hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From na...@apache.org
Subject svn commit: r1440271 [5/7] - in /hive/trunk: ./ common/src/java/org/apache/hadoop/hive/conf/ conf/ ql/src/java/org/apache/hadoop/hive/ql/exec/ ql/src/java/org/apache/hadoop/hive/ql/lib/ ql/src/java/org/apache/hadoop/hive/ql/metadata/ ql/src/java/org/ap...
Date Wed, 30 Jan 2013 04:20:41 GMT
Added: hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out?rev=1440271&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out Wed Jan 30 04:20:39 2013
@@ -0,0 +1,825 @@
+PREHOOK: query: -- This tests inferring how data is bucketed/sorted from the operators in the reducer
+-- and populating that information in partitions' metadata, in particular, this tests
+-- the grouping operators rollup/cube/grouping sets
+
+CREATE TABLE test_table_out (key STRING, value STRING, agg STRING) PARTITIONED BY (part STRING)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: -- This tests inferring how data is bucketed/sorted from the operators in the reducer
+-- and populating that information in partitions' metadata, in particular, this tests
+-- the grouping operators rollup/cube/grouping sets
+
+CREATE TABLE test_table_out (key STRING, value STRING, agg STRING) PARTITIONED BY (part STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@test_table_out
+PREHOOK: query: CREATE TABLE test_table_out_2 (key STRING, value STRING, grouping_key STRING, agg STRING) PARTITIONED BY (part STRING)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE test_table_out_2 (key STRING, value STRING, grouping_key STRING, agg STRING) PARTITIONED BY (part STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@test_table_out_2
+PREHOOK: query: -- Test rollup, should not be bucketed or sorted because its missing the grouping ID
+EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH ROLLUP
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Test rollup, should not be bucketed or sorted because its missing the grouping ID
+EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH ROLLUP
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table_out) (TOK_PARTSPEC (TOK_PARTVAL part '1')))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_ROLLUP_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL value))))
+
+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: key
+                    type: string
+                    expr: value
+                    type: string
+              outputColumnNames: key, value
+              Group By Operator
+                aggregations:
+                      expr: count(1)
+                bucketGroup: false
+                keys:
+                      expr: key
+                      type: string
+                      expr: value
+                      type: string
+                      expr: '0'
+                      type: string
+                mode: hash
+                outputColumnNames: _col0, _col1, _col2, _col3
+                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
+                        expr: _col1
+                        type: string
+                        expr: _col2
+                        type: string
+                  tag: -1
+                  value expressions:
+                        expr: _col3
+                        type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(VALUE._col0)
+          bucketGroup: false
+          keys:
+                expr: KEY._col0
+                type: string
+                expr: KEY._col1
+                type: string
+                expr: KEY._col2
+                type: string
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2, _col3
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: string
+                  expr: _col3
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2
+            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: default.test_table_out
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          partition:
+            part 1
+          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: default.test_table_out
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH ROLLUP
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table_out@part=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH ROLLUP
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table_out@part=1
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+agg                 	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	test_table_out      	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	1                   
+	numRows             	619                 
+	rawDataSize         	6309                
+	totalSize           	6928                
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	-1                  	 
+Bucket Columns:     	[]                  	 
+Sort Columns:       	[]                  	 
+Storage Desc Params:	 	 
+	serialization.format	1                   
+PREHOOK: query: -- Test rollup, should be bucketed and sorted on key, value, grouping_key
+
+INSERT OVERWRITE TABLE test_table_out_2 PARTITION (part = '1') 
+SELECT key, value, GROUPING__ID, count(1) FROM src GROUP BY key, value WITH ROLLUP
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table_out_2@part=1
+POSTHOOK: query: -- Test rollup, should be bucketed and sorted on key, value, grouping_key
+
+INSERT OVERWRITE TABLE test_table_out_2 PARTITION (part = '1') 
+SELECT key, value, GROUPING__ID, count(1) FROM src GROUP BY key, value WITH ROLLUP
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table_out_2@part=1
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: DESCRIBE FORMATTED test_table_out_2 PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESCRIBE FORMATTED test_table_out_2 PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+grouping_key        	string              	None                
+agg                 	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	test_table_out_2    	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	1                   
+	numRows             	619                 
+	rawDataSize         	7547                
+	totalSize           	8166                
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	1                   	 
+Bucket Columns:     	[key, value, grouping_key]	 
+Sort Columns:       	[Order(col:key, order:1), Order(col:value, order:1), Order(col:grouping_key, order:1)]	 
+Storage Desc Params:	 	 
+	serialization.format	1                   
+PREHOOK: query: -- Test cube, should not be bucketed or sorted because its missing the grouping ID
+EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH CUBE
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Test cube, should not be bucketed or sorted because its missing the grouping ID
+EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH CUBE
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table_out) (TOK_PARTSPEC (TOK_PARTVAL part '1')))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL value))))
+
+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: key
+                    type: string
+                    expr: value
+                    type: string
+              outputColumnNames: key, value
+              Group By Operator
+                aggregations:
+                      expr: count(1)
+                bucketGroup: false
+                keys:
+                      expr: key
+                      type: string
+                      expr: value
+                      type: string
+                      expr: '0'
+                      type: string
+                mode: hash
+                outputColumnNames: _col0, _col1, _col2, _col3
+                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
+                        expr: _col1
+                        type: string
+                        expr: _col2
+                        type: string
+                  tag: -1
+                  value expressions:
+                        expr: _col3
+                        type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(VALUE._col0)
+          bucketGroup: false
+          keys:
+                expr: KEY._col0
+                type: string
+                expr: KEY._col1
+                type: string
+                expr: KEY._col2
+                type: string
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2, _col3
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: string
+                  expr: _col3
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2
+            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: default.test_table_out
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          partition:
+            part 1
+          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: default.test_table_out
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH CUBE
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table_out@part=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value WITH CUBE
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table_out@part=1
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+agg                 	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	test_table_out      	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	1                   
+	numRows             	928                 
+	rawDataSize         	9954                
+	totalSize           	10882               
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	-1                  	 
+Bucket Columns:     	[]                  	 
+Sort Columns:       	[]                  	 
+Storage Desc Params:	 	 
+	serialization.format	1                   
+PREHOOK: query: -- Test cube, should be bucketed and sorted on key, value, grouping_key
+
+INSERT OVERWRITE TABLE test_table_out_2 PARTITION (part = '1') 
+SELECT key, value, GROUPING__ID, count(1) FROM src GROUP BY key, value WITH CUBE
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table_out_2@part=1
+POSTHOOK: query: -- Test cube, should be bucketed and sorted on key, value, grouping_key
+
+INSERT OVERWRITE TABLE test_table_out_2 PARTITION (part = '1') 
+SELECT key, value, GROUPING__ID, count(1) FROM src GROUP BY key, value WITH CUBE
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table_out_2@part=1
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: DESCRIBE FORMATTED test_table_out_2 PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESCRIBE FORMATTED test_table_out_2 PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+grouping_key        	string              	None                
+agg                 	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	test_table_out_2    	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	1                   
+	numRows             	928                 
+	rawDataSize         	11810               
+	totalSize           	12738               
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	1                   	 
+Bucket Columns:     	[key, value, grouping_key]	 
+Sort Columns:       	[Order(col:key, order:1), Order(col:value, order:1), Order(col:grouping_key, order:1)]	 
+Storage Desc Params:	 	 
+	serialization.format	1                   
+PREHOOK: query: -- Test grouping sets, should not be bucketed or sorted because its missing the grouping ID
+EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value GROUPING SETS (key, value)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Test grouping sets, should not be bucketed or sorted because its missing the grouping ID
+EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value GROUPING SETS (key, value)
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table_out) (TOK_PARTSPEC (TOK_PARTVAL part '1')))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPING_SETS (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL value) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL key)) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL value)))))
+
+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: key
+                    type: string
+                    expr: value
+                    type: string
+              outputColumnNames: key, value
+              Group By Operator
+                aggregations:
+                      expr: count(1)
+                bucketGroup: false
+                keys:
+                      expr: key
+                      type: string
+                      expr: value
+                      type: string
+                      expr: '0'
+                      type: string
+                mode: hash
+                outputColumnNames: _col0, _col1, _col2, _col3
+                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
+                        expr: _col1
+                        type: string
+                        expr: _col2
+                        type: string
+                  tag: -1
+                  value expressions:
+                        expr: _col3
+                        type: bigint
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(VALUE._col0)
+          bucketGroup: false
+          keys:
+                expr: KEY._col0
+                type: string
+                expr: KEY._col1
+                type: string
+                expr: KEY._col2
+                type: string
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2, _col3
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: string
+                  expr: _col1
+                  type: string
+                  expr: _col3
+                  type: bigint
+            outputColumnNames: _col0, _col1, _col2
+            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: default.test_table_out
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          partition:
+            part 1
+          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: default.test_table_out
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value GROUPING SETS (key, value)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table_out@part=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') 
+SELECT key, value, count(1) FROM src GROUP BY key, value GROUPING SETS (key, value)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table_out@part=1
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+agg                 	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	test_table_out      	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	1                   
+	numRows             	618                 
+	rawDataSize         	6054                
+	totalSize           	6672                
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	-1                  	 
+Bucket Columns:     	[]                  	 
+Sort Columns:       	[]                  	 
+Storage Desc Params:	 	 
+	serialization.format	1                   
+PREHOOK: query: -- Test grouping sets, should be bucketed and sorted on key, value, grouping_key
+
+INSERT OVERWRITE TABLE test_table_out_2 PARTITION (part = '1') 
+SELECT key, value, GROUPING__ID, count(1) FROM src GROUP BY key, value GROUPING SETS (key, value)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table_out_2@part=1
+POSTHOOK: query: -- Test grouping sets, should be bucketed and sorted on key, value, grouping_key
+
+INSERT OVERWRITE TABLE test_table_out_2 PARTITION (part = '1') 
+SELECT key, value, GROUPING__ID, count(1) FROM src GROUP BY key, value GROUPING SETS (key, value)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table_out_2@part=1
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: DESCRIBE FORMATTED test_table_out_2 PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESCRIBE FORMATTED test_table_out_2 PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).agg EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).grouping_key SIMPLE []
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table_out_2 PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+grouping_key        	string              	None                
+agg                 	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	test_table_out_2    	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	1                   
+	numRows             	618                 
+	rawDataSize         	7290                
+	totalSize           	7908                
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	1                   	 
+Bucket Columns:     	[key, value, grouping_key]	 
+Sort Columns:       	[Order(col:key, order:1), Order(col:value, order:1), Order(col:grouping_key, order:1)]	 
+Storage Desc Params:	 	 
+	serialization.format	1                   

Added: hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out?rev=1440271&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out Wed Jan 30 04:20:39 2013
@@ -0,0 +1,158 @@
+PREHOOK: query: -- This tests that bucketing/sorting metadata is not inferred for tables with list bucketing
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+-- create a skewed table
+CREATE TABLE list_bucketing_table (key STRING, value STRING) 
+PARTITIONED BY (part STRING) 
+SKEWED BY (key) ON ("484")
+STORED AS DIRECTORIES
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: -- This tests that bucketing/sorting metadata is not inferred for tables with list bucketing
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+-- create a skewed table
+CREATE TABLE list_bucketing_table (key STRING, value STRING) 
+PARTITIONED BY (part STRING) 
+SKEWED BY (key) ON ("484")
+STORED AS DIRECTORIES
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@list_bucketing_table
+PREHOOK: query: -- Tests group by, the output should neither be bucketed nor sorted
+
+INSERT OVERWRITE TABLE list_bucketing_table PARTITION (part = '1')
+SELECT key, count(*) FROM src GROUP BY key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@list_bucketing_table@part=1
+POSTHOOK: query: -- Tests group by, the output should neither be bucketed nor sorted
+
+INSERT OVERWRITE TABLE list_bucketing_table PARTITION (part = '1')
+SELECT key, count(*) FROM src GROUP BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@list_bucketing_table@part=1
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).value EXPRESSION [(src)src.null, ]
+PREHOOK: query: DESC FORMATTED list_bucketing_table PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESC FORMATTED list_bucketing_table PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).value EXPRESSION [(src)src.null, ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	list_bucketing_table	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	2                   
+	numRows             	309                 
+	rawDataSize         	1482                
+	totalSize           	1791                
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	-1                  	 
+Bucket Columns:     	[]                  	 
+Sort Columns:       	[]                  	 
+Stored As SubDirectories:	Yes                 	 
+Skewed Columns:     	[key]               	 
+Skewed Values:      	[[484]]             	 
+#### A masked pattern was here ####
+Skewed Value to Truncated Path:	{[484]=/list_bucketing_table/part=1/key=484}	 
+Storage Desc Params:	 	 
+	serialization.format	1                   
+PREHOOK: query: -- create a table skewed on a key which doesnt exist in the data
+CREATE TABLE list_bucketing_table2 (key STRING, value STRING) 
+PARTITIONED BY (part STRING) 
+SKEWED BY (key) ON ("abc")
+STORED AS DIRECTORIES
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: -- create a table skewed on a key which doesnt exist in the data
+CREATE TABLE list_bucketing_table2 (key STRING, value STRING) 
+PARTITIONED BY (part STRING) 
+SKEWED BY (key) ON ("abc")
+STORED AS DIRECTORIES
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@list_bucketing_table2
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).value EXPRESSION [(src)src.null, ]
+PREHOOK: query: -- should not be bucketed or sorted
+INSERT OVERWRITE TABLE list_bucketing_table2 PARTITION (part = '1')
+SELECT key, count(*) FROM src GROUP BY key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@list_bucketing_table2@part=1
+POSTHOOK: query: -- should not be bucketed or sorted
+INSERT OVERWRITE TABLE list_bucketing_table2 PARTITION (part = '1')
+SELECT key, count(*) FROM src GROUP BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@list_bucketing_table2@part=1
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).value EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: list_bucketing_table2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_table2 PARTITION(part=1).value EXPRESSION [(src)src.null, ]
+PREHOOK: query: DESC FORMATTED list_bucketing_table2 PARTITION (part = '1')
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: DESC FORMATTED list_bucketing_table2 PARTITION (part = '1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_table PARTITION(part=1).value EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: list_bucketing_table2 PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_table2 PARTITION(part=1).value EXPRESSION [(src)src.null, ]
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+	 	 
+# Partition Information	 	 
+# col_name            	data_type           	comment             
+	 	 
+part                	string              	None                
+	 	 
+# Detailed Partition Information	 	 
+Partition Value:    	[1]                 	 
+Database:           	default             	 
+Table:              	list_bucketing_table2	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+#### A masked pattern was here ####
+Partition Parameters:	 	 
+	numFiles            	1                   
+	numRows             	309                 
+	rawDataSize         	1482                
+	totalSize           	136                 
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	-1                  	 
+Bucket Columns:     	[]                  	 
+Sort Columns:       	[]                  	 
+Stored As SubDirectories:	Yes                 	 
+Skewed Columns:     	[key]               	 
+Skewed Values:      	[[abc]]             	 
+Storage Desc Params:	 	 
+	serialization.format	1                   



Mime
View raw message