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 2011/12/21 18:14:28 UTC
svn commit: r1221812 [3/4] - in /hive/trunk/ql/src:
java/org/apache/hadoop/hive/ql/optimizer/
java/org/apache/hadoop/hive/ql/optimizer/unionproc/
test/queries/clientpositive/ test/results/clientpositive/
Modified: hive/trunk/ql/src/test/results/clientpositive/union20.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/union20.q.out?rev=1221812&r1=1221811&r2=1221812&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/union20.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/union20.q.out Wed Dec 21 17:14:27 2011
@@ -29,10 +29,7 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-3, Stage-5
- Stage-3 is a root stage
- Stage-4 is a root stage
- Stage-5 depends on stages: Stage-4, Stage-6
+ Stage-2 depends on stages: Stage-1, Stage-6
Stage-6 is a root stage
Stage-0 is a root stage
@@ -80,86 +77,43 @@ STAGE PLANS:
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: 0
- value expressions:
- expr: _col0
- type: string
- expr: _col1
- type: string
#### A masked pattern was here ####
- Union
- 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: string
+ TableScan
+ Union
+ 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: string
#### A masked pattern was here ####
- Union
- 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: string
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1}
- 1 {VALUE._col0} {VALUE._col1}
- handleSkewJoin: false
- outputColumnNames: _col0, _col1, _col2, _col3
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: string
- expr: _col2
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col0, _col1, _col2, _col3
- 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:
- null-subquery2:unionsrc2-subquery2:s4
TableScan
- alias: s4
+ Union
+ 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: string
+ null-subquery2:unionsrc1-subquery2:s2
+ TableScan
+ alias: s2
Filter Operator
predicate:
expr: (key < 10)
@@ -171,19 +125,24 @@ STAGE PLANS:
expr: value
type: string
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-4
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery2:unionsrc1-subquery2:s2
+ Union
+ 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: string
+ null-subquery2:unionsrc2-subquery2:s4
TableScan
- alias: s2
+ alias: s4
Filter Operator
predicate:
expr: (key < 10)
@@ -195,32 +154,47 @@ STAGE PLANS:
expr: value
type: string
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-5
- Map Reduce
- Alias -> Map Operator Tree:
-#### A masked pattern was here ####
- Union
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-#### A masked pattern was here ####
- Union
+ Union
+ 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: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2, _col3
File Output Operator
compressed: false
GlobalTableId: 0
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
Stage: Stage-6
Map Reduce
Modified: hive/trunk/ql/src/test/results/clientpositive/union22.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/union22.q.out?rev=1221812&r1=1221811&r2=1221812&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/union22.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/union22.q.out Wed Dec 21 17:14:27 2011
@@ -84,7 +84,8 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-7 is a root stage
Stage-1 depends on stages: Stage-7
- Stage-3 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
Stage-0 depends on stages: Stage-3
Stage-4 depends on stages: Stage-0
@@ -222,7 +223,7 @@ STAGE PLANS:
name: default.dst_union22
name: default.dst_union22
- Stage: Stage-3
+ Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
#### A masked pattern was here ####
@@ -248,49 +249,91 @@ STAGE PLANS:
expr: _col11
type: string
outputColumnNames: _col0, _col1, _col2, _col3
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: string
- expr: _col2
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col0, _col1, _col2, _col3
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2/
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns k1,k2,k3,k4
- columns.types string:string:string:string
-#### A masked pattern was here ####
- name default.dst_union22
- numFiles 1
- numPartitions 1
- numRows 500
- partition_columns ds
- rawDataSize 11124
- serialization.ddl struct dst_union22 { string k1, string k2, string k3, string k4}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 11624
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dst_union22
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string,string,string,string
+ escape.delim \
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10002
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col10,_col11
+ columns.types string,string,string,string
+ escape.delim \
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col10,_col11
+ columns.types string,string,string,string
+ escape.delim \
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ TableScan
+ GatherStats: false
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2/
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns k1,k2,k3,k4
+ columns.types string:string:string:string
+#### A masked pattern was here ####
+ name default.dst_union22
+ numFiles 1
+ numPartitions 1
+ numRows 500
+ partition_columns ds
+ rawDataSize 11124
+ serialization.ddl struct dst_union22 { string k1, string k2, string k3, string k4}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 11624
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dst_union22
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
null-subquery1:subq-subquery1:dst_union22_delta
TableScan
alias: dst_union22_delta
@@ -360,18 +403,18 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: -mr-10002
+ base file name: -mr-10003
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
- columns _col0,_col1,_col10,_col11
+ columns _col0,_col1,_col2,_col3
columns.types string,string,string,string
escape.delim \
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
- columns _col0,_col1,_col10,_col11
+ columns _col0,_col1,_col2,_col3
columns.types string,string,string,string
escape.delim \
#### A masked pattern was here ####
Modified: hive/trunk/ql/src/test/results/clientpositive/union24.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/union24.q.out?rev=1221812&r1=1221811&r2=1221812&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/union24.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/union24.q.out Wed Dec 21 17:14:27 2011
@@ -54,20 +54,17 @@ ABSTRACT SYNTAX TREE:
(TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_UNION (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src3))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src4))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src5))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1) count
)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10)) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))) s)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) count))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL s) key)))))
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-3, Stage-4, Stage-5
Stage-3 is a root stage
- Stage-4 is a root stage
- Stage-5 is a root stage
+ Stage-2 depends on stages: Stage-3
Stage-0 is a root stage
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Map Reduce
Alias -> Map Operator Tree:
- null-subquery1-subquery2:s-subquery1-subquery2:src4
+ null-subquery2:s-subquery2:src5
TableScan
- alias: src4
+ alias: src5
GatherStats: false
Filter Operator
isSamplingPred: false
@@ -78,31 +75,35 @@ STAGE PLANS:
expressions:
expr: key
type: string
- expr: count
- type: bigint
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ 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
Needs Tagging: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src4
+ base file name: src5
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -110,12 +111,12 @@ STAGE PLANS:
columns key,count
columns.types string:bigint
#### A masked pattern was here ####
- name default.src4
+ name default.src5
numFiles 1
numPartitions 0
numRows 309
rawDataSize 1482
- serialization.ddl struct src4 { string key, i64 count}
+ serialization.ddl struct src5 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
@@ -129,103 +130,182 @@ STAGE PLANS:
columns key,count
columns.types string:bigint
#### A masked pattern was here ####
- name default.src4
+ name default.src5
numFiles 1
numPartitions 0
numRows 309
rawDataSize 1482
- serialization.ddl struct src4 { string key, i64 count}
+ serialization.ddl struct src5 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src4
- name: default.src4
+ name: default.src5
+ name: default.src5
+ 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
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string,bigint
+ escape.delim \
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
+ TableScan
+ GatherStats: false
+ Union
+ Select Operator
+ expressions:
expr: _col0
type: string
expr: _col1
type: bigint
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
- expr: _col0
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ null-subquery1-subquery1-subquery1:s-subquery1-subquery1-subquery1:src2
+ TableScan
+ alias: src2
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (key < 10)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
type: string
- expr: _col1
+ expr: count
type: bigint
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
- expr: _col0
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ null-subquery1-subquery1-subquery2:s-subquery1-subquery1-subquery2:src3
+ TableScan
+ alias: src3
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (key < 10)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
type: string
- expr: _col1
+ expr: count
type: bigint
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
- expr: _col0
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ null-subquery1-subquery2:s-subquery1-subquery2:src4
+ TableScan
+ alias: src4
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (key < 10)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
type: string
- expr: _col1
+ expr: count
type: bigint
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
Needs Tagging: false
Path -> Alias:
#### A masked pattern was here ####
@@ -248,117 +328,7 @@ STAGE PLANS:
escape.delim \
#### A masked pattern was here ####
Partition
- base file name: -mr-10003
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-#### A masked pattern was here ####
- Partition
- base file name: -mr-10004
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-#### A masked pattern was here ####
- Partition
- base file name: -mr-10005
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- Reduce Operator Tree:
- Extract
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1
- columns.types string:bigint
- escape.delim \
- serialization.format 1
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-3
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery2:s-subquery2:src5
- TableScan
- alias: src5
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate:
- expr: (key < 10)
- type: boolean
- Select Operator
- expressions:
- expr: key
- type: string
- outputColumnNames: key
- Group By Operator
- aggregations:
- expr: count(1)
- 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
- Needs Tagging: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src5
+ base file name: src2
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -366,12 +336,12 @@ STAGE PLANS:
columns key,count
columns.types string:bigint
#### A masked pattern was here ####
- name default.src5
+ name default.src2
numFiles 1
numPartitions 0
numRows 309
rawDataSize 1482
- serialization.ddl struct src5 { string key, i64 count}
+ serialization.ddl struct src2 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
@@ -379,96 +349,25 @@ STAGE PLANS:
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,count
- columns.types string:bigint
-#### A masked pattern was here ####
- name default.src5
- numFiles 1
- numPartitions 0
- numRows 309
- rawDataSize 1482
- serialization.ddl struct src5 { string key, i64 count}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 1791
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src5
- name: default.src5
- 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
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,count
+ columns.types string:bigint
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-4
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery1-subquery1-subquery2:s-subquery1-subquery1-subquery2:src3
- TableScan
- alias: src3
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate:
- expr: (key < 10)
- type: boolean
- Select Operator
- expressions:
- expr: key
- type: string
- expr: count
- type: bigint
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Needs Tagging: false
- Path -> Alias:
+ name default.src2
+ numFiles 1
+ numPartitions 0
+ numRows 309
+ rawDataSize 1482
+ serialization.ddl struct src2 { string key, i64 count}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 1791
#### A masked pattern was here ####
- Path -> Partition:
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src2
+ name: default.src2
#### A masked pattern was here ####
Partition
base file name: src3
@@ -511,48 +410,9 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.src3
name: default.src3
-
- Stage: Stage-5
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery1-subquery1-subquery1:s-subquery1-subquery1-subquery1:src2
- TableScan
- alias: src2
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate:
- expr: (key < 10)
- type: boolean
- Select Operator
- expressions:
- expr: key
- type: string
- expr: count
- type: bigint
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Needs Tagging: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src2
+ base file name: src4
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -560,12 +420,12 @@ STAGE PLANS:
columns key,count
columns.types string:bigint
#### A masked pattern was here ####
- name default.src2
+ name default.src4
numFiles 1
numPartitions 0
numRows 309
rawDataSize 1482
- serialization.ddl struct src2 { string key, i64 count}
+ serialization.ddl struct src4 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
@@ -579,19 +439,38 @@ STAGE PLANS:
columns key,count
columns.types string:bigint
#### A masked pattern was here ####
- name default.src2
+ name default.src4
numFiles 1
numPartitions 0
numRows 309
rawDataSize 1482
- serialization.ddl struct src2 { string key, i64 count}
+ serialization.ddl struct src4 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src2
- name: default.src2
+ name: default.src4
+ name: default.src4
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:bigint
+ escape.delim \
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -643,9 +522,9 @@ POSTHOOK: Input: default@src5
4 1
4 1
5 3
-5 3
5 1
5 3
+5 3
8 1
8 1
8 1
@@ -679,9 +558,7 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-4, Stage-5
- Stage-4 is a root stage
- Stage-5 is a root stage
+ Stage-2 depends on stages: Stage-1
Stage-0 is a root stage
STAGE PLANS:
@@ -854,140 +731,27 @@ STAGE PLANS:
Map Reduce
Alias -> Map Operator Tree:
#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
+ TableScan
+ GatherStats: false
+ Union
+ Select Operator
+ expressions:
expr: _col0
type: string
expr: _col1
type: bigint
- Needs Tagging: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: -mr-10002
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-#### A masked pattern was here ####
- Partition
- base file name: -mr-10003
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-#### A masked pattern was here ####
- Partition
- base file name: -mr-10004
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- Reduce Operator Tree:
- Extract
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1
- columns.types string:bigint
- escape.delim \
- serialization.format 1
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-4
- Map Reduce
- Alias -> Map Operator Tree:
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
null-subquery1-subquery1:s-subquery1-subquery1:src2
TableScan
alias: src2
@@ -1004,27 +768,82 @@ STAGE PLANS:
expr: count
type: bigint
outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ null-subquery1-subquery2:s-subquery1-subquery2:src3
+ TableScan
+ alias: src3
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (key < 10)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: count
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
Needs Tagging: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
+ base file name: -mr-10002
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string,bigint
+ escape.delim \
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string,bigint
+ escape.delim \
+#### A masked pattern was here ####
+ Partition
base file name: src2
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1065,45 +884,6 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.src2
name: default.src2
-
- Stage: Stage-5
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery1-subquery2:s-subquery1-subquery2:src3
- TableScan
- alias: src3
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate:
- expr: (key < 10)
- type: boolean
- Select Operator
- expressions:
- expr: key
- type: string
- expr: count
- type: bigint
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Needs Tagging: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: src3
@@ -1146,6 +926,25 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.src3
name: default.src3
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:bigint
+ escape.delim \
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -1224,9 +1023,7 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-2, Stage-5, Stage-6
- Stage-5 is a root stage
- Stage-6 is a root stage
+ Stage-3 depends on stages: Stage-2
Stage-0 is a root stage
STAGE PLANS:
@@ -1472,65 +1269,97 @@ STAGE PLANS:
Map Reduce
Alias -> Map Operator Tree:
#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
+ TableScan
+ GatherStats: false
+ Union
+ Select Operator
+ expressions:
expr: _col0
type: string
expr: _col1
type: bigint
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
- expr: _col0
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ null-subquery1-subquery1:s-subquery1-subquery1:src2
+ TableScan
+ alias: src2
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (key < 10)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
type: string
- expr: _col1
+ expr: count
type: bigint
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: bigint
- outputColumnNames: _col0, _col1
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- tag: -1
- value expressions:
- expr: _col0
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ null-subquery1-subquery2:s-subquery1-subquery2:src3
+ TableScan
+ alias: src3
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (key < 10)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
type: string
- expr: _col1
+ expr: count
type: bigint
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
Needs Tagging: false
Path -> Alias:
#### A masked pattern was here ####
@@ -1553,96 +1382,6 @@ STAGE PLANS:
escape.delim \
#### A masked pattern was here ####
Partition
- base file name: -mr-10004
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-#### A masked pattern was here ####
- Partition
- base file name: -mr-10005
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
-
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- Reduce Operator Tree:
- Extract
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1
- columns.types string:bigint
- escape.delim \
- serialization.format 1
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-5
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery1-subquery1:s-subquery1-subquery1:src2
- TableScan
- alias: src2
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate:
- expr: (key < 10)
- type: boolean
- Select Operator
- expressions:
- expr: key
- type: string
- expr: count
- type: bigint
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Needs Tagging: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
base file name: src2
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1683,45 +1422,6 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.src2
name: default.src2
-
- Stage: Stage-6
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery1-subquery2:s-subquery1-subquery2:src3
- TableScan
- alias: src3
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate:
- expr: (key < 10)
- type: boolean
- Select Operator
- expressions:
- expr: key
- type: string
- expr: count
- type: bigint
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1
- columns.types string,bigint
- escape.delim \
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Needs Tagging: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
#### A masked pattern was here ####
Partition
base file name: src3
@@ -1764,6 +1464,25 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.src3
name: default.src3
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:bigint
+ escape.delim \
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -1807,9 +1526,9 @@ POSTHOOK: Input: default@src5
4 1
4 1
4 1
-5 3
5 1
5 3
+5 3
8 1
8 1
8 1
Modified: hive/trunk/ql/src/test/results/clientpositive/union25.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/union25.q.out?rev=1221812&r1=1221811&r2=1221812&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/union25.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/union25.q.out Wed Dec 21 17:14:27 2011
@@ -58,13 +58,10 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-5
- Stage-3 depends on stages: Stage-2, Stage-6
- Stage-0 depends on stages: Stage-3
- Stage-7 depends on stages: Stage-0
- Stage-4 depends on stages: Stage-7
- Stage-5 is a root stage
- Stage-6 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-6 depends on stages: Stage-0
+ Stage-3 depends on stages: Stage-6
STAGE PLANS:
Stage: Stage-1
@@ -80,62 +77,60 @@ STAGE PLANS:
expr: value
type: string
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-2
- Map Reduce
- Alias -> Map Operator Tree:
-#### A masked pattern was here ####
- Union
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ null-subquery2:a-subquery2:master_table-subquery2:t-subquery2:b
+ TableScan
+ alias: b
Select Operator
expressions:
- expr: _col0
+ expr: key
type: string
- outputColumnNames: _col0
- Group By Operator
- bucketGroup: false
- keys:
- expr: _col0
- type: string
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- Map-reduce partition columns:
- expr: _col0
- type: string
- tag: -1
-#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
+ expr: value
type: string
- outputColumnNames: _col0
- Group By Operator
- bucketGroup: false
- keys:
- expr: _col0
- type: string
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- key expressions:
- expr: _col0
- type: string
- sort order: +
- Map-reduce partition columns:
- expr: _col0
- type: string
- tag: -1
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
Reduce Operator Tree:
Group By Operator
bucketGroup: false
@@ -163,81 +158,91 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- Stage: Stage-3
+ Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
#### A masked pattern was here ####
- Union
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col1
- type: string
- outputColumnNames: _col0, _col1
- Group By Operator
- aggregations:
- expr: count(1)
- bucketGroup: false
- keys:
+ TableScan
+ Union
+ Select Operator
+ expressions:
expr: _col0
type: string
expr: _col1
type: string
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Reduce Output Operator
- key expressions:
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
expr: _col0
type: string
expr: _col1
type: string
- sort order: ++
- Map-reduce partition columns:
- expr: _col0
- type: string
- expr: _col1
- type: string
- tag: -1
- value expressions:
- expr: _col2
- type: bigint
-#### A masked pattern was here ####
- Union
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ null-subquery1:a-subquery1:a
+ TableScan
+ alias: a
Select Operator
expressions:
- expr: _col0
+ expr: key
type: string
- expr: _col1
+ expr: value
type: string
outputColumnNames: _col0, _col1
- Group By Operator
- aggregations:
- expr: count(1)
- bucketGroup: false
- keys:
- expr: _col0
- type: string
- expr: _col1
- type: string
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Reduce Output Operator
- key expressions:
+ Union
+ Select Operator
+ expressions:
expr: _col0
type: string
expr: _col1
type: string
- sort order: ++
- Map-reduce partition columns:
- expr: _col0
- type: string
- expr: _col1
- type: string
- tag: -1
- value expressions:
- expr: _col2
- type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
Reduce Operator Tree:
Group By Operator
aggregations:
@@ -273,7 +278,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-7
+ Stage: Stage-6
Create Table Operator:
Create Table
columns: counts bigint, key string, value string
@@ -284,47 +289,7 @@ STAGE PLANS:
name: tmp_unionall
isExternal: false
- Stage: Stage-4
+ Stage: Stage-3
Stats-Aggr Operator
- Stage: Stage-5
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery2:a-subquery2:master_table-subquery2:t-subquery2:b
- TableScan
- alias: b
- Select Operator
- expressions:
- expr: key
- type: string
- expr: value
- type: string
- 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-6
- Map Reduce
- Alias -> Map Operator Tree:
- null-subquery1:a-subquery1:a
- TableScan
- alias: a
- Select Operator
- expressions:
- expr: key
- type: string
- expr: value
- type: string
- 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
-