You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by na...@apache.org on 2010/10/27 21:00:05 UTC
svn commit: r1028072 [3/7] - in /hive/trunk: ./ data/files/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/parse/
ql/src/java/org/apache/hadoop/hive/ql/plan/
ql/src/test/queries/clientnegative/ ql/src/test/queries/cli...
Modified: hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin4.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin4.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin4.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin4.q.out Wed Oct 27 19:00:02 2010
@@ -104,9 +104,7 @@ STAGE PLANS:
TableScan
alias: b
GatherStats: false
- Common Join Operator
- condition map:
- Inner Join 0 to 1
+ JDBM Sink Operator
condition expressions:
0 {key} {value}
1 {value}
@@ -114,16 +112,15 @@ STAGE PLANS:
keys:
0 [Column[key]]
1 [Column[key]]
- outputColumnNames: _col0, _col1, _col5
Position of Big Table: 0
Bucket Mapjoin Context:
Alias Bucket Base File Name Mapping:
b {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt]}
Alias Bucket File Name Mapping:
- b {pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
+ b {pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
Alias Bucket Output File Name Mapping:
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
Stage: Stage-1
Map Reduce
@@ -132,7 +129,7 @@ STAGE PLANS:
TableScan
alias: a
GatherStats: false
- Common Join Operator
+ Map Join Operator
condition map:
Inner Join 0 to 1
condition expressions:
@@ -165,9 +162,9 @@ STAGE PLANS:
File Output Operator
compressed: false
GlobalTableId: 1
- directory: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10002
+ directory: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10002
NumFilesPerFileSink: 1
- Stats Publishing Key Prefix: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10000/
+ Stats Publishing Key Prefix: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10000/
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -177,12 +174,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175837
+ transient_lastDdlTime 1288205575
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -192,9 +189,9 @@ STAGE PLANS:
Map Reduce Local Work
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin [a]
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin [a]
Path -> Partition:
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin
Partition
base file name: srcbucket_mapjoin
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -206,12 +203,12 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin
name srcbucket_mapjoin
serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175830
+ transient_lastDdlTime 1288205572
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -223,12 +220,12 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin
name srcbucket_mapjoin
serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175830
+ transient_lastDdlTime 1288205572
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: srcbucket_mapjoin
name: srcbucket_mapjoin
@@ -240,14 +237,14 @@ STAGE PLANS:
Move Operator
files:
hdfs directory: true
- source: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10002
- destination: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10000
+ source: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10002
+ destination: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10000
Stage: Stage-0
Move Operator
tables:
replace: true
- source: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10000
+ source: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10000
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -257,28 +254,28 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175837
+ transient_lastDdlTime 1288205575
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
- tmp directory: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10001
+ tmp directory: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10001
Stage: Stage-2
Stats-Aggr Operator
- Stats Aggregation Key Prefix: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10000/
+ Stats Aggregation Key Prefix: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10000/
Stage: Stage-3
Map Reduce
Alias -> Map Operator Tree:
- pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10002
+ pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10002
File Output Operator
compressed: false
GlobalTableId: 0
- directory: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10000
+ directory: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10000
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -289,12 +286,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175837
+ transient_lastDdlTime 1288205575
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -302,9 +299,9 @@ STAGE PLANS:
MultiFileSpray: false
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10002 [pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10002]
+ pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10002 [pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10002]
Path -> Partition:
- pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-50-37_713_8397106184600203842/-ext-10002
+ pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-52-55_191_6284354312574445049/-ext-10002
Partition
base file name: -ext-10002
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -315,12 +312,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175837
+ transient_lastDdlTime 1288205575
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -331,12 +328,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175837
+ transient_lastDdlTime 1288205575
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
name: bucketmapjoin_tmp_result
@@ -362,11 +359,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-50-50_080_3250358574001886106/-mr-10000
+PREHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-02_738_4577457943531711045/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-50-50_080_3250358574001886106/-mr-10000
+POSTHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-02_738_4577457943531711045/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
@@ -413,11 +410,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-12_750_5190209184978381690/-mr-10000
+PREHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-16_429_5837890045100564683/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-12_750_5190209184978381690/-mr-10000
+POSTHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-16_429_5837890045100564683/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
@@ -456,14 +453,14 @@ on a.key = b.key
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_hash_result_1
PREHOOK: Input: default@bucketmapjoin_hash_result_2
-PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-22_308_4772430048114309901/-mr-10000
+PREHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-24_119_5713666769406989600/-mr-10000
POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
on a.key = b.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_hash_result_1
POSTHOOK: Input: default@bucketmapjoin_hash_result_2
-POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-22_308_4772430048114309901/-mr-10000
+POSTHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-24_119_5713666769406989600/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
@@ -525,9 +522,7 @@ STAGE PLANS:
TableScan
alias: a
GatherStats: false
- Common Join Operator
- condition map:
- Inner Join 0 to 1
+ JDBM Sink Operator
condition expressions:
0 {key} {value}
1 {value}
@@ -535,16 +530,15 @@ STAGE PLANS:
keys:
0 [Column[key]]
1 [Column[key]]
- outputColumnNames: _col0, _col1, _col5
Position of Big Table: 1
Bucket Mapjoin Context:
Alias Bucket Base File Name Mapping:
a {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt]}
Alias Bucket File Name Mapping:
- a {pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
+ a {pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
Alias Bucket Output File Name Mapping:
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
Stage: Stage-1
Map Reduce
@@ -553,7 +547,7 @@ STAGE PLANS:
TableScan
alias: b
GatherStats: false
- Common Join Operator
+ Map Join Operator
condition map:
Inner Join 0 to 1
condition expressions:
@@ -586,9 +580,9 @@ STAGE PLANS:
File Output Operator
compressed: false
GlobalTableId: 1
- directory: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10002
+ directory: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10002
NumFilesPerFileSink: 1
- Stats Publishing Key Prefix: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10000/
+ Stats Publishing Key Prefix: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10000/
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -598,7 +592,7 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
numFiles 1
numPartitions 0
@@ -607,7 +601,7 @@ STAGE PLANS:
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 8983
- transient_lastDdlTime 1287175872
+ transient_lastDdlTime 1288205596
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -617,9 +611,9 @@ STAGE PLANS:
Map Reduce Local Work
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin [b]
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin [b]
Path -> Partition:
- pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin
+ pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin
Partition
base file name: srcbucket_mapjoin
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -631,12 +625,12 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin
name srcbucket_mapjoin
serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175830
+ transient_lastDdlTime 1288205572
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -648,12 +642,12 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/srcbucket_mapjoin
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/srcbucket_mapjoin
name srcbucket_mapjoin
serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1287175830
+ transient_lastDdlTime 1288205572
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: srcbucket_mapjoin
name: srcbucket_mapjoin
@@ -665,14 +659,14 @@ STAGE PLANS:
Move Operator
files:
hdfs directory: true
- source: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10002
- destination: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10000
+ source: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10002
+ destination: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10000
Stage: Stage-0
Move Operator
tables:
replace: true
- source: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10000
+ source: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10000
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -682,7 +676,7 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
numFiles 1
numPartitions 0
@@ -691,23 +685,23 @@ STAGE PLANS:
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 8983
- transient_lastDdlTime 1287175872
+ transient_lastDdlTime 1288205596
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
- tmp directory: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10001
+ tmp directory: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10001
Stage: Stage-2
Stats-Aggr Operator
- Stats Aggregation Key Prefix: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10000/
+ Stats Aggregation Key Prefix: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10000/
Stage: Stage-3
Map Reduce
Alias -> Map Operator Tree:
- pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10002
+ pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10002
File Output Operator
compressed: false
GlobalTableId: 0
- directory: pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10000
+ directory: pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10000
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -718,7 +712,7 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
numFiles 1
numPartitions 0
@@ -727,7 +721,7 @@ STAGE PLANS:
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 8983
- transient_lastDdlTime 1287175872
+ transient_lastDdlTime 1288205596
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -735,9 +729,9 @@ STAGE PLANS:
MultiFileSpray: false
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10002 [pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10002]
+ pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10002 [pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10002]
Path -> Partition:
- pfile:/data/users/liyintang/trunk_os/build/ql/scratchdir/hive_2010-10-15_13-51-26_294_4777526524357803096/-ext-10002
+ pfile:/data/users/njain/hive-commit1/build/ql/scratchdir/hive_2010-10-27_11-53-27_274_740197042204524306/-ext-10002
Partition
base file name: -ext-10002
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -748,7 +742,7 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
numFiles 1
numPartitions 0
@@ -757,7 +751,7 @@ STAGE PLANS:
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 8983
- transient_lastDdlTime 1287175872
+ transient_lastDdlTime 1288205596
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -768,7 +762,7 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/liyintang/trunk_os/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/data/users/njain/hive-commit1/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
numFiles 1
numPartitions 0
@@ -777,7 +771,7 @@ STAGE PLANS:
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 8983
- transient_lastDdlTime 1287175872
+ transient_lastDdlTime 1288205596
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
name: bucketmapjoin_tmp_result
@@ -815,11 +809,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-38_519_5227176789157682406/-mr-10000
+PREHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-34_796_7433622090937468625/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-38_519_5227176789157682406/-mr-10000
+POSTHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-34_796_7433622090937468625/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
@@ -902,11 +896,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-59_233_5568038317944335995/-mr-10000
+PREHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-48_705_2477192820764361821/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-51-59_233_5568038317944335995/-mr-10000
+POSTHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-48_705_2477192820764361821/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
@@ -969,14 +963,14 @@ on a.key = b.key
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_hash_result_1
PREHOOK: Input: default@bucketmapjoin_hash_result_2
-PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-52-08_602_2192616005048999053/-mr-10000
+PREHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-55_192_5237681680689076654/-mr-10000
POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
on a.key = b.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_hash_result_1
POSTHOOK: Input: default@bucketmapjoin_hash_result_2
-POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-15_13-52-08_602_2192616005048999053/-mr-10000
+POSTHOOK: Output: file:/tmp/njain/hive_2010-10-27_11-53-55_192_5237681680689076654/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
Added: hive/trunk/ql/src/test/results/clientpositive/count.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/count.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/count.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/count.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,577 @@
+PREHOOK: query: create table abcd (a int, b int, c int, d int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table abcd (a int, b int, c int, d int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@abcd
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/in4.txt' INTO TABLE abcd
+PREHOOK: type: LOAD
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/in4.txt' INTO TABLE abcd
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@abcd
+PREHOOK: query: select * from abcd
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_523_248548306762990690/-mr-10000
+POSTHOOK: query: select * from abcd
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_523_248548306762990690/-mr-10000
+NULL 35 23 6
+10 1000 50 1
+100 100 10 3
+12 NULL 80 2
+10 100 NULL 5
+10 100 45 4
+12 100 75 7
+PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF abcd)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL a)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_TABLE_OR_COL d)))) (TOK_GROUPBY (TOK_TABLE_OR_COL a))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ abcd
+ TableScan
+ alias: abcd
+ Select Operator
+ expressions:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ expr: d
+ type: int
+ outputColumnNames: a, b, c, d
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT b)
+ expr: count(DISTINCT c)
+ expr: sum(d)
+ bucketGroup: false
+ keys:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: int
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col3
+ type: bigint
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT KEY._col1:0._col0)
+ expr: count(DISTINCT KEY._col1:1._col0)
+ expr: sum(VALUE._col2)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_925_5142539455043997266/-mr-10000
+POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-12_925_5142539455043997266/-mr-10000
+NULL 1 1 6
+10 2 2 10
+12 1 2 9
+100 1 1 3
+PREHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF abcd)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1)) (TOK_SELEXPR (TOK_FUNCTIONSTAR count)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL a))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count
(TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ abcd
+ TableScan
+ alias: abcd
+ Select Operator
+ expressions:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ expr: d
+ type: int
+ outputColumnNames: a, b, c, d
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ expr: count()
+ expr: count(a)
+ expr: count(b)
+ expr: count(c)
+ expr: count(d)
+ expr: count(DISTINCT a)
+ expr: count(DISTINCT b)
+ expr: count(DISTINCT c)
+ expr: count(DISTINCT d)
+ expr: count(DISTINCT a, b)
+ expr: count(DISTINCT b, c)
+ expr: count(DISTINCT c, d)
+ expr: count(DISTINCT a, d)
+ expr: count(DISTINCT a, c)
+ expr: count(DISTINCT b, d)
+ expr: count(DISTINCT a, b, c)
+ expr: count(DISTINCT b, c, d)
+ expr: count(DISTINCT a, c, d)
+ expr: count(DISTINCT a, b, d)
+ expr: count(DISTINCT a, b, c, d)
+ bucketGroup: false
+ keys:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ expr: d
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: int
+ expr: _col3
+ type: int
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ expr: _col6
+ type: bigint
+ expr: _col7
+ type: bigint
+ expr: _col8
+ type: bigint
+ expr: _col9
+ type: bigint
+ expr: _col10
+ type: bigint
+ expr: _col11
+ type: bigint
+ expr: _col12
+ type: bigint
+ expr: _col13
+ type: bigint
+ expr: _col14
+ type: bigint
+ expr: _col15
+ type: bigint
+ expr: _col16
+ type: bigint
+ expr: _col17
+ type: bigint
+ expr: _col18
+ type: bigint
+ expr: _col19
+ type: bigint
+ expr: _col20
+ type: bigint
+ expr: _col21
+ type: bigint
+ expr: _col22
+ type: bigint
+ expr: _col23
+ type: bigint
+ expr: _col24
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ expr: count(VALUE._col1)
+ expr: count(VALUE._col2)
+ expr: count(VALUE._col3)
+ expr: count(VALUE._col4)
+ expr: count(VALUE._col5)
+ expr: count(DISTINCT KEY._col0:0._col0)
+ expr: count(DISTINCT KEY._col0:1._col0)
+ expr: count(DISTINCT KEY._col0:2._col0)
+ expr: count(DISTINCT KEY._col0:3._col0)
+ expr: count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1)
+ expr: count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1)
+ expr: count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1)
+ expr: count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1)
+ expr: count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1)
+ expr: count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1)
+ expr: count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2)
+ expr: count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2)
+ expr: count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2)
+ expr: count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2)
+ expr: count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ expr: _col6
+ type: bigint
+ expr: _col7
+ type: bigint
+ expr: _col8
+ type: bigint
+ expr: _col9
+ type: bigint
+ expr: _col10
+ type: bigint
+ expr: _col11
+ type: bigint
+ expr: _col12
+ type: bigint
+ expr: _col13
+ type: bigint
+ expr: _col14
+ type: bigint
+ expr: _col15
+ type: bigint
+ expr: _col16
+ type: bigint
+ expr: _col17
+ type: bigint
+ expr: _col18
+ type: bigint
+ expr: _col19
+ type: bigint
+ expr: _col20
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-15_550_8269692453214848200/-mr-10000
+POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-15_550_8269692453214848200/-mr-10000
+7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4
+PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF abcd)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL a)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_TABLE_OR_COL d)))) (TOK_GROUPBY (TOK_TABLE_OR_COL a))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ abcd
+ TableScan
+ alias: abcd
+ Select Operator
+ expressions:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ expr: d
+ type: int
+ outputColumnNames: a, b, c, d
+ Reduce Output Operator
+ key expressions:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ sort order: +++
+ Map-reduce partition columns:
+ expr: a
+ type: int
+ tag: -1
+ value expressions:
+ expr: d
+ type: int
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT KEY._col1:0._col0)
+ expr: count(DISTINCT KEY._col1:1._col0)
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-18_476_7776659377634244729/-mr-10000
+POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-18_476_7776659377634244729/-mr-10000
+NULL 1 1 6
+10 2 2 10
+12 1 2 9
+100 1 1 3
+PREHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF abcd)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1)) (TOK_SELEXPR (TOK_FUNCTIONSTAR count)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL a))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count
(TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL d))) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL a) (TOK_TABLE_OR_COL b) (TOK_TABLE_OR_COL c) (TOK_TABLE_OR_COL d))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ abcd
+ TableScan
+ alias: abcd
+ Select Operator
+ expressions:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ expr: d
+ type: int
+ outputColumnNames: a, b, c, d
+ Reduce Output Operator
+ key expressions:
+ expr: a
+ type: int
+ expr: b
+ type: int
+ expr: c
+ type: int
+ expr: d
+ type: int
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: 1
+ type: int
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ expr: count()
+ expr: count(KEY._col0:14._col0)
+ expr: count(KEY._col0:14._col1)
+ expr: count(KEY._col0:14._col2)
+ expr: count(KEY._col0:14._col3)
+ expr: count(DISTINCT KEY._col0:0._col0)
+ expr: count(DISTINCT KEY._col0:1._col0)
+ expr: count(DISTINCT KEY._col0:2._col0)
+ expr: count(DISTINCT KEY._col0:3._col0)
+ expr: count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1)
+ expr: count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1)
+ expr: count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1)
+ expr: count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1)
+ expr: count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1)
+ expr: count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1)
+ expr: count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2)
+ expr: count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2)
+ expr: count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2)
+ expr: count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2)
+ expr: count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3)
+ bucketGroup: false
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ expr: _col6
+ type: bigint
+ expr: _col7
+ type: bigint
+ expr: _col8
+ type: bigint
+ expr: _col9
+ type: bigint
+ expr: _col10
+ type: bigint
+ expr: _col11
+ type: bigint
+ expr: _col12
+ type: bigint
+ expr: _col13
+ type: bigint
+ expr: _col14
+ type: bigint
+ expr: _col15
+ type: bigint
+ expr: _col16
+ type: bigint
+ expr: _col17
+ type: bigint
+ expr: _col18
+ type: bigint
+ expr: _col19
+ type: bigint
+ expr: _col20
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+PREHOOK: type: QUERY
+PREHOOK: Input: default@abcd
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-20_818_3596074897102517680/-mr-10000
+POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@abcd
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-19_03-08-20_818_3596074897102517680/-mr-10000
+7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4
Modified: hive/trunk/ql/src/test/results/clientpositive/groupby2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby2.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby2.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby2.q.out Wed Oct 27 19:00:02 2010
@@ -50,8 +50,8 @@ STAGE PLANS:
Reduce Operator Tree:
Group By Operator
aggregations:
- expr: count(DISTINCT KEY._col1)
- expr: sum(KEY._col1)
+ expr: count(DISTINCT KEY._col1:0._col0)
+ expr: sum(KEY._col1:0._col0)
bucketGroup: false
keys:
expr: KEY._col0
Modified: hive/trunk/ql/src/test/results/clientpositive/groupby2_map.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby2_map.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby2_map.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby2_map.q.out Wed Oct 27 19:00:02 2010
@@ -64,7 +64,7 @@ STAGE PLANS:
Reduce Operator Tree:
Group By Operator
aggregations:
- expr: count(DISTINCT KEY._col1)
+ expr: count(DISTINCT KEY._col1:0._col0)
expr: sum(VALUE._col1)
bucketGroup: false
keys:
Added: hive/trunk/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,169 @@
+PREHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5)))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL src) value)))) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT substr(value, 5))
+ expr: sum(substr(value, 5))
+ expr: sum(DISTINCT substr(value, 5))
+ expr: count(value)
+ bucketGroup: false
+ keys:
+ expr: substr(key, 1, 1)
+ type: string
+ expr: substr(value, 5)
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: double
+ expr: _col4
+ type: double
+ expr: _col5
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT KEY._col1:0._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(DISTINCT KEY._col1:1._col0)
+ expr: count(VALUE._col3)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: concat(_col0, _col2)
+ type: string
+ expr: _col3
+ type: double
+ expr: _col4
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: _col2
+ type: string
+ expr: UDFToInteger(_col3)
+ type: int
+ expr: UDFToInteger(_col4)
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-03-34_053_4042312084657375262/-mr-10000
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-03-34_053_4042312084657375262/-mr-10000
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+0 1 00.0 0 3
+1 71 116414.0 10044 115
+2 69 225571.0 15780 111
+3 62 332004.0 20119 99
+4 74 452763.0 30965 124
+5 6 5397.0 278 10
+6 5 6398.0 331 6
+7 6 7735.0 447 10
+8 8 8762.0 595 10
+9 7 91047.0 577 12
Modified: hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby2_map_skew.q.out Wed Oct 27 19:00:02 2010
@@ -67,7 +67,7 @@ STAGE PLANS:
Reduce Operator Tree:
Group By Operator
aggregations:
- expr: count(DISTINCT KEY._col1)
+ expr: count(DISTINCT KEY._col1:0._col0)
expr: sum(VALUE._col1)
bucketGroup: false
keys:
Modified: hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew.q.out Wed Oct 27 19:00:02 2010
@@ -47,8 +47,8 @@ STAGE PLANS:
Reduce Operator Tree:
Group By Operator
aggregations:
- expr: count(DISTINCT KEY._col1)
- expr: sum(KEY._col1)
+ expr: count(DISTINCT KEY._col1:0._col0)
+ expr: sum(KEY._col1:0._col0)
bucketGroup: false
keys:
expr: KEY._col0
Added: hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out?rev=1028072&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out Wed Oct 27 19:00:02 2010
@@ -0,0 +1,149 @@
+PREHOOK: query: CREATE TABLE dest_g2(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest_g2(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest_g2
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest_g2)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5)))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL src) value)))) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Reduce Output Operator
+ key expressions:
+ expr: substr(key, 1, 1)
+ type: string
+ expr: substr(value, 5)
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: substr(key, 1, 1)
+ type: string
+ tag: -1
+ value expressions:
+ expr: value
+ type: string
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT KEY._col1:0._col0)
+ expr: sum(KEY._col1:1._col0)
+ expr: sum(DISTINCT KEY._col1:1._col0)
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: concat(_col0, _col2)
+ type: string
+ expr: _col3
+ type: double
+ expr: _col4
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: _col2
+ type: string
+ expr: UDFToInteger(_col3)
+ type: int
+ expr: UDFToInteger(_col4)
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ 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: dest_g2
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: dest_g2
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest_g2
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(src.value) GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest_g2
+POSTHOOK: Lineage: dest_g2.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_g2.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_g2.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_g2.c4 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest_g2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest_g2.* FROM dest_g2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g2
+PREHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-04-17_707_2990757298865083943/-mr-10000
+POSTHOOK: query: SELECT dest_g2.* FROM dest_g2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g2
+POSTHOOK: Output: file:/tmp/amarsri/hive_2010-10-20_03-04-17_707_2990757298865083943/-mr-10000
+POSTHOOK: Lineage: dest_g2.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_g2.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_g2.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_g2.c4 EXPRESSION [(src)src.null, ]
+POSTHOOK: Lineage: dest_g2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+0 1 00.0 0 3
+1 71 116414.0 10044 115
+2 69 225571.0 15780 111
+3 62 332004.0 20119 99
+4 74 452763.0 30965 124
+5 6 5397.0 278 10
+6 5 6398.0 331 6
+7 6 7735.0 447 10
+8 8 8762.0 595 10
+9 7 91047.0 577 12
Modified: hive/trunk/ql/src/test/results/clientpositive/groupby3.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby3.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby3.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby3.q.out Wed Oct 27 19:00:02 2010
@@ -62,15 +62,15 @@ STAGE PLANS:
Reduce Operator Tree:
Group By Operator
aggregations:
- expr: sum(KEY._col0)
- expr: avg(KEY._col0)
- expr: avg(DISTINCT KEY._col0)
- expr: max(KEY._col0)
- expr: min(KEY._col0)
- expr: std(KEY._col0)
- expr: stddev_samp(KEY._col0)
- expr: variance(KEY._col0)
- expr: var_samp(KEY._col0)
+ expr: sum(KEY._col0:0._col0)
+ expr: avg(KEY._col0:0._col0)
+ expr: avg(DISTINCT KEY._col0:0._col0)
+ expr: max(KEY._col0:0._col0)
+ expr: min(KEY._col0:0._col0)
+ expr: std(KEY._col0:0._col0)
+ expr: stddev_samp(KEY._col0:0._col0)
+ expr: variance(KEY._col0:0._col0)
+ expr: var_samp(KEY._col0:0._col0)
bucketGroup: false
mode: partial1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Modified: hive/trunk/ql/src/test/results/clientpositive/groupby3_map.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby3_map.q.out?rev=1028072&r1=1028071&r2=1028072&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby3_map.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby3_map.q.out Wed Oct 27 19:00:02 2010
@@ -96,7 +96,7 @@ STAGE PLANS:
aggregations:
expr: sum(VALUE._col0)
expr: avg(VALUE._col1)
- expr: avg(DISTINCT KEY._col0)
+ expr: avg(DISTINCT KEY._col0:0._col0)
expr: max(VALUE._col3)
expr: min(VALUE._col4)
expr: std(VALUE._col5)