hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1625203 [2/2] - in /hive/branches/spark/ql/src: java/org/apache/hadoop/hive/ql/optimizer/unionproc/ java/org/apache/hadoop/hive/ql/parse/spark/ test/queries/clientpositive/ test/results/clientpositive/spark/
Date Tue, 16 Sep 2014 02:02:49 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_19.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_19.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_19.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_19.q.out Tue Sep 16 02:02:48 2014
@@ -74,7 +74,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -98,7 +99,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -126,39 +127,41 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection
@@ -279,7 +282,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -306,7 +310,7 @@ STAGE PLANS:
                           Map-reduce partition columns: _col0 (type: string)
                           Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -337,39 +341,41 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection
@@ -452,7 +458,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -476,7 +483,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -504,53 +511,51 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
-                  expressions: (_col0 + _col0) (type: double), _col1 (type: bigint)
+                  expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Filter Operator
-                    predicate: (_col0 >= 7.0) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: double), _col1 (type: bigint)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                            name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: (_col0 + _col0) (type: double), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    Filter Operator
+                      predicate: (_col0 >= 7.0) (type: boolean)
+                      Select Operator
+                        expressions: _col0 (type: double), _col1 (type: bigint)
+                        outputColumnNames: _col0, _col1
+                        File Output Operator
+                          compressed: false
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
-                  expressions: (_col0 + _col0) (type: double), _col1 (type: bigint)
+                  expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Filter Operator
-                    predicate: (_col0 >= 7.0) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: double), _col1 (type: bigint)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                            name: default.outputtbl1
+                  Select Operator
+                    expressions: (_col0 + _col0) (type: double), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    Filter Operator
+                      predicate: (_col0 >= 7.0) (type: boolean)
+                      Select Operator
+                        expressions: _col0 (type: double), _col1 (type: bigint)
+                        outputColumnNames: _col0, _col1
+                        File Output Operator
+                          compressed: false
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_2.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_2.q.out Tue Sep 16 02:02:48 2014
@@ -75,27 +75,28 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 3 <- Map 2 (GROUP)
+        Reducer 4 <- Map 3 (GROUP)
+        Union 2 <- Map 1 (NONE), Map 5 (NONE), Reducer 4 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Select Operator
                     expressions: key (type: string), UDFToLong(2) (type: bigint)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl1
-        Map 2 
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: bigint)
+                      outputColumnNames: _col0, _col1
+                      File Output Operator
+                        compressed: false
+                        table:
+                            input format: org.apache.hadoop.mapred.TextInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            name: default.outputtbl1
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -116,43 +117,45 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 4 
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Select Operator
                     expressions: key (type: string), UDFToLong(1) (type: bigint)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl1
-        Reducer 3 
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: bigint)
+                      outputColumnNames: _col0, _col1
+                      File Output Operator
+                        compressed: false
+                        table:
+                            input format: org.apache.hadoop.mapred.TextInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            name: default.outputtbl1
+        Reducer 4 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 2 
+            Vertex: Union 2
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_20.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_20.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_20.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_20.q.out Tue Sep 16 02:02:48 2014
@@ -72,7 +72,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -96,7 +97,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -124,39 +125,41 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
-                  expressions: _col1 (type: bigint), _col0 (type: string)
+                  expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col1 (type: bigint), _col0 (type: string)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
-                  expressions: _col1 (type: bigint), _col0 (type: string)
+                  expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col1 (type: bigint), _col0 (type: string)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_21.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_21.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_21.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_21.q.out Tue Sep 16 02:02:48 2014
@@ -72,7 +72,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -96,7 +97,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -124,39 +125,41 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col0 (type: string)
+                    outputColumnNames: _col0
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string)
+                    outputColumnNames: _col0
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_24.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_24.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_24.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_24.q.out Tue Sep 16 02:02:48 2014
@@ -68,7 +68,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -92,7 +93,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -120,39 +121,41 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: UDFToDouble(UDFToLong(_col0)) (type: double), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col0 (type: double), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: UDFToDouble(_col0) (type: double), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: double), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_25.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_25.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_25.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_25.q.out Tue Sep 16 02:02:48 2014
@@ -86,7 +86,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -110,7 +111,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -138,39 +139,41 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection
@@ -298,7 +301,9 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 4 <- Union 3 (GROUP SORT)
+        Reducer 6 <- Map 5 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 6 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -317,7 +322,7 @@ STAGE PLANS:
                         sort order: 
                         Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
-        Map 3 
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
@@ -338,43 +343,45 @@ STAGE PLANS:
               Select Operator
                 expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string)
                 outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 500
-                  Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string)
                     outputColumnNames: _col0, _col1, _col2
-                    Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl2
+                    Reduce Output Operator
+                      key expressions: _col2 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col2 (type: string)
+                      value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
         Reducer 4 
             Reduce Operator Tree:
+              Extract
+                Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      name: default.outputtbl2
+        Reducer 6 
+            Reduce Operator Tree:
               Select Operator
                 expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string)
                 outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 500
-                  Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string)
                     outputColumnNames: _col0, _col1, _col2
-                    Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl2
+                    Reduce Output Operator
+                      key expressions: _col2 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col2 (type: string)
+                      value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection
@@ -449,7 +456,7 @@ Protect Mode:       	None               
 #### A masked pattern was here ####
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	false               
-	numFiles            	2                   
+	numFiles            	1                   
 	numRows             	-1                  
 	rawDataSize         	-1                  
 	totalSize           	6826                
@@ -491,7 +498,9 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 4 <- Union 3 (GROUP SORT)
+        Reducer 6 <- Map 5 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 6 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -510,7 +519,7 @@ STAGE PLANS:
                         sort order: 
                         Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
-        Map 3 
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
@@ -531,43 +540,45 @@ STAGE PLANS:
               Select Operator
                 expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string)
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 1000
-                  Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string), _col3 (type: string)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl3
+                    Reduce Output Operator
+                      key expressions: _col2 (type: string), _col3 (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
+                      value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string)
         Reducer 4 
             Reduce Operator Tree:
+              Extract
+                Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      name: default.outputtbl3
+        Reducer 6 
+            Reduce Operator Tree:
               Select Operator
                 expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string)
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 1000
-                  Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string), _col3 (type: string)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl3
+                    Reduce Output Operator
+                      key expressions: _col2 (type: string), _col3 (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
+                      value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string)
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection
@@ -648,7 +659,7 @@ Protect Mode:       	None               
 #### A masked pattern was here ####
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	false               
-	numFiles            	2                   
+	numFiles            	1                   
 	numRows             	-1                  
 	rawDataSize         	-1                  
 	totalSize           	6812                

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_4.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_4.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_4.q.out Tue Sep 16 02:02:48 2014
@@ -62,15 +62,21 @@ FROM (
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-2 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-0 depends on stages: Stage-2
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -94,7 +100,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -122,39 +128,50 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
+
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
 
   Stage: Stage-2
     Dependency Collection
@@ -169,6 +186,42 @@ STAGE PLANS:
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.outputtbl1
 
+  Stage: Stage-3
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Merge 
+            Map Operator Tree:
+                TableScan
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl1
+
+  Stage: Stage-5
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Merge 
+            Map Operator Tree:
+                TableScan
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl1
+
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
 PREHOOK: query: insert overwrite table outputTbl1
 SELECT *
 FROM (

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_5.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_5.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_5.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_5.q.out Tue Sep 16 02:02:48 2014
@@ -70,34 +70,40 @@ FROM (
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-2 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-0 depends on stages: Stage-2
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 3 <- Map 2 (GROUP)
+        Reducer 4 <- Map 3 (GROUP)
+        Union 2 <- Map 1 (NONE), Map 5 (NONE), Reducer 4 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Select Operator
                     expressions: key (type: string), UDFToLong(2) (type: bigint)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl1
-        Map 2 
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: bigint)
+                      outputColumnNames: _col0, _col1
+                      File Output Operator
+                        compressed: false
+                        table:
+                            input format: org.apache.hadoop.mapred.TextInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            name: default.outputtbl1
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -118,43 +124,54 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 4 
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Select Operator
                     expressions: key (type: string), UDFToLong(1) (type: bigint)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          name: default.outputtbl1
-        Reducer 3 
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: bigint)
+                      outputColumnNames: _col0, _col1
+                      File Output Operator
+                        compressed: false
+                        table:
+                            input format: org.apache.hadoop.mapred.TextInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            name: default.outputtbl1
+        Reducer 4 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          name: default.outputtbl1
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
 
   Stage: Stage-2
     Dependency Collection
@@ -169,6 +186,42 @@ STAGE PLANS:
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.outputtbl1
 
+  Stage: Stage-3
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Merge 
+            Map Operator Tree:
+                TableScan
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl1
+
+  Stage: Stage-5
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Merge 
+            Map Operator Tree:
+                TableScan
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl1
+
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
 PREHOOK: query: insert overwrite table outputTbl1
 SELECT *
 FROM (

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_7.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_7.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_7.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_7.q.out Tue Sep 16 02:02:48 2014
@@ -74,7 +74,8 @@ STAGE PLANS:
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP)
-        Reducer 4 <- Map 3 (GROUP)
+        Reducer 5 <- Map 4 (GROUP)
+        Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -98,7 +99,7 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -126,39 +127,41 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                        name: default.outputtbl1
-        Reducer 4 
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                          name: default.outputtbl1
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                          name: default.outputtbl1
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_8.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_8.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_8.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_8.q.out Tue Sep 16 02:02:48 2014
@@ -79,27 +79,28 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 3 <- Map 2 (GROUP)
+        Reducer 4 <- Map 3 (GROUP)
+        Union 2 <- Map 1 (NONE), Map 5 (NONE), Reducer 4 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Select Operator
                     expressions: key (type: string), UDFToLong(2) (type: bigint)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                          name: default.outputtbl1
-        Map 2 
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: bigint)
+                      outputColumnNames: _col0, _col1
+                      File Output Operator
+                        compressed: false
+                        table:
+                            input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                            name: default.outputtbl1
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
@@ -120,43 +121,45 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                         value expressions: _col1 (type: bigint)
-        Map 4 
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: inputtbl1
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Select Operator
                     expressions: key (type: string), UDFToLong(1) (type: bigint)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                          name: default.outputtbl1
-        Reducer 3 
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: bigint)
+                      outputColumnNames: _col0, _col1
+                      File Output Operator
+                        compressed: false
+                        table:
+                            input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                            name: default.outputtbl1
+        Reducer 4 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                          name: default.outputtbl1
+        Union 2 
+            Vertex: Union 2
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_9.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_9.q.out?rev=1625203&r1=1625202&r2=1625203&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_9.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union_remove_9.q.out Tue Sep 16 02:02:48 2014
@@ -74,15 +74,20 @@ select * FROM (
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-2 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-0 depends on stages: Stage-2
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
         Reducer 4 <- Map 3 (GROUP)
-        Union 2 <- Map 1 (NONE), Map 5 (NONE)
+        Union 2 <- Map 1 (NONE), Map 5 (NONE), Reducer 4 (NONE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -95,13 +100,16 @@ STAGE PLANS:
                     Select Operator
                       expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint)
                       outputColumnNames: _col0, _col1
-                      File Output Operator
-                        compressed: false
-                        table:
-                            input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                            name: default.outputtbl1
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: bigint)
+                        outputColumnNames: _col0, _col1
+                        File Output Operator
+                          compressed: false
+                          table:
+                              input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                              name: default.outputtbl1
         Map 3 
             Map Operator Tree:
                 TableScan
@@ -133,13 +141,16 @@ STAGE PLANS:
                     Select Operator
                       expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint)
                       outputColumnNames: _col0, _col1
-                      File Output Operator
-                        compressed: false
-                        table:
-                            input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                            name: default.outputtbl1
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: bigint)
+                        outputColumnNames: _col0, _col1
+                        File Output Operator
+                          compressed: false
+                          table:
+                              input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                              name: default.outputtbl1
         Reducer 4 
             Reduce Operator Tree:
               Group By Operator
@@ -147,22 +158,31 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-                        name: default.outputtbl1
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint)
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+                          name: default.outputtbl1
         Union 2 
             Vertex: Union 2
 
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
   Stage: Stage-2
     Dependency Collection
 
@@ -176,6 +196,22 @@ STAGE PLANS:
               serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
               name: default.outputtbl1
 
+  Stage: Stage-3
+    Merge Work
+      merge level: block
+      input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+
+  Stage: Stage-5
+    Merge Work
+      merge level: block
+      input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
 PREHOOK: query: insert overwrite table outputTbl1
 SELECT * FROM
 (



Mime
View raw message