Author: namit
Date: Tue Oct 25 03:46:59 2011
New Revision: 1188507

URL: http://svn.apache.org/viewvc?rev=1188507&view=rev
Log:
HIVE-2497 partition pruning prune some right partition under specific conditions
(binlijin via namit)

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -


Added:
    hive/trunk/ql/src/test/queries/clientpositive/ppr_allchildsarenull.q
    hive/trunk/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out
Modified:
    
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/ExprProcFactory.java

Modified: 
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/ExprProcFactory.java
URL: 
http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/ExprProcFactory.java?rev=1188507&r1=1188506&r2=1188507&view=diff
==============================================================================
--- 
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/ExprProcFactory.java
 (original)
+++ 
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/ExprProcFactory.java
 Tue Oct 25 03:46:59 2011
@@ -104,6 +104,16 @@ public final class ExprProcFactory {
         // values) should derive from a common base class UDFNullAsUnknown, so
         // instead of listing the classes
         // here we would test whether a class is derived from that base class.
+        // If All childs are null, set unknown to true
+        boolean isAllNull = true;
+        for (Object child : nodeOutputs) {
+          ExprNodeDesc child_nd = (ExprNodeDesc) child;
+          if (!(child_nd instanceof ExprNodeConstantDesc
+              && ((ExprNodeConstantDesc) child_nd).getValue() == null)) {
+            isAllNull = false;
+          }
+        }
+        unknown = isAllNull;
       } else if (!FunctionRegistry.isDeterministic(fd.getGenericUDF())) {
         // If it's a non-deterministic UDF, set unknown to true
         unknown = true;

Added: hive/trunk/ql/src/test/queries/clientpositive/ppr_allchildsarenull.q
URL: 
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/ppr_allchildsarenull.q?rev=1188507&view=auto
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/ppr_allchildsarenull.q (added)
+++ hive/trunk/ql/src/test/queries/clientpositive/ppr_allchildsarenull.q Tue 
Oct 25 03:46:59 2011
@@ -0,0 +1,41 @@
+set hive.optimize.ppd=true;
+
+EXPLAIN EXTENDED
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+;
+
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+;
+
+set hive.optimize.ppd=false;
+
+EXPLAIN EXTENDED
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+;
+
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+;

Added: hive/trunk/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out
URL: 
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out?rev=1188507&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out 
(added)
+++ hive/trunk/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out 
Tue Oct 25 03:46:59 2011
@@ -0,0 +1,442 @@
+PREHOOK: query: EXPLAIN EXTENDED
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN EXTENDED
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME srcpart))) (TOK_INSERT 
(TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION 
TOK_INT (TOK_TABLE_OR_COL key)) user_id) (TOK_SELEXPR (TOK_TABLE_OR_COL 
value))) (TOK_WHERE (and (= (TOK_TABLE_OR_COL ds) '2008-04-08') (> 
(TOK_FUNCTION WHEN (OR (LIKE (TOK_TABLE_OR_COL value) 'aaa%') (LIKE 
(TOK_TABLE_OR_COL value) 'vvv%')) 1 0) 0)))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 is a root stage
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        srcpart 
+          TableScan
+            alias: srcpart
+            GatherStats: false
+            Filter Operator
+              isSamplingPred: false
+              predicate:
+                  expr: (CASE WHEN (((value like 'aaa%') or (value like 
'vvv%'))) THEN (1) ELSE (0) END > 0)
+                  type: boolean
+              Select Operator
+                expressions:
+                      expr: UDFToInteger(key)
+                      type: int
+                      expr: value
+                      type: string
+                outputColumnNames: _col0, _col1
+                File Output Operator
+                  compressed: false
+                  GlobalTableId: 0
+                  directory: 
file:/tmp/njain/hive_2011-10-24_14-00-01_801_7691264636007259639/-ext-10001
+                  NumFilesPerFileSink: 1
+                  Stats Publishing Key Prefix: 
file:/tmp/njain/hive_2011-10-24_14-00-01_801_7691264636007259639/-ext-10001/
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: 
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      properties:
+                        columns _col0,_col1
+                        columns.types int:string
+                        escape.delim \
+                        serialization.format 1
+                  TotalFiles: 1
+                  GatherStats: false
+                  MultiFileSpray: false
+      Needs Tagging: false
+      Path -> Alias:
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11
 [srcpart]
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12
 [srcpart]
+      Path -> Partition:
+        
pfile:/data/users/njain/hive_commit3/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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11
+              name default.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 1319489993
+            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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart
+                name default.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 1319489991
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.srcpart
+            name: default.srcpart
+        
pfile:/data/users/njain/hive_commit3/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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12
+              name default.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 1319489994
+            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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart
+                name default.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 1319489991
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.srcpart
+            name: default.srcpart
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+
+
+PREHOOK: query: SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+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: 
file:/tmp/njain/hive_2011-10-24_14-00-04_232_5608766370821242381/-mr-10000
+POSTHOOK: query: SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+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: 
file:/tmp/njain/hive_2011-10-24_14-00-04_232_5608766370821242381/-mr-10000
+PREHOOK: query: EXPLAIN EXTENDED
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN EXTENDED
+SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME srcpart))) (TOK_INSERT 
(TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION 
TOK_INT (TOK_TABLE_OR_COL key)) user_id) (TOK_SELEXPR (TOK_TABLE_OR_COL 
value))) (TOK_WHERE (and (= (TOK_TABLE_OR_COL ds) '2008-04-08') (> 
(TOK_FUNCTION WHEN (OR (LIKE (TOK_TABLE_OR_COL value) 'aaa%') (LIKE 
(TOK_TABLE_OR_COL value) 'vvv%')) 1 0) 0)))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 is a root stage
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        srcpart 
+          TableScan
+            alias: srcpart
+            GatherStats: false
+            Filter Operator
+              isSamplingPred: false
+              predicate:
+                  expr: ((ds = '2008-04-08') and (CASE WHEN (((value like 
'aaa%') or (value like 'vvv%'))) THEN (1) ELSE (0) END > 0))
+                  type: boolean
+              Select Operator
+                expressions:
+                      expr: UDFToInteger(key)
+                      type: int
+                      expr: value
+                      type: string
+                outputColumnNames: _col0, _col1
+                File Output Operator
+                  compressed: false
+                  GlobalTableId: 0
+                  directory: 
file:/tmp/njain/hive_2011-10-24_14-00-08_867_8412389299385207830/-ext-10001
+                  NumFilesPerFileSink: 1
+                  Stats Publishing Key Prefix: 
file:/tmp/njain/hive_2011-10-24_14-00-08_867_8412389299385207830/-ext-10001/
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: 
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      properties:
+                        columns _col0,_col1
+                        columns.types int:string
+                        escape.delim \
+                        serialization.format 1
+                  TotalFiles: 1
+                  GatherStats: false
+                  MultiFileSpray: false
+      Needs Tagging: false
+      Path -> Alias:
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11
 [srcpart]
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12
 [srcpart]
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-09/hr=11
 [srcpart]
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-09/hr=12
 [srcpart]
+      Path -> Partition:
+        
pfile:/data/users/njain/hive_commit3/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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11
+              name default.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 1319489993
+            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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart
+                name default.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 1319489991
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.srcpart
+            name: default.srcpart
+        
pfile:/data/users/njain/hive_commit3/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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=12
+              name default.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 1319489994
+            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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart
+                name default.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 1319489991
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.srcpart
+            name: default.srcpart
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-09/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 2008-04-09
+              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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-09/hr=11
+              name default.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 1319489994
+            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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart
+                name default.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 1319489991
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.srcpart
+            name: default.srcpart
+        
pfile:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-09/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 2008-04-09
+              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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart/ds=2008-04-09/hr=12
+              name default.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 1319489995
+            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:/data/users/njain/hive_commit3/build/ql/test/data/warehouse/srcpart
+                name default.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 1319489991
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.srcpart
+            name: default.srcpart
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+
+
+PREHOOK: query: SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+PREHOOK: type: QUERY
+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
+PREHOOK: Output: 
file:/tmp/njain/hive_2011-10-24_14-00-09_075_3165409676940809709/-mr-10000
+POSTHOOK: query: SELECT
+  CAST(key AS INT) AS user_id, value
+  FROM srcpart
+  WHERE ds='2008-04-08' and
+  ( CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%')
+   THEN 1
+   ELSE 0  end ) > 0
+POSTHOOK: type: QUERY
+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
+POSTHOOK: Output: 
file:/tmp/njain/hive_2011-10-24_14-00-09_075_3165409676940809709/-mr-10000


Reply via email to