hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From li...@apache.org
Subject [07/12] hive git commit: HIVE-10903: Add hive.in.test for HoS tests (Rui reviewed by Xuefu)
Date Wed, 10 Jun 2015 07:12:05 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/02921ed8/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out
index 651c4b4..c3454ee 100644
--- a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out
+++ b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out
@@ -120,25 +120,32 @@ STAGE PLANS:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  alias: b
+                  Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
-                  Reduce Output Operator
-                    key expressions: key (type: string)
-                    sort order: +
-                    Map-reduce partition columns: key (type: string)
-                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    tag: 0
-                    value expressions: value (type: string)
-                    auto parallelism: false
+                  Select Operator
+                    expressions: key (type: string), value (type: string), ds (type: string)
+                    outputColumnNames: _col0, _col1, _col2
+                    Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+                      tag: 0
+                      value expressions: _col1 (type: string), _col2 (type: string)
+                      auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: src
+                  base file name: hr=11
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  partition values:
+                    ds 2008-04-08
+                    hr 11
                   properties:
                     COLUMN_STATS_ACCURATE true
                     bucket_count -1
@@ -146,11 +153,13 @@ STAGE PLANS:
                     columns.comments 'default','default'
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.src
+                    name default.srcpart
                     numFiles 1
                     numRows 500
+                    partition_columns ds/hr
+                    partition_columns.types string:string
                     rawDataSize 5312
-                    serialization.ddl struct src { string key, string value}
+                    serialization.ddl struct srcpart { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 5812
@@ -160,51 +169,29 @@ STAGE PLANS:
                     input format: org.apache.hadoop.mapred.TextInputFormat
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
-                      COLUMN_STATS_ACCURATE true
                       bucket_count -1
                       columns key,value
                       columns.comments 'default','default'
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.src
-                      numFiles 1
-                      numRows 500
-                      rawDataSize 5312
-                      serialization.ddl struct src { string key, string value}
+                      name default.srcpart
+                      partition_columns ds/hr
+                      partition_columns.types string:string
+                      serialization.ddl struct srcpart { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                      totalSize 5812
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.src
-                  name: default.src
-            Truncated Path -> Alias:
-              /src [a]
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
-                  GatherStats: false
-                  Reduce Output Operator
-                    key expressions: key (type: string)
-                    sort order: +
-                    Map-reduce partition columns: key (type: string)
-                    Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
-                    tag: 1
-                    value expressions: value (type: string), ds (type: string)
-                    auto parallelism: false
-            Path -> Alias:
-#### A masked pattern was here ####
-            Path -> Partition:
+                    name: default.srcpart
+                  name: default.srcpart
 #### A masked pattern was here ####
                 Partition
-                  base file name: hr=11
+                  base file name: hr=12
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   partition values:
                     ds 2008-04-08
-                    hr 11
+                    hr 12
                   properties:
                     COLUMN_STATS_ACCURATE true
                     bucket_count -1
@@ -245,12 +232,12 @@ STAGE PLANS:
                   name: default.srcpart
 #### A masked pattern was here ####
                 Partition
-                  base file name: hr=12
+                  base file name: hr=11
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   partition values:
-                    ds 2008-04-08
-                    hr 12
+                    ds 2008-04-09
+                    hr 11
                   properties:
                     COLUMN_STATS_ACCURATE true
                     bucket_count -1
@@ -291,12 +278,12 @@ STAGE PLANS:
                   name: default.srcpart
 #### A masked pattern was here ####
                 Partition
-                  base file name: hr=11
+                  base file name: hr=12
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   partition values:
                     ds 2008-04-09
-                    hr 11
+                    hr 12
                   properties:
                     COLUMN_STATS_ACCURATE true
                     bucket_count -1
@@ -335,14 +322,37 @@ STAGE PLANS:
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     name: default.srcpart
                   name: default.srcpart
+            Truncated Path -> Alias:
+              /srcpart/ds=2008-04-08/hr=11 [b]
+              /srcpart/ds=2008-04-08/hr=12 [b]
+              /srcpart/ds=2008-04-09/hr=11 [b]
+              /srcpart/ds=2008-04-09/hr=12 [b]
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  GatherStats: false
+                  Select Operator
+                    expressions: key (type: string), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col0 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                      tag: 1
+                      value expressions: _col1 (type: string)
+                      auto parallelism: false
+            Path -> Alias:
+#### A masked pattern was here ####
+            Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: hr=12
+                  base file name: src
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-09
-                    hr 12
                   properties:
                     COLUMN_STATS_ACCURATE true
                     bucket_count -1
@@ -350,13 +360,11 @@ STAGE PLANS:
                     columns.comments 'default','default'
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.srcpart
+                    name default.src
                     numFiles 1
                     numRows 500
-                    partition_columns ds/hr
-                    partition_columns.types string:string
                     rawDataSize 5312
-                    serialization.ddl struct srcpart { string key, string value}
+                    serialization.ddl struct src { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 5812
@@ -366,26 +374,26 @@ STAGE PLANS:
                     input format: org.apache.hadoop.mapred.TextInputFormat
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
+                      COLUMN_STATS_ACCURATE true
                       bucket_count -1
                       columns key,value
                       columns.comments 'default','default'
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.srcpart
-                      partition_columns ds/hr
-                      partition_columns.types string:string
-                      serialization.ddl struct srcpart { string key, string value}
+                      name default.src
+                      numFiles 1
+                      numRows 500
+                      rawDataSize 5312
+                      serialization.ddl struct src { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      totalSize 5812
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.srcpart
-                  name: default.srcpart
+                    name: default.src
+                  name: default.src
             Truncated Path -> Alias:
-              /srcpart/ds=2008-04-08/hr=11 [b]
-              /srcpart/ds=2008-04-08/hr=12 [b]
-              /srcpart/ds=2008-04-09/hr=11 [b]
-              /srcpart/ds=2008-04-09/hr=12 [b]
+              /src [a]
         Reducer 2 
             Needs Tagging: true
             Reduce Operator Tree:
@@ -393,21 +401,21 @@ STAGE PLANS:
                 condition map:
                      Outer Join 0 to 1
                 filter mappings:
-                  1 [0, 1]
+                  0 [1, 1]
                 filter predicates:
-                  0 
-                  1 {(VALUE._col1 = '2008-04-08')}
+                  0 {(VALUE._col1 = '2008-04-08')}
+                  1 
                 keys:
-                  0 key (type: string)
-                  1 key (type: string)
-                outputColumnNames: _col0, _col1, _col5, _col6
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col0, _col1, _col3, _col4
                 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
                 Filter Operator
                   isSamplingPred: false
-                  predicate: ((((_col0 > 10) and (_col0 < 20)) and (_col5 > 15)) and (_col5 < 25)) (type: boolean)
+                  predicate: ((((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) and (UDFToDouble(_col0) > 15.0)) and (UDFToDouble(_col0) < 25.0)) (type: boolean)
                   Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                    expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
                     outputColumnNames: _col0, _col1, _col2, _col3
                     Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
                     File Output Operator
@@ -596,80 +604,25 @@ STAGE PLANS:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  GatherStats: false
-                  Reduce Output Operator
-                    key expressions: key (type: string)
-                    sort order: +
-                    Map-reduce partition columns: key (type: string)
-                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    tag: 0
-                    value expressions: value (type: string)
-                    auto parallelism: false
-            Path -> Alias:
-#### A masked pattern was here ####
-            Path -> Partition:
-#### A masked pattern was here ####
-                Partition
-                  base file name: src
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  properties:
-                    COLUMN_STATS_ACCURATE true
-                    bucket_count -1
-                    columns key,value
-                    columns.comments 'default','default'
-                    columns.types string:string
-#### A masked pattern was here ####
-                    name default.src
-                    numFiles 1
-                    numRows 500
-                    rawDataSize 5312
-                    serialization.ddl struct src { string key, string value}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 5812
-#### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                
-                    input format: org.apache.hadoop.mapred.TextInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                    properties:
-                      COLUMN_STATS_ACCURATE true
-                      bucket_count -1
-                      columns key,value
-                      columns.comments 'default','default'
-                      columns.types string:string
-#### A masked pattern was here ####
-                      name default.src
-                      numFiles 1
-                      numRows 500
-                      rawDataSize 5312
-                      serialization.ddl struct src { string key, string value}
-                      serialization.format 1
-                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                      totalSize 5812
-#### A masked pattern was here ####
-                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.src
-                  name: default.src
-            Truncated Path -> Alias:
-              /src [a]
-        Map 3 
-            Map Operator Tree:
-                TableScan
                   alias: b
-                  Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
-                  Reduce Output Operator
-                    key expressions: key (type: string)
-                    sort order: +
-                    Map-reduce partition columns: key (type: string)
-                    Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
-                    tag: 1
-                    value expressions: value (type: string), ds (type: string)
-                    auto parallelism: false
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+                    Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 111 Data size: 1179 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+                        tag: 0
+                        value expressions: _col1 (type: string)
+                        auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -765,60 +718,39 @@ STAGE PLANS:
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     name: default.srcpart
                   name: default.srcpart
+            Truncated Path -> Alias:
+              /srcpart/ds=2008-04-08/hr=11 [b]
+              /srcpart/ds=2008-04-08/hr=12 [b]
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  GatherStats: false
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+                    Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                        tag: 1
+                        value expressions: _col1 (type: string)
+                        auto parallelism: false
+            Path -> Alias:
 #### A masked pattern was here ####
-                Partition
-                  base file name: hr=11
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-09
-                    hr 11
-                  properties:
-                    COLUMN_STATS_ACCURATE true
-                    bucket_count -1
-                    columns key,value
-                    columns.comments 'default','default'
-                    columns.types string:string
-#### A masked pattern was here ####
-                    name default.srcpart
-                    numFiles 1
-                    numRows 500
-                    partition_columns ds/hr
-                    partition_columns.types string:string
-                    rawDataSize 5312
-                    serialization.ddl struct srcpart { string key, string value}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 5812
-#### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                
-                    input format: org.apache.hadoop.mapred.TextInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                    properties:
-                      bucket_count -1
-                      columns key,value
-                      columns.comments 'default','default'
-                      columns.types string:string
-#### A masked pattern was here ####
-                      name default.srcpart
-                      partition_columns ds/hr
-                      partition_columns.types string:string
-                      serialization.ddl struct srcpart { string key, string value}
-                      serialization.format 1
-                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.srcpart
-                  name: default.srcpart
+            Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: hr=12
+                  base file name: src
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-09
-                    hr 12
                   properties:
                     COLUMN_STATS_ACCURATE true
                     bucket_count -1
@@ -826,13 +758,11 @@ STAGE PLANS:
                     columns.comments 'default','default'
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.srcpart
+                    name default.src
                     numFiles 1
                     numRows 500
-                    partition_columns ds/hr
-                    partition_columns.types string:string
                     rawDataSize 5312
-                    serialization.ddl struct srcpart { string key, string value}
+                    serialization.ddl struct src { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 5812
@@ -842,43 +772,43 @@ STAGE PLANS:
                     input format: org.apache.hadoop.mapred.TextInputFormat
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
+                      COLUMN_STATS_ACCURATE true
                       bucket_count -1
                       columns key,value
                       columns.comments 'default','default'
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.srcpart
-                      partition_columns ds/hr
-                      partition_columns.types string:string
-                      serialization.ddl struct srcpart { string key, string value}
+                      name default.src
+                      numFiles 1
+                      numRows 500
+                      rawDataSize 5312
+                      serialization.ddl struct src { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      totalSize 5812
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.srcpart
-                  name: default.srcpart
+                    name: default.src
+                  name: default.src
             Truncated Path -> Alias:
-              /srcpart/ds=2008-04-08/hr=11 [b]
-              /srcpart/ds=2008-04-08/hr=12 [b]
-              /srcpart/ds=2008-04-09/hr=11 [b]
-              /srcpart/ds=2008-04-09/hr=12 [b]
+              /src [a]
         Reducer 2 
             Needs Tagging: true
             Reduce Operator Tree:
               Join Operator
                 condition map:
-                     Outer Join 0 to 1
+                     Left Outer Join0 to 1
                 keys:
-                  0 key (type: string)
-                  1 key (type: string)
-                outputColumnNames: _col0, _col1, _col5, _col6, _col7
-                Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col0, _col1, _col3, _col4
+                Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
                 Filter Operator
                   isSamplingPred: false
-                  predicate: (((((_col0 > 10) and (_col0 < 20)) and (_col5 > 15)) and (_col5 < 25)) and (_col7 = '2008-04-08')) (type: boolean)
+                  predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) (type: boolean)
                   Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                    expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
                     outputColumnNames: _col0, _col1, _col2, _col3
                     Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
                     File Output Operator
@@ -921,8 +851,6 @@ PREHOOK: Input: default@src
 PREHOOK: Input: default@srcpart
 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 #### A masked pattern was here ####
 POSTHOOK: query: FROM 
   src a
@@ -936,8 +864,6 @@ POSTHOOK: Input: default@src
 POSTHOOK: Input: default@srcpart
 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 #### A masked pattern was here ####
 17	val_17	17	val_17
 17	val_17	17	val_17

http://git-wip-us.apache.org/repos/asf/hive/blob/02921ed8/ql/src/test/results/clientpositive/spark/parallel_join1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/parallel_join1.q.out b/ql/src/test/results/clientpositive/spark/parallel_join1.q.out
index 15171d9..47555b2 100644
--- a/ql/src/test/results/clientpositive/spark/parallel_join1.q.out
+++ b/ql/src/test/results/clientpositive/spark/parallel_join1.q.out
@@ -38,37 +38,45 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
                       Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: src2
+                  alias: src1
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
+                    Select Operator
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 keys:
-                  0 key (type: string)
-                  1 key (type: string)
-                outputColumnNames: _col0, _col6
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col1, _col2
                 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
-                  expressions: UDFToInteger(_col0) (type: int), _col6 (type: string)
+                  expressions: UDFToInteger(_col2) (type: int), _col1 (type: string)
                   outputColumnNames: _col0, _col1
                   Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
@@ -104,7 +112,7 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@src
 POSTHOOK: Output: default@dest_j1
 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ]
 PREHOOK: query: SELECT dest_j1.* FROM dest_j1
 PREHOOK: type: QUERY
 PREHOOK: Input: default@dest_j1

http://git-wip-us.apache.org/repos/asf/hive/blob/02921ed8/ql/src/test/results/clientpositive/spark/pcr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/pcr.q.out b/ql/src/test/results/clientpositive/spark/pcr.q.out
index 4c22f0b..efadb1d 100644
--- a/ql/src/test/results/clientpositive/spark/pcr.q.out
+++ b/ql/src/test/results/clientpositive/spark/pcr.q.out
@@ -4818,7 +4818,7 @@ STAGE PLANS:
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
-                    predicate: (key = 11) (type: boolean)
+                    predicate: (UDFToDouble(key) = 11.0) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: value (type: string), hr (type: string)
@@ -5047,7 +5047,7 @@ STAGE PLANS:
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
-                    predicate: (key = 11) (type: boolean)
+                    predicate: (UDFToDouble(key) = 11.0) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: value (type: string), ds (type: string)

http://git-wip-us.apache.org/repos/asf/hive/blob/02921ed8/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out
index 78db996..31b25b3 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out
@@ -40,41 +40,56 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
-                    Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                    predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string), value (type: string)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
                       Filter Operator
-                        predicate: (_col0 < '400') (type: boolean)
-                        Statistics: Num rows: 4 Data size: 42 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: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE
-                          value expressions: _col1 (type: string)
+                        predicate: (_col0 <> '4') (type: boolean)
+                        Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+                        Filter Operator
+                          predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
+                          Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                          Filter Operator
+                            predicate: _col0 is not null (type: boolean)
+                            Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((((key > '2') and (key < '400')) and (key <> '4')) and (key > '20')) (type: boolean)
-                    Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                       Filter Operator
-                        predicate: (_col0 < '400') (type: boolean)
-                        Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+                        predicate: ((_col0 > '20') and (((_col1 < 'val_50') or (_col0 > '2')) and (_col0 < '400'))) (type: boolean)
+                        Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col0 (type: string)
+                          outputColumnNames: _col0
+                          Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                          Filter Operator
+                            predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean)
+                            Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                            Filter Operator
+                              predicate: _col0 is not null (type: boolean)
+                              Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -83,27 +98,31 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
-                outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col1 (type: string), _col0 (type: string)
+                  outputColumnNames: _col0, _col1
                   Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: _col0 (type: string)
-                    outputColumnNames: _col0
+                  Filter Operator
+                    predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean)
                     Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
-                    Group By Operator
-                      aggregations: count(1)
-                      keys: _col0 (type: string)
-                      mode: hash
-                      outputColumnNames: _col0, _col1
+                    Select Operator
+                      expressions: _col0 (type: string)
+                      outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
+                      Group By Operator
+                        aggregations: count(1)
+                        keys: _col0 (type: string)
+                        mode: hash
+                        outputColumnNames: _col0, _col1
                         Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: bigint)
+                        Reduce Output Operator
+                          key expressions: _col0 (type: string)
+                          sort order: +
+                          Map-reduce partition columns: _col0 (type: string)
+                          Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
+                          value expressions: _col1 (type: bigint)
         Reducer 3 
             Reduce Operator Tree:
               Group By Operator
@@ -315,35 +334,34 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
-                    Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                    predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string), value (type: string)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 3 Data size: 31 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
+                        Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((((key > '2') and (key < '400')) and (key <> '4')) and (key > '20')) (type: boolean)
-                    Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 2 Data size: 21 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: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -352,13 +370,13 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
-                outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 19 Data size: 210 Basic stats: COMPLETE Column stats: NONE
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
                 Filter Operator
-                  predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+                  predicate: ((_col0 > '50') or (_col1 < '50')) (type: boolean)
                   Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    expressions: _col0 (type: string)
+                    expressions: _col1 (type: string)
                     outputColumnNames: _col0
                     Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator

http://git-wip-us.apache.org/repos/asf/hive/blob/02921ed8/ql/src/test/results/clientpositive/spark/ppd_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join.q.out b/ql/src/test/results/clientpositive/spark/ppd_join.q.out
index 441fee1..b97431c 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join.q.out
@@ -37,42 +37,57 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
-                    Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                    predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
                       Filter Operator
-                        predicate: (_col0 < '400') (type: boolean)
-                        Statistics: Num rows: 4 Data size: 42 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: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE
-                          value expressions: _col1 (type: string)
+                        predicate: (_col0 <> '4') (type: boolean)
+                        Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+                        Filter Operator
+                          predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
+                          Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                          Filter Operator
+                            predicate: _col0 is not null (type: boolean)
+                            Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                              value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((((key > '2') and (key < '400')) and (key <> '4')) and (key > '20')) (type: boolean)
-                    Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                       Filter Operator
-                        predicate: (_col0 < '400') (type: boolean)
-                        Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
-                          value expressions: _col1 (type: string)
+                        predicate: ((_col0 > '20') and (((_col1 < 'val_50') or (_col0 > '2')) and (_col0 < '400'))) (type: boolean)
+                        Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col0 (type: string)
+                          outputColumnNames: _col0
+                          Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                          Filter Operator
+                            predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean)
+                            Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                            Filter Operator
+                              predicate: _col0 is not null (type: boolean)
+                              Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -81,22 +96,26 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
-                outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
                   Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: _col0 (type: string), _col3 (type: string)
-                    outputColumnNames: _col0, _col1
+                  Filter Operator
+                    predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean)
                     Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
+                    Select Operator
+                      expressions: _col0 (type: string), _col2 (type: string)
+                      outputColumnNames: _col0, _col1
                       Statistics: Num rows: 1 Data size: 11 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
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 1 Data size: 11 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-0
     Fetch Operator
@@ -577,17 +596,17 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (((((key > '1') and (key < '400')) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
-                    Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                    predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 3 Data size: 31 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
@@ -595,18 +614,17 @@ STAGE PLANS:
                   alias: src
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((((key > '2') and (key < '400')) and (key <> '4')) and (key > '20')) (type: boolean)
-                    Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
+                    Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string), value (type: string)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 2 Data size: 21 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: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
+                        Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -615,13 +633,13 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
-                outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 19 Data size: 210 Basic stats: COMPLETE Column stats: NONE
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
                 Filter Operator
-                  predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+                  predicate: ((_col0 > '50') or (_col2 < '50')) (type: boolean)
                   Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    expressions: _col0 (type: string), _col3 (type: string)
+                    expressions: _col2 (type: string), _col1 (type: string)
                     outputColumnNames: _col0, _col1
                     Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
                     File Output Operator


Mime
View raw message