hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From ser...@apache.org
Subject svn commit: r1645808 [34/49] - in /hive/trunk: accumulo-handler/src/test/results/positive/ common/src/java/org/apache/hadoop/hive/conf/ contrib/src/test/results/clientpositive/ hbase-handler/src/test/results/positive/ itests/hive-unit/src/test/java/org...
Date Tue, 16 Dec 2014 01:13:30 GMT
Modified: hive/trunk/ql/src/test/results/clientpositive/subquery_notin.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/subquery_notin.q.out?rev=1645808&r1=1645807&r2=1645808&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/subquery_notin.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/subquery_notin.q.out Tue Dec 16 01:13:24 2014
@@ -1,4 +1,4 @@
-Warning: Shuffle Join JOIN[18][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: -- non agg, non corr
 explain
 select * 
@@ -18,17 +18,17 @@ where src.key not in
   )
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-4 is a root stage
-  Stage-1 depends on stages: Stage-4
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
 
 STAGE PLANS:
-  Stage: Stage-4
+  Stage: Stage-3
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: s1
+            alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: ((key > '2') and key is null) (type: boolean)
@@ -54,20 +54,13 @@ STAGE PLANS:
             predicate: (_col0 = 0) (type: boolean)
             Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
             Select Operator
-              expressions: 0 (type: bigint)
-              outputColumnNames: _col0
               Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                keys: _col0 (type: bigint)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+              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-1
     Map Reduce
@@ -75,10 +68,14 @@ STAGE PLANS:
           TableScan
             alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              sort order: 
+            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
-              value expressions: key (type: string), value (type: string)
+              Reduce Output Operator
+                sort order: 
+                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: string)
           TableScan
             Reduce Output Operator
               sort order: 
@@ -86,7 +83,7 @@ STAGE PLANS:
       Reduce Operator Tree:
         Join Operator
           condition map:
-               Left Semi Join 0 to 1
+               Inner Join 0 to 1
           keys:
             0 
             1 
@@ -110,7 +107,7 @@ STAGE PLANS:
               Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
               value expressions: _col1 (type: string)
           TableScan
-            alias: s1
+            alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: (key > '2') (type: boolean)
@@ -131,10 +128,10 @@ STAGE PLANS:
           keys:
             0 _col0 (type: string)
             1 _col0 (type: string)
-          outputColumnNames: _col0, _col1, _col5
+          outputColumnNames: _col0, _col1, _col3
           Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: _col5 is null (type: boolean)
+            predicate: _col3 is null (type: boolean)
             Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: _col0 (type: string), _col1 (type: string)
@@ -154,7 +151,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[18][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: select * 
 from src 
 where src.key not in  ( select key from src s1 where s1.key > '2')
@@ -288,7 +285,7 @@ POSTHOOK: Input: default@src
 199	val_199
 199	val_199
 2	val_2
-Warning: Shuffle Join JOIN[26][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: -- non agg, corr
 explain
 select p_mfgr, b.p_name, p_size 
@@ -311,10 +308,10 @@ where b.p_name not in
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-3 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-3
-  Stage-4 is a root stage
-  Stage-5 depends on stages: Stage-4
-  Stage-1 depends on stages: Stage-5
+  Stage-4 depends on stages: Stage-3
+  Stage-1 depends on stages: Stage-4
+  Stage-2 depends on stages: Stage-1, Stage-5
+  Stage-5 is a root stage
   Stage-0 depends on stages: Stage-2
 
 STAGE PLANS:
@@ -322,92 +319,25 @@ STAGE PLANS:
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: part
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
-      Reduce Operator Tree:
-        Extract
-          Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-          PTF Operator
+            alias: b
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: (_wcol0 <= 2) (type: boolean)
-              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: _col1 (type: string), _col2 (type: string)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-                File Output Operator
-                  compressed: false
-                  table:
-                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                      serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col1 (type: string), _col2 (type: string)
-              sort order: ++
-              Map-reduce partition columns: _col1 (type: string), _col2 (type: string)
-              Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col5 (type: int)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string), _col1 (type: string)
-              sort order: ++
-              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Outer Join0 to 1
-          keys:
-            0 _col1 (type: string), _col2 (type: string)
-            1 _col0 (type: string), _col1 (type: string)
-          outputColumnNames: _col1, _col2, _col5, _col12
-          Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
-          Filter Operator
-            predicate: _col12 is null (type: boolean)
-            Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
             Select Operator
-              expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int)
+              expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
               outputColumnNames: _col0, _col1, _col2
-              Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                Statistics: Num rows: 15 Data size: 1903 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
-
-  Stage: Stage-4
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: part
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+              Reduce Output Operator
+                key expressions: _col1 (type: string), _col2 (type: int)
+                sort order: ++
+                Map-reduce partition columns: _col1 (type: string)
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
       Reduce Operator Tree:
         Extract
           Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
           PTF Operator
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
-              predicate: ((_wcol0 <= 2) and (_col1 is null or _col2 is null)) (type: boolean)
+              predicate: ((_wcol0 <= 2) and (_col0 is null or _col1 is null)) (type: boolean)
               Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
@@ -423,7 +353,7 @@ STAGE PLANS:
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                         serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
-  Stage: Stage-5
+  Stage: Stage-4
     Map Reduce
       Map Operator Tree:
           TableScan
@@ -441,20 +371,13 @@ STAGE PLANS:
             predicate: (_col0 = 0) (type: boolean)
             Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
             Select Operator
-              expressions: 0 (type: bigint)
-              outputColumnNames: _col0
               Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                keys: _col0 (type: bigint)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+              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-1
     Map Reduce
@@ -462,10 +385,14 @@ STAGE PLANS:
           TableScan
             alias: b
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              sort order: 
+            Select Operator
+              expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1, _col2
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+              Reduce Output Operator
+                sort order: 
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
           TableScan
             Reduce Output Operator
               sort order: 
@@ -473,11 +400,11 @@ STAGE PLANS:
       Reduce Operator Tree:
         Join Operator
           condition map:
-               Left Semi Join 0 to 1
+               Inner Join 0 to 1
           keys:
             0 
             1 
-          outputColumnNames: _col1, _col2, _col5
+          outputColumnNames: _col0, _col1, _col2
           Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
           File Output Operator
             compressed: false
@@ -486,13 +413,88 @@ STAGE PLANS:
                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                 serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
+  Stage: Stage-2
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            Reduce Output Operator
+              key expressions: _col0 (type: string), _col1 (type: string)
+              sort order: ++
+              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+              Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+              value expressions: _col2 (type: int)
+          TableScan
+            Reduce Output Operator
+              key expressions: _col0 (type: string), _col1 (type: string)
+              sort order: ++
+              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+      Reduce Operator Tree:
+        Join Operator
+          condition map:
+               Left Outer Join0 to 1
+          keys:
+            0 _col0 (type: string), _col1 (type: string)
+            1 _col0 (type: string), _col1 (type: string)
+          outputColumnNames: _col0, _col1, _col2, _col4
+          Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
+          Filter Operator
+            predicate: _col4 is null (type: boolean)
+            Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
+            Select Operator
+              expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int)
+              outputColumnNames: _col0, _col1, _col2
+              Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
+              File Output Operator
+                compressed: false
+                Statistics: Num rows: 15 Data size: 1903 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
+
+  Stage: Stage-5
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            alias: b
+            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+            Select Operator
+              expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1, _col2
+              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+              Reduce Output Operator
+                key expressions: _col1 (type: string), _col2 (type: int)
+                sort order: ++
+                Map-reduce partition columns: _col1 (type: string)
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+      Reduce Operator Tree:
+        Extract
+          Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+          PTF Operator
+            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+            Filter Operator
+              predicate: (_wcol0 <= 2) (type: boolean)
+              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+              Select Operator
+                expressions: _col0 (type: string), _col1 (type: string)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
   Stage: Stage-0
     Fetch Operator
       limit: -1
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[26][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: select p_mfgr, b.p_name, p_size 
 from part b 
 where b.p_name not in 
@@ -531,7 +533,7 @@ Manufacturer#4	almond azure aquamarine p
 Manufacturer#5	almond antique blue firebrick mint	31
 Manufacturer#5	almond aquamarine dodger light gainsboro	46
 Manufacturer#5	almond azure blanched chiffon midnight	23
-Warning: Shuffle Join JOIN[34][tables = [part, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[45][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
 PREHOOK: query: -- agg, non corr
 explain
 select p_name, p_size 
@@ -555,10 +557,10 @@ POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-3 is a root stage
   Stage-4 depends on stages: Stage-3
-  Stage-2 depends on stages: Stage-1, Stage-4
+  Stage-1 depends on stages: Stage-4
+  Stage-2 depends on stages: Stage-1, Stage-6
   Stage-5 is a root stage
   Stage-6 depends on stages: Stage-5
-  Stage-1 depends on stages: Stage-6
   Stage-0 depends on stages: Stage-2
 
 STAGE PLANS:
@@ -568,12 +570,16 @@ STAGE PLANS:
           TableScan
             alias: part
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
+            Select Operator
+              expressions: p_mfgr (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_mfgr (type: string), p_size (type: int)
+              Reduce Output Operator
+                key expressions: _col0 (type: string), _col1 (type: int)
+                sort order: ++
+                Map-reduce partition columns: _col0 (type: string)
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: int)
       Reduce Operator Tree:
         Extract
           Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -583,7 +589,7 @@ STAGE PLANS:
               predicate: (_wcol0 <= 2) (type: boolean)
               Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
               Select Operator
-                expressions: _col5 (type: int)
+                expressions: _col1 (type: int)
                 outputColumnNames: _col0
                 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
@@ -619,16 +625,22 @@ STAGE PLANS:
                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                 serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
-  Stage: Stage-2
+  Stage: Stage-1
     Map Reduce
       Map Operator Tree:
           TableScan
-            Reduce Output Operator
-              key expressions: UDFToDouble(_col5) (type: double)
-              sort order: +
-              Map-reduce partition columns: UDFToDouble(_col5) (type: double)
-              Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: string), _col5 (type: int)
+            alias: part
+            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+            Select Operator
+              expressions: p_name (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1
+              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+              Reduce Output Operator
+                key expressions: UDFToDouble(_col1) (type: double)
+                sort order: +
+                Map-reduce partition columns: UDFToDouble(_col1) (type: double)
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: int)
           TableScan
             Reduce Output Operator
               key expressions: _col0 (type: double)
@@ -640,24 +652,52 @@ STAGE PLANS:
           condition map:
                Left Outer Join0 to 1
           keys:
-            0 UDFToDouble(_col5) (type: double)
+            0 UDFToDouble(_col1) (type: double)
             1 _col0 (type: double)
-          outputColumnNames: _col1, _col5, _col12
-          Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
+          outputColumnNames: _col0, _col1, _col2
+          Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: _col12 is null (type: boolean)
+            predicate: _col2 is null (type: boolean)
+            Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+            File Output Operator
+              compressed: false
+              table:
+                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+  Stage: Stage-2
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            Reduce Output Operator
+              sort order: 
+              Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+              value expressions: _col0 (type: string), _col1 (type: int)
+          TableScan
+            Reduce Output Operator
+              sort order: 
+              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+      Reduce Operator Tree:
+        Join Operator
+          condition map:
+               Inner Join 0 to 1
+          keys:
+            0 
+            1 
+          outputColumnNames: _col0, _col1
+          Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
+          Select Operator
+            expressions: _col0 (type: string), _col1 (type: int)
+            outputColumnNames: _col0, _col1
             Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: _col1 (type: string), _col5 (type: int)
-              outputColumnNames: _col0, _col1
+            File Output Operator
+              compressed: false
               Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                Statistics: Num rows: 15 Data size: 1903 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
+              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
 
   Stage: Stage-5
     Map Reduce
@@ -665,12 +705,16 @@ STAGE PLANS:
           TableScan
             alias: part
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
+            Select Operator
+              expressions: p_mfgr (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_mfgr (type: string), p_size (type: int)
+              Reduce Output Operator
+                key expressions: _col0 (type: string), _col1 (type: int)
+                sort order: ++
+                Map-reduce partition columns: _col0 (type: string)
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: int)
       Reduce Operator Tree:
         Extract
           Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -680,7 +724,7 @@ STAGE PLANS:
               predicate: (_wcol0 <= 2) (type: boolean)
               Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
               Select Operator
-                expressions: _col5 (type: int)
+                expressions: _col1 (type: int)
                 outputColumnNames: _col0
                 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
@@ -723,50 +767,13 @@ STAGE PLANS:
                   predicate: (_col0 = 0) (type: boolean)
                   Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                   Select Operator
-                    expressions: 0 (type: bigint)
-                    outputColumnNames: _col0
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Group By Operator
-                      keys: _col0 (type: bigint)
-                      mode: hash
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: part
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_name (type: string), p_size (type: int)
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Semi Join 0 to 1
-          keys:
-            0 
-            1 
-          outputColumnNames: _col1, _col5
-          Statistics: Num rows: 28 Data size: 3461 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
+                    File Output Operator
+                      compressed: false
+                      table:
+                          input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -774,7 +781,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[34][tables = [part, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[45][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
 PREHOOK: query: select p_name, p_size 
 from 
 part where part.p_size not in 
@@ -821,7 +828,7 @@ almond aquamarine sandy cyan gainsboro	1
 almond aquamarine yellow dodger mint	7
 almond azure aquamarine papaya violet	12
 almond azure blanched chiffon midnight	23
-Warning: Shuffle Join JOIN[34][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[42][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: -- agg, corr
 explain
 select p_mfgr, p_name, p_size 
@@ -843,11 +850,11 @@ POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-3 is a root stage
   Stage-4 depends on stages: Stage-3
-  Stage-2 depends on stages: Stage-1, Stage-4
-  Stage-5 is a root stage
-  Stage-6 depends on stages: Stage-5
+  Stage-5 depends on stages: Stage-4
+  Stage-1 depends on stages: Stage-5
+  Stage-2 depends on stages: Stage-1, Stage-7
+  Stage-6 is a root stage
   Stage-7 depends on stages: Stage-6
-  Stage-1 depends on stages: Stage-7
   Stage-0 depends on stages: Stage-2
 
 STAGE PLANS:
@@ -855,14 +862,18 @@ STAGE PLANS:
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: part
+            alias: b
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
+            Select Operator
+              expressions: p_mfgr (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_mfgr (type: string), p_size (type: int)
+              Reduce Output Operator
+                key expressions: _col0 (type: string), _col1 (type: int)
+                sort order: ++
+                Map-reduce partition columns: _col0 (type: string)
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: int)
       Reduce Operator Tree:
         Extract
           Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -872,7 +883,7 @@ STAGE PLANS:
               predicate: (_wcol0 <= 2) (type: boolean)
               Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
               Select Operator
-                expressions: _col2 (type: string), _col5 (type: int)
+                expressions: _col0 (type: string), _col1 (type: int)
                 outputColumnNames: _col0, _col1
                 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
@@ -905,27 +916,93 @@ STAGE PLANS:
           mode: mergepartial
           outputColumnNames: _col0, _col1
           Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col1 (type: int), _col0 (type: string)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 4 Data size: 484 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
+          Filter Operator
+            predicate: (_col1 is null or _col0 is null) (type: boolean)
+            Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+            Select Operator
+              Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+              Group By Operator
+                aggregations: count()
+                mode: hash
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 12 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
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            Reduce Output Operator
+              sort order: 
+              Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+              value expressions: _col0 (type: bigint)
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations: count(VALUE._col0)
+          mode: mergepartial
+          outputColumnNames: _col0
+          Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+          Filter Operator
+            predicate: (_col0 = 0) (type: boolean)
+            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+            Select Operator
+              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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-1
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            alias: b
+            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+            Select Operator
+              expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1, _col2
+              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+              Reduce Output Operator
+                sort order: 
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+          TableScan
+            Reduce Output Operator
+              sort order: 
+              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+      Reduce Operator Tree:
+        Join Operator
+          condition map:
+               Inner Join 0 to 1
+          keys:
+            0 
+            1 
+          outputColumnNames: _col0, _col1, _col2
+          Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+          File Output Operator
+            compressed: false
+            table:
+                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-2
     Map Reduce
       Map Operator Tree:
           TableScan
             Reduce Output Operator
-              key expressions: _col5 (type: int), _col2 (type: string)
+              key expressions: _col2 (type: int), _col1 (type: string)
               sort order: ++
-              Map-reduce partition columns: _col5 (type: int), _col2 (type: string)
+              Map-reduce partition columns: _col2 (type: int), _col1 (type: string)
               Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: string)
+              value expressions: _col0 (type: string)
           TableScan
             Reduce Output Operator
               key expressions: _col0 (type: int), _col1 (type: string)
@@ -937,15 +1014,15 @@ STAGE PLANS:
           condition map:
                Left Outer Join0 to 1
           keys:
-            0 _col5 (type: int), _col2 (type: string)
+            0 _col2 (type: int), _col1 (type: string)
             1 _col0 (type: int), _col1 (type: string)
-          outputColumnNames: _col1, _col2, _col5, _col12
+          outputColumnNames: _col0, _col1, _col2, _col4
           Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: _col12 is null (type: boolean)
+            predicate: _col4 is null (type: boolean)
             Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
             Select Operator
-              expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int)
+              expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int)
               outputColumnNames: _col0, _col1, _col2
               Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
               File Output Operator
@@ -956,18 +1033,22 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
-  Stage: Stage-5
+  Stage: Stage-6
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: part
+            alias: b
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
+            Select Operator
+              expressions: p_mfgr (type: string), p_size (type: int)
+              outputColumnNames: _col0, _col1
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_mfgr (type: string), p_size (type: int)
+              Reduce Output Operator
+                key expressions: _col0 (type: string), _col1 (type: int)
+                sort order: ++
+                Map-reduce partition columns: _col0 (type: string)
+                Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                value expressions: _col0 (type: string), _col1 (type: int)
       Reduce Operator Tree:
         Extract
           Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -977,7 +1058,7 @@ STAGE PLANS:
               predicate: (_wcol0 <= 2) (type: boolean)
               Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
               Select Operator
-                expressions: _col2 (type: string), _col5 (type: int)
+                expressions: _col0 (type: string), _col1 (type: int)
                 outputColumnNames: _col0, _col1
                 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
@@ -993,7 +1074,7 @@ STAGE PLANS:
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                         serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
-  Stage: Stage-6
+  Stage: Stage-7
     Map Reduce
       Map Operator Tree:
           TableScan
@@ -1010,85 +1091,16 @@ STAGE PLANS:
           mode: mergepartial
           outputColumnNames: _col0, _col1
           Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
-          Filter Operator
-            predicate: (_col1 is null or _col0 is null) (type: boolean)
-            Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: count()
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 12 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-7
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: bigint)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-          Filter Operator
-            predicate: (_col0 = 0) (type: boolean)
-            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-            Select Operator
-              expressions: 0 (type: bigint)
-              outputColumnNames: _col0
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                keys: _col0 (type: bigint)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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-1
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: b
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
-          TableScan
-            Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Semi Join 0 to 1
-          keys:
-            0 
-            1 
-          outputColumnNames: _col1, _col2, _col5
-          Statistics: Num rows: 28 Data size: 3461 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
+          Select Operator
+            expressions: _col1 (type: int), _col0 (type: string)
+            outputColumnNames: _col0, _col1
+            Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+            File Output Operator
+              compressed: false
+              table:
+                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -1096,7 +1108,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[34][tables = [b, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[42][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: select p_mfgr, p_name, p_size 
 from part b where b.p_size not in 
   (select min(p_size) 
@@ -1137,7 +1149,7 @@ Manufacturer#5	almond antique medium spr
 Manufacturer#5	almond azure blanched chiffon midnight	23
 Manufacturer#5	almond antique blue firebrick mint	31
 Manufacturer#5	almond aquamarine dodger light gainsboro	46
-Warning: Shuffle Join JOIN[18][tables = [li, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: -- non agg, non corr, Group By in Parent Query
 select li.l_partkey, count(*) 
 from lineitem li 
@@ -1172,7 +1184,7 @@ POSTHOOK: Input: default@lineitem
 139636	1
 175839	1
 182052	1
-Warning: Shuffle Join JOIN[18][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: -- alternate not in syntax
 select * 
 from src 
@@ -1336,7 +1348,7 @@ POSTHOOK: Input: default@src
 POSTHOOK: Input: default@t1_v
 POSTHOOK: Output: database:default
 POSTHOOK: Output: default@T2_v
-Warning: Shuffle Join JOIN[24][tables = [t1_v, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: explain
 select * 
 from T1_v where T1_v.key not in (select T2_v.key from T2_v)
@@ -1346,39 +1358,32 @@ select *
 from T1_v where T1_v.key not in (select T2_v.key from T2_v)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-4 is a root stage
-  Stage-1 depends on stages: Stage-4
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
 
 STAGE PLANS:
-  Stage: Stage-4
+  Stage: Stage-3
     Map Reduce
       Map Operator Tree:
           TableScan
             alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
-              predicate: (key < '11') (type: boolean)
-              Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+              predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE (key) END is null) (type: boolean)
+              Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
               Select Operator
-                expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string)
-                outputColumnNames: _col0
-                Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: _col0 is null (type: boolean)
-                  Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
-                    Group By Operator
-                      aggregations: count()
-                      mode: hash
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        sort order: 
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: bigint)
+                Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  aggregations: count()
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    sort order: 
+                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col0 (type: bigint)
       Reduce Operator Tree:
         Group By Operator
           aggregations: count(VALUE._col0)
@@ -1389,20 +1394,13 @@ STAGE PLANS:
             predicate: (_col0 = 0) (type: boolean)
             Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
             Select Operator
-              expressions: 0 (type: bigint)
-              outputColumnNames: _col0
               Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                keys: _col0 (type: bigint)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+              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-1
     Map Reduce
@@ -1428,7 +1426,7 @@ STAGE PLANS:
       Reduce Operator Tree:
         Join Operator
           condition map:
-               Left Semi Join 0 to 1
+               Inner Join 0 to 1
           keys:
             0 
             1 
@@ -1454,17 +1452,17 @@ STAGE PLANS:
             alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
-              predicate: (key < '11') (type: boolean)
-              Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+              predicate: ((key < '11') and (CASE WHEN ((key > '104')) THEN (null) ELSE (key) END < '11')) (type: boolean)
+              Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+                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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
       Reduce Operator Tree:
         Join Operator
           condition map:
@@ -1472,10 +1470,10 @@ STAGE PLANS:
           keys:
             0 _col0 (type: string)
             1 _col0 (type: string)
-          outputColumnNames: _col0, _col1
+          outputColumnNames: _col0, _col2
           Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: _col1 is null (type: boolean)
+            predicate: _col2 is null (type: boolean)
             Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: _col0 (type: string)
@@ -1495,7 +1493,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[24][tables = [t1_v, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
 PREHOOK: query: select * 
 from T1_v where T1_v.key not in (select T2_v.key from T2_v)
 PREHOOK: type: QUERY

Modified: hive/trunk/ql/src/test/results/clientpositive/subquery_notin_having.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/subquery_notin_having.q.out?rev=1645808&r1=1645807&r2=1645808&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/subquery_notin_having.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/subquery_notin_having.q.out Tue Dec 16 01:13:24 2014
@@ -1,4 +1,4 @@
-Warning: Shuffle Join JOIN[22][tables = [gby_sq1, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
 PREHOOK: query: -- non agg, non corr
 explain
 select key, count(*) 
@@ -21,9 +21,9 @@ having key not in
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-5
+  Stage-2 depends on stages: Stage-1, Stage-4
   Stage-3 depends on stages: Stage-2
-  Stage-5 is a root stage
+  Stage-4 is a root stage
   Stage-0 depends on stages: Stage-3
 
 STAGE PLANS:
@@ -35,11 +35,11 @@ STAGE PLANS:
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: key (type: string)
-              outputColumnNames: key
+              outputColumnNames: _col0
               Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
                 aggregations: count()
-                keys: key (type: string)
+                keys: _col0 (type: string)
                 mode: hash
                 outputColumnNames: _col0, _col1
                 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -78,7 +78,7 @@ STAGE PLANS:
       Reduce Operator Tree:
         Join Operator
           condition map:
-               Left Semi Join 0 to 1
+               Inner Join 0 to 1
           keys:
             0 
             1 
@@ -102,7 +102,7 @@ STAGE PLANS:
               Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
               value expressions: _col1 (type: bigint)
           TableScan
-            alias: s1
+            alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: (key > '12') (type: boolean)
@@ -123,10 +123,10 @@ STAGE PLANS:
           keys:
             0 _col0 (type: string)
             1 _col0 (type: string)
-          outputColumnNames: _col0, _col1, _col2
+          outputColumnNames: _col0, _col1, _col3
           Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: _col2 is null (type: boolean)
+            predicate: _col3 is null (type: boolean)
             Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: _col0 (type: string), _col1 (type: bigint)
@@ -140,11 +140,11 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
-  Stage: Stage-5
+  Stage: Stage-4
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: s1
+            alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: ((key > '12') and key is null) (type: boolean)
@@ -170,20 +170,13 @@ STAGE PLANS:
             predicate: (_col0 = 0) (type: boolean)
             Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
             Select Operator
-              expressions: 0 (type: bigint)
-              outputColumnNames: _col0
               Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                keys: _col0 (type: bigint)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+              File Output Operator
+                compressed: false
+                table:
+                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -191,7 +184,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[32][tables = [gby_sq1, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
 PREHOOK: query: -- non agg, corr
 explain
 select b.p_mfgr, min(p_retailprice) 
@@ -216,11 +209,11 @@ having b.p_mfgr not in
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-6
-  Stage-3 depends on stages: Stage-2, Stage-4
+  Stage-2 depends on stages: Stage-1, Stage-5
+  Stage-3 depends on stages: Stage-2, Stage-6
   Stage-4 is a root stage
-  Stage-5 is a root stage
-  Stage-6 depends on stages: Stage-5
+  Stage-5 depends on stages: Stage-4
+  Stage-6 is a root stage
   Stage-0 depends on stages: Stage-3
 
 STAGE PLANS:
@@ -232,26 +225,26 @@ STAGE PLANS:
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: p_mfgr (type: string), p_retailprice (type: double)
-              outputColumnNames: p_mfgr, p_retailprice
+              outputColumnNames: _col0, _col1
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
-                aggregations: min(p_retailprice), max(p_retailprice), avg(p_retailprice)
-                keys: p_mfgr (type: string)
+                aggregations: min(_col1)
+                keys: _col0 (type: string)
                 mode: hash
-                outputColumnNames: _col0, _col1, _col2, _col3
+                outputColumnNames: _col0, _col1
                 Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: struct<count:bigint,sum:double,input:double>)
+                  value expressions: _col1 (type: double)
       Reduce Operator Tree:
         Group By Operator
-          aggregations: min(VALUE._col0), max(VALUE._col1), avg(VALUE._col2)
+          aggregations: min(VALUE._col0)
           keys: KEY._col0 (type: string)
           mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
+          outputColumnNames: _col0, _col1
           Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
           File Output Operator
             compressed: false
@@ -275,7 +268,7 @@ STAGE PLANS:
       Reduce Operator Tree:
         Join Operator
           condition map:
-               Left Semi Join 0 to 1
+               Inner Join 0 to 1
           keys:
             0 
             1 
@@ -310,10 +303,10 @@ STAGE PLANS:
           keys:
             0 _col0 (type: string), _col1 (type: double)
             1 _col0 (type: string), _col1 (type: double)
-          outputColumnNames: _col0, _col1, _col4
+          outputColumnNames: _col0, _col1, _col3
           Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: _col4 is null (type: boolean)
+            predicate: _col3 is null (type: boolean)
             Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: _col0 (type: string), _col1 (type: double)
@@ -331,76 +324,33 @@ STAGE PLANS:
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: part
+            alias: b
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: p_mfgr (type: string), p_retailprice (type: double)
-              outputColumnNames: p_mfgr, p_retailprice
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                aggregations: min(p_retailprice), max(p_retailprice), avg(p_retailprice)
-                keys: p_mfgr (type: string)
-                mode: hash
-                outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: struct<count:bigint,sum:double,input:double>)
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: min(VALUE._col0), max(VALUE._col1), avg(VALUE._col2)
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-          Filter Operator
-            predicate: ((_col2 - _col1) > 600) (type: boolean)
-            Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: _col0 (type: string), _col1 (type: double)
               outputColumnNames: _col0, _col1
-              Statistics: Num rows: 4 Data size: 484 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
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: part
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: p_mfgr (type: string), p_retailprice (type: double)
-              outputColumnNames: p_mfgr, p_retailprice
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
-                aggregations: min(p_retailprice), max(p_retailprice), avg(p_retailprice)
-                keys: p_mfgr (type: string)
+                aggregations: max(_col1), min(_col1)
+                keys: _col0 (type: string)
                 mode: hash
-                outputColumnNames: _col0, _col1, _col2, _col3
+                outputColumnNames: _col0, _col1, _col2
                 Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: struct<count:bigint,sum:double,input:double>)
+                  value expressions: _col1 (type: double), _col2 (type: double)
       Reduce Operator Tree:
         Group By Operator
-          aggregations: min(VALUE._col0), max(VALUE._col1), avg(VALUE._col2)
+          aggregations: max(VALUE._col0), min(VALUE._col1)
           keys: KEY._col0 (type: string)
           mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
+          outputColumnNames: _col0, _col1, _col2
           Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: ((_col0 is null or _col1 is null) and ((_col2 - _col1) > 600)) (type: boolean)
+            predicate: ((_col0 is null or _col2 is null) and ((_col1 - _col2) > 600.0)) (type: boolean)
             Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
@@ -408,7 +358,7 @@ STAGE PLANS:
                 aggregations: count()
                 mode: hash
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                 File Output Operator
                   compressed: false
                   table:
@@ -416,38 +366,74 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
-  Stage: Stage-6
+  Stage: Stage-5
     Map Reduce
       Map Operator Tree:
           TableScan
             Reduce Output Operator
               sort order: 
-              Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
               value expressions: _col0 (type: bigint)
       Reduce Operator Tree:
         Group By Operator
           aggregations: count(VALUE._col0)
           mode: mergepartial
           outputColumnNames: _col0
-          Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
             predicate: (_col0 = 0) (type: boolean)
             Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
             Select Operator
-              expressions: 0 (type: bigint)
-              outputColumnNames: _col0
               Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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-6
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            alias: b
+            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+            Select Operator
+              expressions: p_mfgr (type: string), p_retailprice (type: double)
+              outputColumnNames: _col0, _col1
+              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
-                keys: _col0 (type: bigint)
+                aggregations: min(_col1), max(_col1)
+                keys: _col0 (type: string)
                 mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                  value expressions: _col1 (type: double), _col2 (type: double)
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations: min(VALUE._col0), max(VALUE._col1)
+          keys: KEY._col0 (type: string)
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2
+          Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+          Filter Operator
+            predicate: ((_col2 - _col1) > 600.0) (type: boolean)
+            Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+            Select Operator
+              expressions: _col0 (type: string), _col1 (type: double)
+              outputColumnNames: _col0, _col1
+              Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+              File Output Operator
+                compressed: false
+                table:
+                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -455,7 +441,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[32][tables = [gby_sq1, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
 PREHOOK: query: select b.p_mfgr, min(p_retailprice) 
 from part b 
 group by b.p_mfgr
@@ -480,7 +466,7 @@ POSTHOOK: Input: default@part
 #### A masked pattern was here ####
 Manufacturer#1	1173.15
 Manufacturer#2	1690.68
-Warning: Shuffle Join JOIN[30][tables = [gby_sq1, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[41][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
 PREHOOK: query: -- agg, non corr
 explain
 select b.p_mfgr, min(p_retailprice) 
@@ -507,8 +493,8 @@ having b.p_mfgr not in
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-2 depends on stages: Stage-1, Stage-6
-  Stage-3 depends on stages: Stage-2, Stage-4
+  Stage-2 depends on stages: Stage-1, Stage-4
+  Stage-3 depends on stages: Stage-2, Stage-6
   Stage-4 is a root stage
   Stage-5 is a root stage
   Stage-6 depends on stages: Stage-5
@@ -523,26 +509,26 @@ STAGE PLANS:
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: p_mfgr (type: string), p_retailprice (type: double)
-              outputColumnNames: p_mfgr, p_retailprice
+              outputColumnNames: _col0, _col1
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
-                aggregations: min(p_retailprice), max(p_retailprice)
-                keys: p_mfgr (type: string)
+                aggregations: min(_col1)
+                keys: _col0 (type: string)
                 mode: hash
-                outputColumnNames: _col0, _col1, _col2
+                outputColumnNames: _col0, _col1
                 Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: double), _col2 (type: double)
+                  value expressions: _col1 (type: double)
       Reduce Operator Tree:
         Group By Operator
-          aggregations: min(VALUE._col0), max(VALUE._col1)
+          aggregations: min(VALUE._col0)
           keys: KEY._col0 (type: string)
           mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2
+          outputColumnNames: _col0, _col1
           Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
           File Output Operator
             compressed: false
@@ -556,82 +542,82 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             Reduce Output Operator
-              sort order: 
+              key expressions: _col0 (type: string)
+              sort order: +
+              Map-reduce partition columns: _col0 (type: string)
               Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: string), _col1 (type: double)
+              value expressions: _col1 (type: double)
           TableScan
             Reduce Output Operator
-              sort order: 
-              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+              key expressions: _col0 (type: string)
+              sort order: +
+              Map-reduce partition columns: _col0 (type: string)
+              Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
       Reduce Operator Tree:
         Join Operator
           condition map:
-               Left Semi Join 0 to 1
+               Left Outer Join0 to 1
           keys:
-            0 
-            1 
-          outputColumnNames: _col0, _col1
+            0 _col0 (type: string)
+            1 _col0 (type: string)
+          outputColumnNames: _col0, _col1, _col2
           Statistics: Num rows: 14 Data size: 1730 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
+          Filter Operator
+            predicate: _col2 is null (type: boolean)
+            Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+            File Output Operator
+              compressed: false
+              table:
+                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-3
     Map Reduce
       Map Operator Tree:
           TableScan
             Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: double)
+              sort order: 
+              Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+              value expressions: _col0 (type: string), _col1 (type: double)
           TableScan
             Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+              sort order: 
+              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
       Reduce Operator Tree:
         Join Operator
           condition map:
-               Left Outer Join0 to 1
+               Inner Join 0 to 1
           keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col1, _col3
-          Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
-          Filter Operator
-            predicate: _col3 is null (type: boolean)
-            Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: _col0 (type: string), _col1 (type: double)
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                Statistics: Num rows: 7 Data size: 888 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
+            0 
+            1 
+          outputColumnNames: _col0, _col1
+          Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE
+          Select Operator
+            expressions: _col0 (type: string), _col1 (type: double)
+            outputColumnNames: _col0, _col1
+            Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE
+            File Output Operator
+              compressed: false
+              Statistics: Num rows: 7 Data size: 951 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
 
   Stage: Stage-4
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: a
+            alias: b
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: p_mfgr (type: string), p_retailprice (type: double)
-              outputColumnNames: p_mfgr, p_retailprice
+              outputColumnNames: _col0, _col1
               Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
-                aggregations: max(p_retailprice), min(p_retailprice)
-                keys: p_mfgr (type: string)
+                aggregations: max(_col1), min(_col1)
+                keys: _col0 (type: string)
                 mode: hash
                 outputColumnNames: _col0, _col1, _col2
                 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -649,7 +635,7 @@ STAGE PLANS:
           outputColumnNames: _col0, _col1, _col2
           Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: ((_col1 - _col2) > 600) (type: boolean)
+            predicate: ((_col1 - _col2) > 600.0) (type: boolean)
             Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: _col0 (type: string)
@@ -666,18 +652,18 @@ STAGE PLANS:
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: a
+            alias: b
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: p_mfgr is null (type: boolean)
               Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: null (type: void), p_retailprice (type: double)
-                outputColumnNames: p_mfgr, p_retailprice
+                outputColumnNames: _col0, _col1
                 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
-                  aggregations: max(p_retailprice), min(p_retailprice)
-                  keys: p_mfgr (type: string)
+                  aggregations: max(_col1), min(_col1)
+                  keys: _col0 (type: string)
                   mode: hash
                   outputColumnNames: _col0, _col1, _col2
                   Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
@@ -695,7 +681,7 @@ STAGE PLANS:
           outputColumnNames: _col0, _col1, _col2
           Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: ((_col1 - _col2) > 600) (type: boolean)
+            predicate: ((_col1 - _col2) > 600.0) (type: boolean)
             Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
@@ -729,20 +715,13 @@ STAGE PLANS:
             predicate: (_col0 = 0) (type: boolean)
             Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
             Select Operator
-              expressions: 0 (type: bigint)
-              outputColumnNames: _col0
               Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-              Group By Operator
-                keys: _col0 (type: bigint)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+              File Output Operator
+                compressed: false
+                table:
+                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -750,7 +729,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[30][tables = [gby_sq1, sq_1_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[41][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
 PREHOOK: query: select b.p_mfgr, min(p_retailprice) 
 from part b 
 group by b.p_mfgr
@@ -775,5 +754,5 @@ having b.p_mfgr not in
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@part
 #### A masked pattern was here ####
-Manufacturer#1	1173.15
 Manufacturer#2	1690.68
+Manufacturer#1	1173.15



Mime
View raw message