-      Processor Tree:
-        ListSink
-
-PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT a.key AS key, count(1) AS cnt
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)
-      GROUP BY a.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 a.key AS key, count(1) AS cnt
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)
-      GROUP BY a.key) tmp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@src1
-#### A masked pattern was here ####
-12744278	310
-PREHOOK: query: -- After FULL OUTER JOIN, keys with null values are not grouped, right now,
--- we have to generate 2 MR jobs for tmp, 1 MR job for a join b and another for the
--- GroupByOperator on key.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT a.key AS key, count(1) AS cnt
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)
-      GROUP BY a.key) tmp
-PREHOOK: type: QUERY
-POSTHOOK: query: -- After FULL OUTER JOIN, keys with null values are not grouped, right now,
--- we have to generate 2 MR jobs for tmp, 1 MR job for a join b and another for the
--- GroupByOperator on key.
-EXPLAIN
-SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
-FROM (SELECT a.key AS key, count(1) AS cnt
-      FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
-      FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
-      ON (a.key = b.key)
-      GROUP BY a.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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: key
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: key (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
-          TableScan
-            alias: y
-            Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: key (type: string)
-              outputColumnNames: key
-              Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: key (type: string)
-                mode: hash
-                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
-      Reduce Operator Tree:
-        Demux Operator
-          Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE
-              Join Operator
-                condition map:
-                     Outer 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
-                Group By Operator
-                  aggregations: count(1)
-                  keys: _col0 (type: string)
-                  mode: hash
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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
-          Group By Operator
-            keys: KEY._col0 (type: string)
-            mode: mergepartial
-            outputColumnNames: _col0
-            Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE
-            Mux Operator
-              Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE
-              Join Operator
-                condition map:
-                     Outer 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
-                Group By Operator
-                  aggregations: count(1)
-                  keys: _col0 (type: string)
-                  mode: hash
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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: 1 Data size: 0 Basic stats: PARTIAL 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: 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: C

<TRUNCATED>

Mime
View raw message