hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hashut...@apache.org
Subject [06/16] hive git commit: HIVE-16230 : Enable CBO in presence of hints (Pengcheng Xiong via Ashutosh Chauhan)
Date Mon, 20 Mar 2017 23:33:42 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/42181575/ql/src/test/results/clientpositive/spark/join_reorder4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join_reorder4.q.out b/ql/src/test/results/clientpositive/spark/join_reorder4.q.out
index 83ea4c5..8ba636c 100644
--- a/ql/src/test/results/clientpositive/spark/join_reorder4.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_reorder4.q.out
@@ -51,16 +51,31 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain select /*+ STREAMTABLE(a) */ a.*, b.*, c.* from T1 a join T2 b on a.key1=b.key2 join T3 c on a.key1=c.key3
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key1 is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key1 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key1 (type: string)
+                      Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val1 (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -68,14 +83,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key2 is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 3 
+                    Reduce Output Operator
+                      key expressions: key2 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key2 (type: string)
+                      Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val2 (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -83,52 +97,35 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key3 is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key1 is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      input vertices:
-                        1 Map 2
-                        2 Map 3
-                      Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 2 Data size: 66 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
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key3 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key3 (type: string)
+                      Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val3 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                keys:
+                  0 key1 (type: string)
+                  1 key2 (type: string)
+                  2 key3 (type: string)
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 2 Data size: 66 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
@@ -154,16 +151,31 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain select /*+ STREAMTABLE(b) */ a.*, b.*, c.* from T1 a join T2 b on a.key1=b.key2 join T3 c on a.key1=c.key3
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key1 is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key1 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key1 (type: string)
+                      Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val1 (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -171,14 +183,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key2 is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 3 
+                    Reduce Output Operator
+                      key expressions: key2 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key2 (type: string)
+                      Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val2 (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -186,52 +197,35 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key3 is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key1 is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      input vertices:
-                        1 Map 2
-                        2 Map 3
-                      Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 2 Data size: 66 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
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key3 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key3 (type: string)
+                      Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val3 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                keys:
+                  0 key1 (type: string)
+                  1 key2 (type: string)
+                  2 key3 (type: string)
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 2 Data size: 66 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
@@ -257,16 +251,31 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain select /*+ STREAMTABLE(c) */ a.*, b.*, c.* from T1 a join T2 b on a.key1=b.key2 join T3 c on a.key1=c.key3
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key1 is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key1 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key1 (type: string)
+                      Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val1 (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -274,14 +283,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key2 is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 3 
+                    Reduce Output Operator
+                      key expressions: key2 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key2 (type: string)
+                      Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val2 (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -289,52 +297,35 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key3 is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key1 is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      keys:
-                        0 key1 (type: string)
-                        1 key2 (type: string)
-                        2 key3 (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      input vertices:
-                        1 Map 2
-                        2 Map 3
-                      Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 2 Data size: 66 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
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key3 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key3 (type: string)
+                      Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val3 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                keys:
+                  0 key1 (type: string)
+                  1 key2 (type: string)
+                  2 key3 (type: string)
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 2 Data size: 66 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

http://git-wip-us.apache.org/repos/asf/hive/blob/42181575/ql/src/test/results/clientpositive/spark/mapjoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/mapjoin1.q.out b/ql/src/test/results/clientpositive/spark/mapjoin1.q.out
index ca489e4..aa96fc5 100644
--- a/ql/src/test/results/clientpositive/spark/mapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/spark/mapjoin1.q.out
@@ -42,13 +42,14 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    filter predicates:
-                      0 
-                      1 {true}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
+                  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
+                    Spark HashTable Sink Operator
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -61,22 +62,19 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    filter predicates:
-                      0 
-                      1 {true}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
-                    Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                  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
+                    Map Join Operator
+                      condition map:
+                           Right Outer Join0 to 1
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
                       outputColumnNames: _col0, _col1, _col2, _col3
+                      input vertices:
+                        0 Map 1
                       Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                       Limit
                         Number of rows: 10
@@ -136,13 +134,17 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    filter predicates:
-                      0 
-                      1 {((key * 10) < '1000')}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
+                  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
+                    Spark HashTable Sink Operator
+                      filter predicates:
+                        0 
+                        1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -155,22 +157,22 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    filter predicates:
-                      0 
-                      1 {((key * 10) < '1000')}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
-                    Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                  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
+                    Map Join Operator
+                      condition map:
+                           Right Outer Join0 to 1
+                      filter predicates:
+                        0 
+                        1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
                       outputColumnNames: _col0, _col1, _col2, _col3
+                      input vertices:
+                        0 Map 1
                       Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                       Limit
                         Number of rows: 10
@@ -227,18 +229,22 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    filter predicates:
-                      0 
-                      1 {(_col1.key > 200)}
-                    keys:
-                      0 key (type: string)
-                      1 _col0 (type: string)
+                  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
+                    Spark HashTable Sink Operator
+                      filter predicates:
+                        0 
+                        1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -246,7 +252,7 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: src
@@ -260,28 +266,24 @@ STAGE PLANS:
                            Right Outer Join0 to 1
                       filter predicates:
                         0 
-                        1 {(_col1.key > 200)}
+                        1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
                       keys:
-                        0 key (type: string)
+                        0 _col0 (type: string)
                         1 _col0 (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
+                      outputColumnNames: _col0, _col1, _col2, _col3
                       input vertices:
-                        0 Map 2
+                        0 Map 1
                       Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: struct<key:string,value:string>)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                        Limit
-                          Number of rows: 10
+                      Limit
+                        Number of rows: 10
+                        Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
                           Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 10 Data size: 100 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
+                          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
             Local Work:
               Map Reduce Local Work
 
@@ -332,13 +334,14 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    filter predicates:
-                      0 
-                      1 {true}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
+                  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
+                    Spark HashTable Sink Operator
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -351,22 +354,19 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    filter predicates:
-                      0 
-                      1 {true}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
-                    Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                  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
+                    Map Join Operator
+                      condition map:
+                           Right Outer Join0 to 1
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
                       outputColumnNames: _col0, _col1, _col2, _col3
+                      input vertices:
+                        0 Map 1
                       Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                       Limit
                         Number of rows: 10
@@ -426,13 +426,17 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    filter predicates:
-                      0 
-                      1 {((key * 10) < '1000')}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
+                  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
+                    Spark HashTable Sink Operator
+                      filter predicates:
+                        0 
+                        1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -445,22 +449,22 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    filter predicates:
-                      0 
-                      1 {((key * 10) < '1000')}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
-                    Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                  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
+                    Map Join Operator
+                      condition map:
+                           Right Outer Join0 to 1
+                      filter predicates:
+                        0 
+                        1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
                       outputColumnNames: _col0, _col1, _col2, _col3
+                      input vertices:
+                        0 Map 1
                       Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                       Limit
                         Number of rows: 10
@@ -517,18 +521,22 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    filter predicates:
-                      0 
-                      1 {(_col1.key > 200)}
-                    keys:
-                      0 key (type: string)
-                      1 _col0 (type: string)
+                  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
+                    Spark HashTable Sink Operator
+                      filter predicates:
+                        0 
+                        1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -536,7 +544,7 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: src
@@ -550,28 +558,24 @@ STAGE PLANS:
                            Right Outer Join0 to 1
                       filter predicates:
                         0 
-                        1 {(_col1.key > 200)}
+                        1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
                       keys:
-                        0 key (type: string)
+                        0 _col0 (type: string)
                         1 _col0 (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
+                      outputColumnNames: _col0, _col1, _col2, _col3
                       input vertices:
-                        0 Map 2
+                        0 Map 1
                       Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: struct<key:string,value:string>)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                        Limit
-                          Number of rows: 10
+                      Limit
+                        Number of rows: 10
+                        Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
                           Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 10 Data size: 100 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
+                          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
             Local Work:
               Map Reduce Local Work
 

http://git-wip-us.apache.org/repos/asf/hive/blob/42181575/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out b/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out
index 6b3fcc0..bdae7a5 100644
--- a/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out
+++ b/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out
@@ -28,10 +28,14 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
+                    Select Operator
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+                      Spark HashTable Sink Operator
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -50,26 +54,30 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col1
-                      input vertices:
-                        1 Map 4
-                      Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        keys: _col1 (type: string)
-                        mode: hash
-                        outputColumnNames: _col0
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1000 Data size: 10624 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: _col1
+                        input vertices:
+                          1 Map 4
                         Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                        Reduce Output Operator
-                          key expressions: _col0 (type: string)
-                          sort order: +
-                          Map-reduce partition columns: rand() (type: double)
+                        Group By Operator
+                          keys: _col1 (type: string)
+                          mode: hash
+                          outputColumnNames: _col0
                           Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+                          Reduce Output Operator
+                            key expressions: _col0 (type: string)
+                            sort order: +
+                            Map-reduce partition columns: rand() (type: double)
+                            Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
             Local Work:
               Map Reduce Local Work
         Reducer 2 
@@ -163,10 +171,14 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
+                    Select Operator
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+                      Spark HashTable Sink Operator
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -184,26 +196,30 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col1
-                      input vertices:
-                        1 Map 3
-                      Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        keys: _col1 (type: string)
-                        mode: hash
-                        outputColumnNames: _col0
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1000 Data size: 10624 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: _col1
+                        input vertices:
+                          1 Map 3
                         Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                        Reduce Output Operator
-                          key expressions: _col0 (type: string)
-                          sort order: +
-                          Map-reduce partition columns: _col0 (type: string)
+                        Group By Operator
+                          keys: _col1 (type: string)
+                          mode: hash
+                          outputColumnNames: _col0
                           Statistics: Num rows: 1100 Data size: 11686 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: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
             Local Work:
               Map Reduce Local Work
         Reducer 2 
@@ -285,10 +301,14 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
+                    Select Operator
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+                      Spark HashTable Sink Operator
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -307,21 +327,25 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col1
-                      input vertices:
-                        1 Map 4
-                      Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col1 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: rand() (type: double)
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1000 Data size: 10624 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: _col1
+                        input vertices:
+                          1 Map 4
                         Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          key expressions: _col1 (type: string)
+                          sort order: +
+                          Map-reduce partition columns: rand() (type: double)
+                          Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
             Local Work:
               Map Reduce Local Work
         Reducer 2 
@@ -415,10 +439,14 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
+                    Select Operator
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+                      Spark HashTable Sink Operator
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
 
@@ -436,21 +464,25 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col1
-                      input vertices:
-                        1 Map 3
-                      Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col1 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col1 (type: string)
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1000 Data size: 10624 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: _col1
+                        input vertices:
+                          1 Map 3
                         Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          key expressions: _col1 (type: string)
+                          sort order: +
+                          Map-reduce partition columns: _col1 (type: string)
+                          Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
             Local Work:
               Map Reduce Local Work
         Reducer 2 

http://git-wip-us.apache.org/repos/asf/hive/blob/42181575/ql/src/test/results/clientpositive/spark/skewjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/skewjoin.q.out b/ql/src/test/results/clientpositive/spark/skewjoin.q.out
index dade580..fdcb4bb 100644
--- a/ql/src/test/results/clientpositive/spark/skewjoin.q.out
+++ b/ql/src/test/results/clientpositive/spark/skewjoin.q.out
@@ -664,23 +664,19 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
-                outputColumnNames: _col1, _col2
+                outputColumnNames: _col2, _col3
                 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col1) (type: int), hash(_col2) (type: int)
+                Group By Operator
+                  aggregations: sum(hash(_col2)), sum(hash(_col3))
+                  mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 550 Data size: 5843 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
+                  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
     Conditional Operator
@@ -712,22 +708,18 @@ STAGE PLANS:
                     keys:
                       0 reducesinkkey0 (type: string)
                       1 reducesinkkey0 (type: string)
-                    outputColumnNames: _col1, _col2
-                    Select Operator
-                      expressions: hash(_col1) (type: int), hash(_col2) (type: int)
+                    outputColumnNames: _col2, _col3
+                    Group By Operator
+                      aggregations: sum(hash(_col2)), sum(hash(_col3))
+                      mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 550 Data size: 5843 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
+                      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
             Local Work:
               Map Reduce Local Work
 
@@ -819,7 +811,7 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (key is not null and value is not null) (type: boolean)
+                    predicate: (key is not null and UDFToDouble(substring(value, 5)) is not null) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
@@ -836,16 +828,16 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (key is not null and value is not null) (type: boolean)
+                    predicate: (key is not null and (substring(value, 5) + 1) is not null) (type: boolean)
                     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), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double)
+                        key expressions: _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
                         sort order: ++
-                        Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double)
+                        Map-reduce partition columns: _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
                         Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Reducer 2 
@@ -856,24 +848,20 @@ STAGE PLANS:
                 handleSkewJoin: true
                 keys:
                   0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double)
-                  1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double)
+                  1 _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
                 outputColumnNames: _col2, _col3
                 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col2) (type: int), hash(_col3) (type: int)
+                Group By Operator
+                  aggregations: sum(hash(_col2)), sum(hash(_col3))
+                  mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 550 Data size: 5843 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
+                  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
     Conditional Operator
@@ -906,21 +894,17 @@ STAGE PLANS:
                       0 reducesinkkey0 (type: string), reducesinkkey1 (type: double)
                       1 reducesinkkey0 (type: string), reducesinkkey1 (type: double)
                     outputColumnNames: _col2, _col3
-                    Select Operator
-                      expressions: hash(_col2) (type: int), hash(_col3) (type: int)
+                    Group By Operator
+                      aggregations: sum(hash(_col2)), sum(hash(_col3))
+                      mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 550 Data size: 5843 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
+                      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
             Local Work:
               Map Reduce Local Work
 
@@ -1022,7 +1006,7 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean)
+                    predicate: ((key < 80) and (key < 100)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
@@ -1039,35 +1023,35 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((UDFToDouble(key) < 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean)
+                    predicate: ((key < 100) and (key < 80)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
                       Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
         Map 5 
             Map Operator Tree:
                 TableScan
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean)
+                    predicate: ((key < 100) and (key < 80)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string), value (type: string)
-                      outputColumnNames: _col0, _col1
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
                       Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -1081,21 +1065,17 @@ STAGE PLANS:
                   2 _col0 (type: string)
                 outputColumnNames: _col0, _col3
                 Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: hash(_col0) (type: int), hash(_col3) (type: int)
+                Group By Operator
+                  aggregations: sum(hash(_col0)), sum(hash(_col3))
+                  mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 121 Data size: 1284 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
+                  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-5
     Conditional Operator
@@ -1141,21 +1121,17 @@ STAGE PLANS:
                       1 reducesinkkey0 (type: string)
                       2 reducesinkkey0 (type: string)
                     outputColumnNames: _col0, _col3
-                    Select Operator
-                      expressions: hash(_col0) (type: int), hash(_col3) (type: int)
+                    Group By Operator
+                      aggregations: sum(hash(_col0)), sum(hash(_col3))
+                      mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 121 Data size: 1284 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
+                      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
             Local Work:
               Map Reduce Local Work
 
@@ -1228,21 +1204,17 @@ STAGE PLANS:
                       1 reducesinkkey0 (type: string)
                       2 reducesinkkey0 (type: string)
                     outputColumnNames: _col0, _col3
-                    Select Operator
-                      expressions: hash(_col0) (type: int), hash(_col3) (type: int)
+                    Group By Operator
+                      aggregations: sum(hash(_col0)), sum(hash(_col3))
+                      mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 121 Data size: 1284 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
+                      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
             Local Work:
               Map Reduce Local Work
 


Mime
View raw message