You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by na...@apache.org on 2010/10/27 21:00:05 UTC

svn commit: r1028072 [4/7] - in /hive/trunk: ./ data/files/ ql/src/java/org/apache/hadoop/hive/ql/exec/ ql/src/java/org/apache/hadoop/hive/ql/parse/ ql/src/java/org/apache/hadoop/hive/ql/plan/ ql/src/test/queries/clientnegative/ ql/src/test/queries/cli...

Added: hive/trunk/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,256 @@
+PREHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE, c10 DOUBLE, c11 DOUBLE) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE, c10 DOUBLE, c11 DOUBLE) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION avg (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI avg (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION std (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION stddev_samp (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION variance (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION var_samp (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TO
 K_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+  Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+          TableScan
+            alias: src
+            Select Operator
+              expressions:
+                    expr: value
+                    type: string
+              outputColumnNames: value
+              Group By Operator
+                aggregations:
+                      expr: sum(substr(value, 5))
+                      expr: avg(substr(value, 5))
+                      expr: avg(DISTINCT substr(value, 5))
+                      expr: max(substr(value, 5))
+                      expr: min(substr(value, 5))
+                      expr: std(substr(value, 5))
+                      expr: stddev_samp(substr(value, 5))
+                      expr: variance(substr(value, 5))
+                      expr: var_samp(substr(value, 5))
+                      expr: sum(DISTINCT substr(value, 5))
+                      expr: count(DISTINCT substr(value, 5))
+                bucketGroup: false
+                keys:
+                      expr: substr(value, 5)
+                      type: string
+                mode: hash
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
+                Reduce Output Operator
+                  key expressions:
+                        expr: _col0
+                        type: string
+                  sort order: +
+                  tag: -1
+                  value expressions:
+                        expr: _col1
+                        type: double
+                        expr: _col2
+                        type: struct<count:bigint,sum:double>
+                        expr: _col3
+                        type: struct<count:bigint,sum:double>
+                        expr: _col4
+                        type: string
+                        expr: _col5
+                        type: string
+                        expr: _col6
+                        type: struct<count:bigint,sum:double,variance:double>
+                        expr: _col7
+                        type: struct<count:bigint,sum:double,variance:double>
+                        expr: _col8
+                        type: struct<count:bigint,sum:double,variance:double>
+                        expr: _col9
+                        type: struct<count:bigint,sum:double,variance:double>
+                        expr: _col10
+                        type: double
+                        expr: _col11
+                        type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(VALUE._col0)
+                expr: avg(VALUE._col1)
+                expr: avg(DISTINCT KEY._col0:0._col0)
+                expr: max(VALUE._col3)
+                expr: min(VALUE._col4)
+                expr: std(VALUE._col5)
+                expr: stddev_samp(VALUE._col6)
+                expr: variance(VALUE._col7)
+                expr: var_samp(VALUE._col8)
+                expr: sum(DISTINCT KEY._col0:1._col0)
+                expr: count(DISTINCT KEY._col0:2._col0)
+          bucketGroup: false
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: double
+                  expr: _col1
+                  type: double
+                  expr: _col2
+                  type: double
+                  expr: _col3
+                  type: string
+                  expr: _col4
+                  type: string
+                  expr: _col5
+                  type: double
+                  expr: _col6
+                  type: double
+                  expr: _col7
+                  type: double
+                  expr: _col8
+                  type: double
+                  expr: _col9
+                  type: double
+                  expr: _col10
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+            Select Operator
+              expressions:
+                    expr: _col0
+                    type: double
+                    expr: _col1
+                    type: double
+                    expr: _col2
+                    type: double
+                    expr: UDFToDouble(_col3)
+                    type: double
+                    expr: UDFToDouble(_col4)
+                    type: double
+                    expr: _col5
+                    type: double
+                    expr: _col6
+                    type: double
+                    expr: _col7
+                    type: double
+                    expr: _col8
+                    type: double
+                    expr: _col9
+                    type: double
+                    expr: UDFToDouble(_col10)
+                    type: double
+              outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+              File Output Operator
+                compressed: false
+                GlobalTableId: 1
+                table:
+                    input format: org.apache.hadoop.mapred.TextInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: dest1
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-52_499_6413045004889165690/-mr-10000
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-52_499_6413045004889165690/-mr-10000
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+130091.0	260.182	256.10355987055016	98.0	0.0	142.9268095075238	143.06995106518906	20428.072876	20469.01089779559	79136.0	309.0

Modified: hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby3_map_skew.q.out Wed Oct 27 19:00:02 2010
@@ -100,7 +100,7 @@ STAGE PLANS:
           aggregations:
                 expr: sum(VALUE._col0)
                 expr: avg(VALUE._col1)
-                expr: avg(DISTINCT KEY._col0)
+                expr: avg(DISTINCT KEY._col0:0._col0)
                 expr: max(VALUE._col3)
                 expr: min(VALUE._col4)
                 expr: std(VALUE._col5)

Modified: hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew.q.out Wed Oct 27 19:00:02 2010
@@ -58,15 +58,15 @@ STAGE PLANS:
       Reduce Operator Tree:
         Group By Operator
           aggregations:
-                expr: sum(KEY._col0)
-                expr: avg(KEY._col0)
-                expr: avg(DISTINCT KEY._col0)
-                expr: max(KEY._col0)
-                expr: min(KEY._col0)
-                expr: std(KEY._col0)
-                expr: stddev_samp(KEY._col0)
-                expr: variance(KEY._col0)
-                expr: var_samp(KEY._col0)
+                expr: sum(KEY._col0:0._col0)
+                expr: avg(KEY._col0:0._col0)
+                expr: avg(DISTINCT KEY._col0:0._col0)
+                expr: max(KEY._col0:0._col0)
+                expr: min(KEY._col0:0._col0)
+                expr: std(KEY._col0:0._col0)
+                expr: stddev_samp(KEY._col0:0._col0)
+                expr: variance(KEY._col0:0._col0)
+                expr: var_samp(KEY._col0:0._col0)
           bucketGroup: false
           mode: complete
           outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8

Added: hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,214 @@
+PREHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE, c10 DOUBLE, c11 DOUBLE) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE, c10 DOUBLE, c11 DOUBLE) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION avg (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI avg (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION std (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION stddev_samp (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION variance (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION var_samp (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TO
 K_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+  Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+          TableScan
+            alias: src
+            Select Operator
+              expressions:
+                    expr: value
+                    type: string
+              outputColumnNames: value
+              Reduce Output Operator
+                key expressions:
+                      expr: substr(value, 5)
+                      type: string
+                sort order: +
+                tag: -1
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: sum(KEY._col0:2._col0)
+                expr: avg(KEY._col0:2._col0)
+                expr: avg(DISTINCT KEY._col0:0._col0)
+                expr: max(KEY._col0:2._col0)
+                expr: min(KEY._col0:2._col0)
+                expr: std(KEY._col0:2._col0)
+                expr: stddev_samp(KEY._col0:2._col0)
+                expr: variance(KEY._col0:2._col0)
+                expr: var_samp(KEY._col0:2._col0)
+                expr: sum(DISTINCT KEY._col0:1._col0)
+                expr: count(DISTINCT KEY._col0:2._col0)
+          bucketGroup: false
+          mode: complete
+          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: double
+                  expr: _col1
+                  type: double
+                  expr: _col2
+                  type: double
+                  expr: _col3
+                  type: string
+                  expr: _col4
+                  type: string
+                  expr: _col5
+                  type: double
+                  expr: _col6
+                  type: double
+                  expr: _col7
+                  type: double
+                  expr: _col8
+                  type: double
+                  expr: _col9
+                  type: double
+                  expr: _col10
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+            Select Operator
+              expressions:
+                    expr: _col0
+                    type: double
+                    expr: _col1
+                    type: double
+                    expr: _col2
+                    type: double
+                    expr: UDFToDouble(_col3)
+                    type: double
+                    expr: UDFToDouble(_col4)
+                    type: double
+                    expr: _col5
+                    type: double
+                    expr: _col6
+                    type: double
+                    expr: _col7
+                    type: double
+                    expr: _col8
+                    type: double
+                    expr: _col9
+                    type: double
+                    expr: UDFToDouble(_col10)
+                    type: double
+              outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+              File Output Operator
+                compressed: false
+                GlobalTableId: 1
+                table:
+                    input format: org.apache.hadoop.mapred.TextInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    name: dest1
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: dest1
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT
+  sum(substr(src.value,5)),
+  avg(substr(src.value,5)),
+  avg(DISTINCT substr(src.value,5)),
+  max(substr(src.value,5)),
+  min(substr(src.value,5)),
+  std(substr(src.value,5)),
+  stddev_samp(substr(src.value,5)),
+  variance(substr(src.value,5)),
+  var_samp(substr(src.value,5)),
+  sum(DISTINCT substr(src.value, 5)),
+  count(DISTINCT substr(src.value, 5))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.null, ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-11_371_9192473715365716502/-mr-10000
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-58-11_371_9192473715365716502/-mr-10000
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.null, ]
+130091.0	260.182	256.10355987055016	98.0	0.0	142.92680950752379	143.06995106518903	20428.07287599999	20469.010897795582	79136.0	309.0

Modified: hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr.q.out Wed Oct 27 19:00:02 2010
@@ -168,7 +168,7 @@ STAGE PLANS:
       Reduce Operator Tree:
         Group By Operator
           aggregations:
-                expr: count(DISTINCT KEY._col1)
+                expr: count(DISTINCT KEY._col1:0._col0)
                 expr: sum(VALUE._col1)
           bucketGroup: false
           keys:

Added: hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,318 @@
+PREHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, C3 INT, c4 INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, C3 INT, c4 INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN EXTENDED
+FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) 
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN EXTENDED
+FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) 
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF srcpart src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5)))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI count (. (TOK_TABLE_OR_COL src) value)))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL src) ds) '2008-04-08')) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+  Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+          TableScan
+            alias: src
+            GatherStats: false
+            Filter Operator
+              isSamplingPred: false
+              predicate:
+                  expr: (ds = '2008-04-08')
+                  type: boolean
+              Filter Operator
+                isSamplingPred: false
+                predicate:
+                    expr: (ds = '2008-04-08')
+                    type: boolean
+                Select Operator
+                  expressions:
+                        expr: key
+                        type: string
+                        expr: value
+                        type: string
+                  outputColumnNames: key, value
+                  Group By Operator
+                    aggregations:
+                          expr: count(DISTINCT substr(value, 5))
+                          expr: sum(substr(value, 5))
+                          expr: sum(DISTINCT substr(value, 5))
+                          expr: count(DISTINCT value)
+                    bucketGroup: false
+                    keys:
+                          expr: substr(key, 1, 1)
+                          type: string
+                          expr: substr(value, 5)
+                          type: string
+                          expr: value
+                          type: string
+                    mode: hash
+                    outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+                    Reduce Output Operator
+                      key expressions:
+                            expr: _col0
+                            type: string
+                            expr: _col1
+                            type: string
+                            expr: _col2
+                            type: string
+                      sort order: +++
+                      Map-reduce partition columns:
+                            expr: _col0
+                            type: string
+                      tag: -1
+                      value expressions:
+                            expr: _col3
+                            type: bigint
+                            expr: _col4
+                            type: double
+                            expr: _col5
+                            type: double
+                            expr: _col6
+                            type: bigint
+      Needs Tagging: false
+      Path -> Alias:
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 [src]
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 [src]
+      Path -> Partition:
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 
+          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 2008-04-08
+              hr 11
+            properties:
+              bucket_count -1
+              columns key,value
+              columns.types string:string
+              file.inputformat org.apache.hadoop.mapred.TextInputFormat
+              file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+              name srcpart
+              partition_columns ds/hr
+              serialization.ddl struct srcpart { string key, string value}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              transient_lastDdlTime 1287568503
+            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.types string:string
+                file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+                name srcpart
+                partition_columns ds/hr
+                serialization.ddl struct srcpart { string key, string value}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                transient_lastDdlTime 1287568503
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: srcpart
+            name: srcpart
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 
+          Partition
+            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 12
+            properties:
+              bucket_count -1
+              columns key,value
+              columns.types string:string
+              file.inputformat org.apache.hadoop.mapred.TextInputFormat
+              file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+              name srcpart
+              partition_columns ds/hr
+              serialization.ddl struct srcpart { string key, string value}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              transient_lastDdlTime 1287568503
+            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.types string:string
+                file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+                name srcpart
+                partition_columns ds/hr
+                serialization.ddl struct srcpart { string key, string value}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                transient_lastDdlTime 1287568503
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: srcpart
+            name: srcpart
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(DISTINCT KEY._col1:0._col0)
+                expr: sum(VALUE._col1)
+                expr: sum(DISTINCT KEY._col1:1._col0)
+                expr: count(DISTINCT KEY._col1:2._col0)
+          bucketGroup: false
+          keys:
+                expr: KEY._col0
+                type: string
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2, _col3, _col4
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: bigint
+                  expr: concat(_col0, _col2)
+                  type: string
+                  expr: _col3
+                  type: double
+                  expr: _col4
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2, _col3, _col4
+            Select Operator
+              expressions:
+                    expr: _col0
+                    type: string
+                    expr: UDFToInteger(_col1)
+                    type: int
+                    expr: _col2
+                    type: string
+                    expr: UDFToInteger(_col3)
+                    type: int
+                    expr: UDFToInteger(_col4)
+                    type: int
+              outputColumnNames: _col0, _col1, _col2, _col3, _col4
+              File Output Operator
+                compressed: false
+                GlobalTableId: 1
+                directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_02-55-09_918_9018058416994975476/-ext-10000
+                NumFilesPerFileSink: 1
+                Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_02-55-09_918_9018058416994975476/-ext-10000/
+                table:
+                    input format: org.apache.hadoop.mapred.TextInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                    properties:
+                      bucket_count -1
+                      columns key,c1,c2,c3,c4
+                      columns.types string:int:string:int:int
+                      file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                      file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/dest1
+                      name dest1
+                      serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4}
+                      serialization.format 1
+                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      transient_lastDdlTime 1287568509
+                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    name: dest1
+                TotalFiles: 1
+                GatherStats: true
+                MultiFileSpray: false
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+          source: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_02-55-09_918_9018058416994975476/-ext-10000
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                bucket_count -1
+                columns key,c1,c2,c3,c4
+                columns.types string:int:string:int:int
+                file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/dest1
+                name dest1
+                serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                transient_lastDdlTime 1287568509
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: dest1
+          tmp directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_02-55-09_918_9018058416994975476/-ext-10001
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+      Stats Aggregation Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_02-55-09_918_9018058416994975476/-ext-10000/
+
+
+PREHOOK: query: FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) 
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) 
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-55-17_568_1009308907147328020/-mr-10000
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_02-55-17_568_1009308907147328020/-mr-10000
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ]
+0	1	00.0	0	1
+1	71	132828.0	10044	71
+2	69	251142.0	15780	69
+3	62	364008.0	20119	62
+4	74	4105526.0	30965	74
+5	6	5794.0	278	6
+6	5	6796.0	331	5
+7	6	71470.0	447	6
+8	8	81524.0	595	8
+9	7	92094.0	577	7

Modified: hive/trunk/ql/src/test/results/clientpositive/groupby_ppr.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby_ppr.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby_ppr.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby_ppr.q.out Wed Oct 27 19:00:02 2010
@@ -151,8 +151,8 @@ STAGE PLANS:
       Reduce Operator Tree:
         Group By Operator
           aggregations:
-                expr: count(DISTINCT KEY._col1)
-                expr: sum(KEY._col1)
+                expr: count(DISTINCT KEY._col1:0._col0)
+                expr: sum(KEY._col1:0._col0)
           bucketGroup: false
           keys:
                 expr: KEY._col0

Added: hive/trunk/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,293 @@
+PREHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN EXTENDED
+FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN EXTENDED
+FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF srcpart src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5)))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI count (. (TOK_TABLE_OR_COL src) value)))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL src) ds) '2008-04-08')) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+  Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        src 
+          TableScan
+            alias: src
+            GatherStats: false
+            Filter Operator
+              isSamplingPred: false
+              predicate:
+                  expr: (ds = '2008-04-08')
+                  type: boolean
+              Filter Operator
+                isSamplingPred: false
+                predicate:
+                    expr: (ds = '2008-04-08')
+                    type: boolean
+                Select Operator
+                  expressions:
+                        expr: key
+                        type: string
+                        expr: value
+                        type: string
+                  outputColumnNames: key, value
+                  Reduce Output Operator
+                    key expressions:
+                          expr: substr(key, 1, 1)
+                          type: string
+                          expr: substr(value, 5)
+                          type: string
+                          expr: value
+                          type: string
+                    sort order: +++
+                    Map-reduce partition columns:
+                          expr: substr(key, 1, 1)
+                          type: string
+                    tag: -1
+      Needs Tagging: false
+      Path -> Alias:
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 [src]
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 [src]
+      Path -> Partition:
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 
+          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 2008-04-08
+              hr 11
+            properties:
+              bucket_count -1
+              columns key,value
+              columns.types string:string
+              file.inputformat org.apache.hadoop.mapred.TextInputFormat
+              file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+              name srcpart
+              partition_columns ds/hr
+              serialization.ddl struct srcpart { string key, string value}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              transient_lastDdlTime 1287568918
+            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.types string:string
+                file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+                name srcpart
+                partition_columns ds/hr
+                serialization.ddl struct srcpart { string key, string value}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                transient_lastDdlTime 1287568918
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: srcpart
+            name: srcpart
+        pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12 
+          Partition
+            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 12
+            properties:
+              bucket_count -1
+              columns key,value
+              columns.types string:string
+              file.inputformat org.apache.hadoop.mapred.TextInputFormat
+              file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+              name srcpart
+              partition_columns ds/hr
+              serialization.ddl struct srcpart { string key, string value}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              transient_lastDdlTime 1287568918
+            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.types string:string
+                file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/srcpart
+                name srcpart
+                partition_columns ds/hr
+                serialization.ddl struct srcpart { string key, string value}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                transient_lastDdlTime 1287568918
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: srcpart
+            name: srcpart
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(DISTINCT KEY._col1:0._col0)
+                expr: sum(KEY._col1:1._col0)
+                expr: sum(DISTINCT KEY._col1:1._col0)
+                expr: count(DISTINCT KEY._col1:2._col0)
+          bucketGroup: false
+          keys:
+                expr: KEY._col0
+                type: string
+          mode: complete
+          outputColumnNames: _col0, _col1, _col2, _col3, _col4
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: bigint
+                  expr: concat(_col0, _col2)
+                  type: string
+                  expr: _col3
+                  type: double
+                  expr: _col4
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2, _col3, _col4
+            Select Operator
+              expressions:
+                    expr: _col0
+                    type: string
+                    expr: UDFToInteger(_col1)
+                    type: int
+                    expr: _col2
+                    type: string
+                    expr: UDFToInteger(_col3)
+                    type: int
+                    expr: UDFToInteger(_col4)
+                    type: int
+              outputColumnNames: _col0, _col1, _col2, _col3, _col4
+              File Output Operator
+                compressed: false
+                GlobalTableId: 1
+                directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_03-02-02_146_1431549693668387725/-ext-10000
+                NumFilesPerFileSink: 1
+                Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_03-02-02_146_1431549693668387725/-ext-10000/
+                table:
+                    input format: org.apache.hadoop.mapred.TextInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                    properties:
+                      bucket_count -1
+                      columns key,c1,c2,c3,c4
+                      columns.types string:int:string:int:int
+                      file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                      file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/dest1
+                      name dest1
+                      serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4}
+                      serialization.format 1
+                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      transient_lastDdlTime 1287568922
+                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    name: dest1
+                TotalFiles: 1
+                GatherStats: true
+                MultiFileSpray: false
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+          source: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_03-02-02_146_1431549693668387725/-ext-10000
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                bucket_count -1
+                columns key,c1,c2,c3,c4
+                columns.types string:int:string:int:int
+                file.inputformat org.apache.hadoop.mapred.TextInputFormat
+                file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/dest1
+                name dest1
+                serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                transient_lastDdlTime 1287568922
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: dest1
+          tmp directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_03-02-02_146_1431549693668387725/-ext-10001
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+      Stats Aggregation Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2010-10-20_03-02-02_146_1431549693668387725/-ext-10000/
+
+
+PREHOOK: query: FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM srcpart src
+INSERT OVERWRITE TABLE dest1 
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.null, ]
+POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-02-06_602_914264234722067634/-mr-10000
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-02-06_602_914264234722067634/-mr-10000
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.null, ]
+POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ]
+0	1	00.0	0	1
+1	71	132828.0	10044	71
+2	69	251142.0	15780	69
+3	62	364008.0	20119	62
+4	74	4105526.0	30965	74
+5	6	5794.0	278	6
+6	5	6796.0	331	5
+7	6	71470.0	447	6
+8	8	81524.0	595	8
+9	7	92094.0	577	7

Modified: hive/trunk/ql/src/test/results/clientpositive/join18.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/join18.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/join18.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/join18.q.out Wed Oct 27 19:00:02 2010
@@ -75,7 +75,7 @@ STAGE PLANS:
       Reduce Operator Tree:
         Group By Operator
           aggregations:
-                expr: count(DISTINCT KEY._col1)
+                expr: count(DISTINCT KEY._col1:0._col0)
           bucketGroup: false
           keys:
                 expr: KEY._col0

Added: hive/trunk/ql/src/test/results/clientpositive/join18_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/join18_multi_distinct.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/join18_multi_distinct.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/join18_multi_distinct.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,596 @@
+PREHOOK: query: EXPLAIN
+ SELECT a.key, a.value, b.key, b.value1,  b.value2
+ FROM 
+  (
+  SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+  ) a
+ FULL OUTER JOIN 
+ (
+  SELECT src2.key as key, count(distinct(src2.value)) AS value1, 
+  count(distinct(src2.key)) AS value2
+  FROM src1 src2 group by src2.key
+ ) b 
+ ON (a.key = b.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+ SELECT a.key, a.value, b.key, b.value1,  b.value2
+ FROM 
+  (
+  SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+  ) a
+ FULL OUTER JOIN 
+ (
+  SELECT src2.key as key, count(distinct(src2.value)) AS value1, 
+  count(distinct(src2.key)) AS value2
+  FROM src1 src2 group by src2.key
+ ) b 
+ ON (a.key = b.key)
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_FULLOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF src src1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL src1) value)) value)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL src1) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF src1 src2)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) key) key) (TOK_SELEXPR (TOK_FUNCTIONDI count (. (TOK_TABLE_OR_COL src2) value)) value1) (TOK_SELEXPR (TOK_FUNCTIONDI count (. (TOK_TABLE_OR_COL src2) key)) value2)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL src2) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key)) (TOK_SE
 LEXPR (. (TOK_TABLE_OR_COL b) value1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value2)))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-2 depends on stages: Stage-1, Stage-3
+  Stage-3 is a root stage
+  Stage-0 is a root stage
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        b:src2 
+          TableScan
+            alias: src2
+            Select Operator
+              expressions:
+                    expr: key
+                    type: string
+                    expr: value
+                    type: string
+              outputColumnNames: key, value
+              Group By Operator
+                aggregations:
+                      expr: count(DISTINCT value)
+                      expr: count(DISTINCT key)
+                bucketGroup: false
+                keys:
+                      expr: key
+                      type: string
+                      expr: value
+                      type: string
+                mode: hash
+                outputColumnNames: _col0, _col1, _col2, _col3
+                Reduce Output Operator
+                  key expressions:
+                        expr: _col0
+                        type: string
+                        expr: _col1
+                        type: string
+                  sort order: ++
+                  Map-reduce partition columns:
+                        expr: _col0
+                        type: string
+                  tag: -1
+                  value expressions:
+                        expr: _col2
+                        type: bigint
+                        expr: _col3
+                        type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(DISTINCT KEY._col1:0._col0)
+                expr: count(DISTINCT KEY._col1:1._col0)
+          bucketGroup: false
+          keys:
+                expr: KEY._col1:1._col0
+                type: string
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: bigint
+                  expr: _col2
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+              table:
+                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+  Stage: Stage-2
+    Map Reduce
+      Alias -> Map Operator Tree:
+        $INTNAME 
+            Reduce Output Operator
+              key expressions:
+                    expr: _col0
+                    type: string
+              sort order: +
+              Map-reduce partition columns:
+                    expr: _col0
+                    type: string
+              tag: 1
+              value expressions:
+                    expr: _col0
+                    type: string
+                    expr: _col1
+                    type: bigint
+                    expr: _col2
+                    type: bigint
+        $INTNAME1 
+            Reduce Output Operator
+              key expressions:
+                    expr: _col0
+                    type: string
+              sort order: +
+              Map-reduce partition columns:
+                    expr: _col0
+                    type: string
+              tag: 0
+              value expressions:
+                    expr: _col0
+                    type: string
+                    expr: _col1
+                    type: bigint
+      Reduce Operator Tree:
+        Join Operator
+          condition map:
+               Outer Join 0 to 1
+          condition expressions:
+            0 {VALUE._col0} {VALUE._col1}
+            1 {VALUE._col0} {VALUE._col1} {VALUE._col2}
+          handleSkewJoin: false
+          outputColumnNames: _col0, _col1, _col2, _col3, _col4
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: bigint
+                  expr: _col2
+                  type: string
+                  expr: _col3
+                  type: bigint
+                  expr: _col4
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2, _col3, _col4
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+  Stage: Stage-3
+    Map Reduce
+      Alias -> Map Operator Tree:
+        a:src1 
+          TableScan
+            alias: src1
+            Select Operator
+              expressions:
+                    expr: key
+                    type: string
+                    expr: value
+                    type: string
+              outputColumnNames: key, value
+              Group By Operator
+                aggregations:
+                      expr: count(value)
+                bucketGroup: false
+                keys:
+                      expr: key
+                      type: string
+                mode: hash
+                outputColumnNames: _col0, _col1
+                Reduce Output Operator
+                  key expressions:
+                        expr: _col0
+                        type: string
+                  sort order: +
+                  Map-reduce partition columns:
+                        expr: _col0
+                        type: string
+                  tag: -1
+                  value expressions:
+                        expr: _col1
+                        type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(VALUE._col0)
+          bucketGroup: false
+          keys:
+                expr: KEY._col0
+                type: string
+          mode: mergepartial
+          outputColumnNames: _col0, _col1
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: bigint
+            outputColumnNames: _col0, _col1
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+              table:
+                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+
+
+PREHOOK: query: SELECT a.key, a.value, b.key, b.value1,  b.value2
+ FROM 
+  (
+  SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+  ) a
+ FULL OUTER JOIN 
+ (
+  SELECT src2.key as key, count(distinct(src2.value)) AS value1,
+  count(distinct(src2.key)) AS value2
+  FROM src1 src2 group by src2.key
+ ) b 
+ ON (a.key = b.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-06-44_648_893234056742394843/-mr-10000
+POSTHOOK: query: SELECT a.key, a.value, b.key, b.value1,  b.value2
+ FROM 
+  (
+  SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+  ) a
+ FULL OUTER JOIN 
+ (
+  SELECT src2.key as key, count(distinct(src2.value)) AS value1,
+  count(distinct(src2.key)) AS value2
+  FROM src1 src2 group by src2.key
+ ) b 
+ ON (a.key = b.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-06-44_648_893234056742394843/-mr-10000
+NULL	NULL		1	0
+NULL	NULL		1	0
+NULL	NULL		1	0
+NULL	NULL		1	1
+0	3	NULL	NULL	NULL
+10	1	NULL	NULL	NULL
+100	2	NULL	NULL	NULL
+103	2	NULL	NULL	NULL
+104	2	NULL	NULL	NULL
+105	1	NULL	NULL	NULL
+11	1	NULL	NULL	NULL
+111	1	NULL	NULL	NULL
+113	2	NULL	NULL	NULL
+114	1	NULL	NULL	NULL
+116	1	NULL	NULL	NULL
+118	2	NULL	NULL	NULL
+119	3	NULL	NULL	NULL
+12	2	NULL	NULL	NULL
+120	2	NULL	NULL	NULL
+125	2	NULL	NULL	NULL
+126	1	NULL	NULL	NULL
+128	3	128	0	1
+129	2	NULL	NULL	NULL
+131	1	NULL	NULL	NULL
+133	1	NULL	NULL	NULL
+134	2	NULL	NULL	NULL
+136	1	NULL	NULL	NULL
+137	2	NULL	NULL	NULL
+138	4	NULL	NULL	NULL
+143	1	NULL	NULL	NULL
+145	1	NULL	NULL	NULL
+146	2	146	0	1
+149	2	NULL	NULL	NULL
+15	2	NULL	NULL	NULL
+150	1	150	0	1
+152	2	NULL	NULL	NULL
+153	1	NULL	NULL	NULL
+155	1	NULL	NULL	NULL
+156	1	NULL	NULL	NULL
+157	1	NULL	NULL	NULL
+158	1	NULL	NULL	NULL
+160	1	NULL	NULL	NULL
+162	1	NULL	NULL	NULL
+163	1	NULL	NULL	NULL
+164	2	NULL	NULL	NULL
+165	2	NULL	NULL	NULL
+166	1	NULL	NULL	NULL
+167	3	NULL	NULL	NULL
+168	1	NULL	NULL	NULL
+169	4	NULL	NULL	NULL
+17	1	NULL	NULL	NULL
+170	1	NULL	NULL	NULL
+172	2	NULL	NULL	NULL
+174	2	NULL	NULL	NULL
+175	2	NULL	NULL	NULL
+176	2	NULL	NULL	NULL
+177	1	NULL	NULL	NULL
+178	1	NULL	NULL	NULL
+179	2	NULL	NULL	NULL
+18	2	NULL	NULL	NULL
+180	1	NULL	NULL	NULL
+181	1	NULL	NULL	NULL
+183	1	NULL	NULL	NULL
+186	1	NULL	NULL	NULL
+187	3	NULL	NULL	NULL
+189	1	NULL	NULL	NULL
+19	1	NULL	NULL	NULL
+190	1	NULL	NULL	NULL
+191	2	NULL	NULL	NULL
+192	1	NULL	NULL	NULL
+193	3	NULL	NULL	NULL
+194	1	NULL	NULL	NULL
+195	2	NULL	NULL	NULL
+196	1	NULL	NULL	NULL
+197	2	NULL	NULL	NULL
+199	3	NULL	NULL	NULL
+2	1	NULL	NULL	NULL
+20	1	NULL	NULL	NULL
+200	2	NULL	NULL	NULL
+201	1	NULL	NULL	NULL
+202	1	NULL	NULL	NULL
+203	2	NULL	NULL	NULL
+205	2	NULL	NULL	NULL
+207	2	NULL	NULL	NULL
+208	3	NULL	NULL	NULL
+209	2	NULL	NULL	NULL
+213	2	213	0	1
+214	1	NULL	NULL	NULL
+216	2	NULL	NULL	NULL
+217	2	NULL	NULL	NULL
+218	1	NULL	NULL	NULL
+219	2	NULL	NULL	NULL
+221	2	NULL	NULL	NULL
+222	1	NULL	NULL	NULL
+223	2	NULL	NULL	NULL
+224	2	224	0	1
+226	1	NULL	NULL	NULL
+228	1	NULL	NULL	NULL
+229	2	NULL	NULL	NULL
+230	5	NULL	NULL	NULL
+233	2	NULL	NULL	NULL
+235	1	NULL	NULL	NULL
+237	2	NULL	NULL	NULL
+238	2	238	0	1
+239	2	NULL	NULL	NULL
+24	2	NULL	NULL	NULL
+241	1	NULL	NULL	NULL
+242	2	NULL	NULL	NULL
+244	1	NULL	NULL	NULL
+247	1	NULL	NULL	NULL
+248	1	NULL	NULL	NULL
+249	1	NULL	NULL	NULL
+252	1	NULL	NULL	NULL
+255	2	255	0	1
+256	2	NULL	NULL	NULL
+257	1	NULL	NULL	NULL
+258	1	NULL	NULL	NULL
+26	2	NULL	NULL	NULL
+260	1	NULL	NULL	NULL
+262	1	NULL	NULL	NULL
+263	1	NULL	NULL	NULL
+265	2	NULL	NULL	NULL
+266	1	NULL	NULL	NULL
+27	1	NULL	NULL	NULL
+272	2	NULL	NULL	NULL
+273	3	273	0	1
+274	1	NULL	NULL	NULL
+275	1	NULL	NULL	NULL
+277	4	NULL	NULL	NULL
+278	2	278	0	1
+28	1	NULL	NULL	NULL
+280	2	NULL	NULL	NULL
+281	2	NULL	NULL	NULL
+282	2	NULL	NULL	NULL
+283	1	NULL	NULL	NULL
+284	1	NULL	NULL	NULL
+285	1	NULL	NULL	NULL
+286	1	NULL	NULL	NULL
+287	1	NULL	NULL	NULL
+288	2	NULL	NULL	NULL
+289	1	NULL	NULL	NULL
+291	1	NULL	NULL	NULL
+292	1	NULL	NULL	NULL
+296	1	NULL	NULL	NULL
+298	3	NULL	NULL	NULL
+30	1	NULL	NULL	NULL
+302	1	NULL	NULL	NULL
+305	1	NULL	NULL	NULL
+306	1	NULL	NULL	NULL
+307	2	NULL	NULL	NULL
+308	1	NULL	NULL	NULL
+309	2	NULL	NULL	NULL
+310	1	NULL	NULL	NULL
+311	3	311	0	1
+315	1	NULL	NULL	NULL
+316	3	NULL	NULL	NULL
+317	2	NULL	NULL	NULL
+318	3	NULL	NULL	NULL
+321	2	NULL	NULL	NULL
+322	2	NULL	NULL	NULL
+323	1	NULL	NULL	NULL
+325	2	NULL	NULL	NULL
+327	3	NULL	NULL	NULL
+33	1	NULL	NULL	NULL
+331	2	NULL	NULL	NULL
+332	1	NULL	NULL	NULL
+333	2	NULL	NULL	NULL
+335	1	NULL	NULL	NULL
+336	1	NULL	NULL	NULL
+338	1	NULL	NULL	NULL
+339	1	NULL	NULL	NULL
+34	1	NULL	NULL	NULL
+341	1	NULL	NULL	NULL
+342	2	NULL	NULL	NULL
+344	2	NULL	NULL	NULL
+345	1	NULL	NULL	NULL
+348	5	NULL	NULL	NULL
+35	3	NULL	NULL	NULL
+351	1	NULL	NULL	NULL
+353	2	NULL	NULL	NULL
+356	1	NULL	NULL	NULL
+360	1	NULL	NULL	NULL
+362	1	NULL	NULL	NULL
+364	1	NULL	NULL	NULL
+365	1	NULL	NULL	NULL
+366	1	NULL	NULL	NULL
+367	2	NULL	NULL	NULL
+368	1	NULL	NULL	NULL
+369	3	369	0	1
+37	2	NULL	NULL	NULL
+373	1	NULL	NULL	NULL
+374	1	NULL	NULL	NULL
+375	1	NULL	NULL	NULL
+377	1	NULL	NULL	NULL
+378	1	NULL	NULL	NULL
+379	1	NULL	NULL	NULL
+382	2	NULL	NULL	NULL
+384	3	NULL	NULL	NULL
+386	1	NULL	NULL	NULL
+389	1	NULL	NULL	NULL
+392	1	NULL	NULL	NULL
+393	1	NULL	NULL	NULL
+394	1	NULL	NULL	NULL
+395	2	NULL	NULL	NULL
+396	3	NULL	NULL	NULL
+397	2	NULL	NULL	NULL
+399	2	NULL	NULL	NULL
+4	1	NULL	NULL	NULL
+400	1	NULL	NULL	NULL
+401	5	401	0	1
+402	1	NULL	NULL	NULL
+403	3	NULL	NULL	NULL
+404	2	NULL	NULL	NULL
+406	4	406	0	1
+407	1	NULL	NULL	NULL
+409	3	NULL	NULL	NULL
+41	1	NULL	NULL	NULL
+411	1	NULL	NULL	NULL
+413	2	NULL	NULL	NULL
+414	2	NULL	NULL	NULL
+417	3	NULL	NULL	NULL
+418	1	NULL	NULL	NULL
+419	1	NULL	NULL	NULL
+42	2	NULL	NULL	NULL
+421	1	NULL	NULL	NULL
+424	2	NULL	NULL	NULL
+427	1	NULL	NULL	NULL
+429	2	NULL	NULL	NULL
+43	1	NULL	NULL	NULL
+430	3	NULL	NULL	NULL
+431	3	NULL	NULL	NULL
+432	1	NULL	NULL	NULL
+435	1	NULL	NULL	NULL
+436	1	NULL	NULL	NULL
+437	1	NULL	NULL	NULL
+438	3	NULL	NULL	NULL
+439	2	NULL	NULL	NULL
+44	1	NULL	NULL	NULL
+443	1	NULL	NULL	NULL
+444	1	NULL	NULL	NULL
+446	1	NULL	NULL	NULL
+448	1	NULL	NULL	NULL
+449	1	NULL	NULL	NULL
+452	1	NULL	NULL	NULL
+453	1	NULL	NULL	NULL
+454	3	NULL	NULL	NULL
+455	1	NULL	NULL	NULL
+457	1	NULL	NULL	NULL
+458	2	NULL	NULL	NULL
+459	2	NULL	NULL	NULL
+460	1	NULL	NULL	NULL
+462	2	NULL	NULL	NULL
+463	2	NULL	NULL	NULL
+466	3	NULL	NULL	NULL
+467	1	NULL	NULL	NULL
+468	4	NULL	NULL	NULL
+469	5	NULL	NULL	NULL
+47	1	NULL	NULL	NULL
+470	1	NULL	NULL	NULL
+472	1	NULL	NULL	NULL
+475	1	NULL	NULL	NULL
+477	1	NULL	NULL	NULL
+478	2	NULL	NULL	NULL
+479	1	NULL	NULL	NULL
+480	3	NULL	NULL	NULL
+481	1	NULL	NULL	NULL
+482	1	NULL	NULL	NULL
+483	1	NULL	NULL	NULL
+484	1	NULL	NULL	NULL
+485	1	NULL	NULL	NULL
+487	1	NULL	NULL	NULL
+489	4	NULL	NULL	NULL
+490	1	NULL	NULL	NULL
+491	1	NULL	NULL	NULL
+492	2	NULL	NULL	NULL
+493	1	NULL	NULL	NULL
+494	1	NULL	NULL	NULL
+495	1	NULL	NULL	NULL
+496	1	NULL	NULL	NULL
+497	1	NULL	NULL	NULL
+498	3	NULL	NULL	NULL
+5	3	NULL	NULL	NULL
+51	2	NULL	NULL	NULL
+53	1	NULL	NULL	NULL
+54	1	NULL	NULL	NULL
+57	1	NULL	NULL	NULL
+58	2	NULL	NULL	NULL
+64	1	NULL	NULL	NULL
+65	1	NULL	NULL	NULL
+66	1	66	0	1
+67	2	NULL	NULL	NULL
+69	1	NULL	NULL	NULL
+70	3	NULL	NULL	NULL
+72	2	NULL	NULL	NULL
+74	1	NULL	NULL	NULL
+76	2	NULL	NULL	NULL
+77	1	NULL	NULL	NULL
+78	1	NULL	NULL	NULL
+8	1	NULL	NULL	NULL
+80	1	NULL	NULL	NULL
+82	1	NULL	NULL	NULL
+83	2	NULL	NULL	NULL
+84	2	NULL	NULL	NULL
+85	1	NULL	NULL	NULL
+86	1	NULL	NULL	NULL
+87	1	NULL	NULL	NULL
+9	1	NULL	NULL	NULL
+90	3	NULL	NULL	NULL
+92	1	NULL	NULL	NULL
+95	2	NULL	NULL	NULL
+96	1	NULL	NULL	NULL
+97	2	NULL	NULL	NULL
+98	2	98	0	1
+NULL	NULL	val_146	1	0
+NULL	NULL	val_150	1	0
+NULL	NULL	val_165	1	0
+NULL	NULL	val_193	1	0
+NULL	NULL	val_213	1	0
+NULL	NULL	val_238	1	0
+NULL	NULL	val_255	1	0
+NULL	NULL	val_265	1	0
+NULL	NULL	val_27	1	0
+NULL	NULL	val_273	1	0
+NULL	NULL	val_278	1	0
+NULL	NULL	val_311	1	0
+NULL	NULL	val_401	1	0
+NULL	NULL	val_406	1	0
+NULL	NULL	val_409	1	0
+NULL	NULL	val_484	1	0
+NULL	NULL	val_66	1	0
+NULL	NULL	val_98	1	0

Modified: hive/trunk/ql/src/test/results/clientpositive/join25.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/join25.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/join25.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/join25.q.out Wed Oct 27 19:00:02 2010
@@ -36,9 +36,7 @@ STAGE PLANS:
         x 
           TableScan
             alias: x
-            Common Join Operator
-              condition map:
-                   Inner Join 0 to 1
+            JDBM Sink Operator
               condition expressions:
                 0 {key} {value}
                 1 {value}
@@ -46,7 +44,6 @@ STAGE PLANS:
               keys:
                 0 [Column[key]]
                 1 [Column[key]]
-              outputColumnNames: _col0, _col1, _col5
               Position of Big Table: 1
 
   Stage: Stage-1
@@ -55,7 +52,7 @@ STAGE PLANS:
         y 
           TableScan
             alias: y
-            Common Join Operator
+            Map Join Operator
               condition map:
                    Inner Join 0 to 1
               condition expressions:
@@ -112,7 +109,7 @@ STAGE PLANS:
     Move Operator
       files:
           hdfs directory: true
-          destination: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_14-31-18_284_5431009683335318359/-ext-10000
+          destination: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-58_967_6806228839153646653/-ext-10000
 
   Stage: Stage-0
     Move Operator
@@ -130,7 +127,7 @@ STAGE PLANS:
   Stage: Stage-3
     Map Reduce
       Alias -> Map Operator Tree:
-        pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_14-31-18_284_5431009683335318359/-ext-10002 
+        pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-58_967_6806228839153646653/-ext-10002 
             File Output Operator
               compressed: false
               GlobalTableId: 0
@@ -161,11 +158,11 @@ POSTHOOK: Lineage: dest_j1.value SIMPLE 
 PREHOOK: query: select * from dest_j1 x order by x.key
 PREHOOK: type: QUERY
 PREHOOK: Input: default@dest_j1
-PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_14-31-25_895_7020388466103281499/-mr-10000
+PREHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-54-04_814_7186456825570807641/-mr-10000
 POSTHOOK: query: select * from dest_j1 x order by x.key
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@dest_j1
-POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_14-31-25_895_7020388466103281499/-mr-10000
+POSTHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-54-04_814_7186456825570807641/-mr-10000
 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
 POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
 POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]