You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by li...@apache.org on 2017/06/30 08:07:42 UTC
[7/8] hive git commit: HIVE-6348: Order by/Sort by in subquery (Rui
Li reviewed by Vineet Garg)
http://git-wip-us.apache.org/repos/asf/hive/blob/b11e43b1/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out b/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out
deleted file mode 100644
index 873a41d..0000000
--- a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out
+++ /dev/null
@@ -1,1431 +0,0 @@
-PREHOOK: query: EXPLAIN
-FROM
-(SELECT src.* FROM src sort by key) X
-RIGHT OUTER JOIN
-(SELECT src.* FROM src sort by value) Y
-ON (X.key = Y.key)
-JOIN
-(SELECT src.* FROM src sort by value) Z
-ON (X.key = Z.key)
-SELECT sum(hash(Y.key,Y.value)) GROUP BY Y.key
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-FROM
-(SELECT src.* FROM src sort by key) X
-RIGHT OUTER JOIN
-(SELECT src.* FROM src sort by value) Y
-ON (X.key = Y.key)
-JOIN
-(SELECT src.* FROM src sort by value) Z
-ON (X.key = Z.key)
-SELECT sum(hash(Y.key,Y.value)) GROUP BY Y.key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-4, Stage-5
- Stage-3 depends on stages: Stage-2
- Stage-4 is a root stage
- Stage-5 is a root stage
- Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- 2 _col0 (type: string)
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col2,_col3))
- keys: _col2 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: CREATE TABLE dest1(key INT, value STRING)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dest1
-POSTHOOK: query: CREATE TABLE dest1(key INT, value STRING)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dest1
-PREHOOK: query: CREATE TABLE dest2(key INT, value STRING)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dest2
-POSTHOOK: query: CREATE TABLE dest2(key INT, value STRING)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dest2
-PREHOOK: query: EXPLAIN
-FROM src
-INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(SUBSTR(src.value,5)) GROUP BY src.key
-INSERT OVERWRITE TABLE dest2 SELECT src.key, sum(SUBSTR(src.value,5)) GROUP BY src.key
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-FROM src
-INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(SUBSTR(src.value,5)) GROUP BY src.key
-INSERT OVERWRITE TABLE dest2 SELECT src.key, sum(SUBSTR(src.value,5)) GROUP BY src.key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-0 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-0
- Stage-4 depends on stages: Stage-2
- Stage-1 depends on stages: Stage-4
- Stage-5 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(substr(value, 5))
- keys: key (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(substr(value, 5))
- keys: key (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), UDFToString(_col1) (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.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: default.dest1
-
- Stage: Stage-3
- Stats-Aggr Operator
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: sum(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), UDFToString(_col1) (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: true
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest2
-
- Stage: Stage-1
- 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: default.dest2
-
- Stage: Stage-5
- Stats-Aggr Operator
-
-PREHOOK: query: SELECT dest1.* FROM dest1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT dest1.* FROM dest1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest1
-#### A masked pattern was here ####
-PREHOOK: query: SELECT dest2.* FROM dest2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest2
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT dest2.* FROM dest2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest2
-#### A masked pattern was here ####
-PREHOOK: query: DROP TABLE dest1
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@dest1
-PREHOOK: Output: default@dest1
-POSTHOOK: query: DROP TABLE dest1
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@dest1
-POSTHOOK: Output: default@dest1
-PREHOOK: query: DROP TABLE dest2
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@dest2
-PREHOOK: Output: default@dest2
-POSTHOOK: query: DROP TABLE dest2
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@dest2
-POSTHOOK: Output: default@dest2
-PREHOOK: query: CREATE TABLE tmptable(key STRING, value INT)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@tmptable
-POSTHOOK: query: CREATE TABLE tmptable(key STRING, value INT)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@tmptable
-PREHOOK: query: EXPLAIN
-INSERT OVERWRITE TABLE tmptable
- SELECT unionsrc.key, unionsrc.value FROM (SELECT 'tst1' AS key, count(1) AS value FROM src s1
- UNION ALL
- SELECT 'tst2' AS key, count(1) AS value FROM src s2
- UNION ALL
- SELECT 'tst3' AS key, count(1) AS value FROM src s3) unionsrc
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-INSERT OVERWRITE TABLE tmptable
- SELECT unionsrc.key, unionsrc.value FROM (SELECT 'tst1' AS key, count(1) AS value FROM src s1
- UNION ALL
- SELECT 'tst2' AS key, count(1) AS value FROM src s2
- UNION ALL
- SELECT 'tst3' AS key, count(1) AS value FROM src s3) unionsrc
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-9, Stage-10
- Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6
- Stage-5
- Stage-0 depends on stages: Stage-5, Stage-4, Stage-7
- Stage-3 depends on stages: Stage-0
- Stage-4
- Stage-6
- Stage-7 depends on stages: Stage-6
- Stage-9 is a root stage
- Stage-10 is a root stage
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 'tst1' (type: string), _col0 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Union
- Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.tmptable
- TableScan
- Union
- Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.tmptable
- TableScan
- Union
- Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.tmptable
-
- Stage: Stage-8
- Conditional Operator
-
- Stage: Stage-5
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- 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: default.tmptable
-
- Stage: Stage-3
- Stats-Aggr Operator
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.tmptable
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.tmptable
-
- Stage: Stage-7
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-9
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 'tst2' (type: string), _col0 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-10
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 'tst3' (type: string), _col0 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-PREHOOK: query: SELECT * FROM tmptable x SORT BY x.key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@tmptable
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM tmptable x SORT BY x.key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@tmptable
-#### A masked pattern was here ####
-PREHOOK: query: DROP TABLE tmtable
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE tmtable
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: EXPLAIN
-SELECT unionsrc1.key, unionsrc1.value, unionsrc2.key, unionsrc2.value
-FROM (SELECT 'tst1' AS key, cast(count(1) AS string) AS value FROM src s1
- UNION ALL
- SELECT s2.key AS key, s2.value AS value FROM src s2 WHERE s2.key < 10) unionsrc1
-JOIN
- (SELECT 'tst1' AS key, cast(count(1) AS string) AS value FROM src s3
- UNION ALL
- SELECT s4.key AS key, s4.value AS value FROM src s4 WHERE s4.key < 10) unionsrc2
-ON (unionsrc1.key = unionsrc2.key)
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-SELECT unionsrc1.key, unionsrc1.value, unionsrc2.key, unionsrc2.value
-FROM (SELECT 'tst1' AS key, cast(count(1) AS string) AS value FROM src s1
- UNION ALL
- SELECT s2.key AS key, s2.value AS value FROM src s2 WHERE s2.key < 10) unionsrc1
-JOIN
- (SELECT 'tst1' AS key, cast(count(1) AS string) AS value FROM src s3
- UNION ALL
- SELECT s4.key AS key, s4.value AS value FROM src s4 WHERE s4.key < 10) unionsrc2
-ON (unionsrc1.key = unionsrc2.key)
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-4
- Stage-4 is a root stage
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 'tst1' (type: string), UDFToString(_col0) (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Union
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- value expressions: _col1 (type: string)
- TableScan
- alias: s2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (UDFToDouble(key) < 10.0) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Union
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- value expressions: _col1 (type: string)
- TableScan
- Union
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- value expressions: _col1 (type: string)
- TableScan
- alias: s4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (UDFToDouble(key) < 10.0) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Union
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL
- File Output Operator
- compressed: true
- Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 'tst1' (type: string), UDFToString(_col0) (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: CREATE TABLE inv(w_warehouse_name STRING , w_warehouse_sk INT , stdev INT , d_moy INT , mean INT , cov INT , inv_quantity_on_hand INT)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@inv
-POSTHOOK: query: CREATE TABLE inv(w_warehouse_name STRING , w_warehouse_sk INT , stdev INT , d_moy INT , mean INT , cov INT , inv_quantity_on_hand INT)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@inv
-PREHOOK: query: CREATE TABLE inventory(inv_date_sk INT , inv_item_sk INT ,inv_quantity_on_hand INT ,inv_warehouse_sk INT)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@inventory
-POSTHOOK: query: CREATE TABLE inventory(inv_date_sk INT , inv_item_sk INT ,inv_quantity_on_hand INT ,inv_warehouse_sk INT)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@inventory
-PREHOOK: query: CREATE TABLE item(i_item_sk INT)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@item
-POSTHOOK: query: CREATE TABLE item(i_item_sk INT)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@item
-PREHOOK: query: CREATE TABLE warehouse(w_warehouse_sk INT , w_warehouse_name STRING)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@warehouse
-POSTHOOK: query: CREATE TABLE warehouse(w_warehouse_sk INT , w_warehouse_name STRING)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@warehouse
-PREHOOK: query: CREATE TABLE date_dim(d_date_sk INT , d_year INT , d_moy INT)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@date_dim
-POSTHOOK: query: CREATE TABLE date_dim(d_date_sk INT , d_year INT , d_moy INT)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@date_dim
-PREHOOK: query: EXPLAIN
-WITH inv AS
-(SELECT w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
- ,stdev,mean, CASE mean WHEN 0 THEN null ELSE stdev/mean END cov
-FROM(SELECT w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
- ,STDDEV_SAMP(inv_quantity_on_hand) stdev,AVG(inv_quantity_on_hand) mean
- FROM inventory
- ,item
- ,warehouse
- ,date_dim
- WHERE inv_item_sk = i_item_sk
- AND inv_warehouse_sk = w_warehouse_sk
- AND inv_date_sk = d_date_sk
- AND d_year =1999
- GROUP BY w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo
- WHERE CASE mean WHEN 0 THEN 0 ELSE stdev/mean END > 1)
-SELECT inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov
- ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov
-FROM inv inv1,inv inv2
-WHERE inv1.i_item_sk = inv2.i_item_sk
- AND inv1.w_warehouse_sk = inv2.w_warehouse_sk
- AND inv1.d_moy=3
- AND inv2.d_moy=3+1
-ORDER BY inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov
- ,inv2.d_moy,inv2.mean, inv2.cov
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-WITH inv AS
-(SELECT w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
- ,stdev,mean, CASE mean WHEN 0 THEN null ELSE stdev/mean END cov
-FROM(SELECT w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
- ,STDDEV_SAMP(inv_quantity_on_hand) stdev,AVG(inv_quantity_on_hand) mean
- FROM inventory
- ,item
- ,warehouse
- ,date_dim
- WHERE inv_item_sk = i_item_sk
- AND inv_warehouse_sk = w_warehouse_sk
- AND inv_date_sk = d_date_sk
- AND d_year =1999
- GROUP BY w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo
- WHERE CASE mean WHEN 0 THEN 0 ELSE stdev/mean END > 1)
-SELECT inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov
- ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov
-FROM inv inv1,inv inv2
-WHERE inv1.i_item_sk = inv2.i_item_sk
- AND inv1.w_warehouse_sk = inv2.w_warehouse_sk
- AND inv1.d_moy=3
- AND inv2.d_moy=3+1
-ORDER BY inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov
- ,inv2.d_moy,inv2.mean, inv2.cov
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-3
- Stage-5 depends on stages: Stage-4, Stage-13
- Stage-6 depends on stages: Stage-5
- Stage-10 is a root stage
- Stage-11 depends on stages: Stage-10
- Stage-12 depends on stages: Stage-11
- Stage-13 depends on stages: Stage-12
- Stage-0 depends on stages: Stage-6
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: inventory
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int), inv_warehouse_sk (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int)
- TableScan
- alias: item
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: i_item_sk is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: i_item_sk (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col3 (type: int)
- sort order: +
- Map-reduce partition columns: _col3 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int)
- TableScan
- alias: warehouse
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: w_warehouse_sk is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col3 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col2, _col4, _col5, _col6
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: string)
- TableScan
- alias: date_dim
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: ((d_year = 1999) and (d_moy = 3) and d_date_sk is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: d_date_sk (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col2, _col4, _col5, _col6
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: stddev_samp(_col2), avg(_col2)
- keys: _col5 (type: int), _col4 (type: int), _col6 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string)
- sort order: +++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:int>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: stddev_samp(VALUE._col0), avg(VALUE._col1)
- keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: int), _col3 (type: double), _col4 (type: double)
- outputColumnNames: _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col3 / _col4) > 1.0)) END (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col3 / _col4)) END (type: double)
- outputColumnNames: _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col1 (type: int), _col2 (type: int)
- sort order: ++
- Map-reduce partition columns: _col1 (type: int), _col2 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col3 (type: double), _col4 (type: double)
- TableScan
- Reduce Output Operator
- key expressions: _col1 (type: int), _col2 (type: int)
- sort order: ++
- Map-reduce partition columns: _col1 (type: int), _col2 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col3 (type: double), _col4 (type: double)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: int), _col2 (type: int)
- 1 _col1 (type: int), _col2 (type: int)
- outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col8, _col9
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double), _col4 (type: double), _col6 (type: int), _col7 (type: int), _col8 (type: double), _col9 (type: double)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: double), _col3 (type: double), _col6 (type: double), _col7 (type: double)
- sort order: ++++++
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col4 (type: int), _col5 (type: int)
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), 3 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), 4 (type: int), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-10
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: inventory
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int), inv_warehouse_sk (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int)
- TableScan
- alias: item
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: i_item_sk is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: i_item_sk (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-11
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col3 (type: int)
- sort order: +
- Map-reduce partition columns: _col3 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int)
- TableScan
- alias: warehouse
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: w_warehouse_sk is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col3 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col2, _col4, _col5, _col6
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-12
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: string)
- TableScan
- alias: date_dim
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: ((d_year = 1999) and (d_moy = 4) and d_date_sk is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: d_date_sk (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col2, _col4, _col5, _col6
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: stddev_samp(_col2), avg(_col2)
- keys: _col5 (type: int), _col4 (type: int), _col6 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-13
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string)
- sort order: +++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:int>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: stddev_samp(VALUE._col0), avg(VALUE._col1)
- keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: int), _col3 (type: double), _col4 (type: double)
- outputColumnNames: _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col3 / _col4) > 1.0)) END (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col3 / _col4)) END (type: double)
- outputColumnNames: _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: EXPLAIN
-WITH test AS
-(SELECT inv_date_sk , inv_item_sk ,inv_quantity_on_hand FROM inventory
- UNION ALL
- SELECT inv_date_sk , inv_item_sk ,inv_quantity_on_hand FROM inventory)
-SELECT inv_date_sk , inv_item_sk ,inv_quantity_on_hand FROM test SORT BY inv_quantity_on_hand
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
-WITH test AS
-(SELECT inv_date_sk , inv_item_sk ,inv_quantity_on_hand FROM inventory
- UNION ALL
- SELECT inv_date_sk , inv_item_sk ,inv_quantity_on_hand FROM inventory)
-SELECT inv_date_sk , inv_item_sk ,inv_quantity_on_hand FROM test SORT BY inv_quantity_on_hand
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: inventory
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Union
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: int)
- sort order: +
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: int)
- TableScan
- alias: inventory
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_quantity_on_hand (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Union
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: int)
- sort order: +
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: int)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: true
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: DROP TABLE inv
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@inv
-PREHOOK: Output: default@inv
-POSTHOOK: query: DROP TABLE inv
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@inv
-POSTHOOK: Output: default@inv
-PREHOOK: query: DROP TABLE inventory
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@inventory
-PREHOOK: Output: default@inventory
-POSTHOOK: query: DROP TABLE inventory
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@inventory
-POSTHOOK: Output: default@inventory
-PREHOOK: query: DROP TABLE item
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@item
-PREHOOK: Output: default@item
-POSTHOOK: query: DROP TABLE item
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@item
-POSTHOOK: Output: default@item
-PREHOOK: query: DROP TABLE warehouse
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@warehouse
-PREHOOK: Output: default@warehouse
-POSTHOOK: query: DROP TABLE warehouse
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@warehouse
-POSTHOOK: Output: default@warehouse
-PREHOOK: query: DROP TABLE date_dim
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@date_dim
-PREHOOK: Output: default@date_dim
-POSTHOOK: query: DROP TABLE date_dim
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@date_dim
-POSTHOOK: Output: default@date_dim
http://git-wip-us.apache.org/repos/asf/hive/blob/b11e43b1/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out
index a721b7f..4c5b0f8 100644
--- a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out
+++ b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out
@@ -24,8 +24,7 @@ POSTHOOK: query: explain select Q1.int1, sum(distinct Q1.int1) from (select * fr
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -36,39 +35,19 @@ STAGE PLANS:
Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: int1 (type: int)
- outputColumnNames: _col0
+ outputColumnNames: int1
Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
+ Group By Operator
+ aggregations: sum(DISTINCT int1)
+ keys: int1 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(DISTINCT _col0)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
aggregations: sum(DISTINCT KEY._col1:0._col0)
http://git-wip-us.apache.org/repos/asf/hive/blob/b11e43b1/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out b/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out
index 7ec14e8..eaa48a0 100644
--- a/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out
+++ b/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out
@@ -17,157 +17,31 @@ from
where t2.value='val_105' and t3.key='105'
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-6 depends on stages: Stage-1, Stage-3 , consists of Stage-7, Stage-8, Stage-2
- Stage-7 has a backup stage: Stage-2
- Stage-4 depends on stages: Stage-7
- Stage-8 has a backup stage: Stage-2
- Stage-5 depends on stages: Stage-8
- Stage-2
- Stage-3 is a root stage
- Stage-0 depends on stages: Stage-4, Stage-5, Stage-2
+ Stage-4 is a root stage
+ Stage-3 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-3
STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((value = 'val_105') and (key = '105')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: '105' (type: string)
- sort order: +
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Select Operator
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-6
- Conditional Operator
-
- Stage: Stage-7
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $INTNAME1
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- $INTNAME1
- TableScan
- HashTable Sink Operator
- keys:
- 0 '105' (type: string)
- 1 '105' (type: string)
-
Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 '105' (type: string)
- 1 '105' (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '105' (type: string), 'val_105' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-8
Map Reduce Local Work
Alias -> Map Local Tables:
- $INTNAME
+ t2:t1:src
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
- $INTNAME
+ t2:t1:src
TableScan
- HashTable Sink Operator
- keys:
- 0 '105' (type: string)
- 1 '105' (type: string)
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 '105' (type: string)
- 1 '105' (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '105' (type: string), 'val_105' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: '105' (type: string)
- sort order: +
- Map-reduce partition columns: '105' (type: string)
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((value = 'val_105') and (key = '105')) (type: boolean)
Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: '105' (type: string)
- sort order: +
- Map-reduce partition columns: '105' (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '105' (type: string), 'val_105' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 '105' (type: string)
+ 1 '105' (type: string)
Stage: Stage-3
Map Reduce
@@ -180,19 +54,26 @@ STAGE PLANS:
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: '105' (type: string)
- sort order: +
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Select Operator
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 '105' (type: string)
+ 1 '105' (type: string)
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '105' (type: string), 'val_105' (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b11e43b1/ql/src/test/results/clientpositive/input20.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input20.q.out b/ql/src/test/results/clientpositive/input20.q.out
index cf0ee1d..9587445 100644
--- a/ql/src/test/results/clientpositive/input20.q.out
+++ b/ql/src/test/results/clientpositive/input20.q.out
@@ -11,8 +11,7 @@ FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -24,8 +23,7 @@ FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -56,9 +54,8 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string)
+ sort order:
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
@@ -103,8 +100,7 @@ PREHOOK: query: FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -117,8 +113,7 @@ POSTHOOK: query: FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -129,11 +124,11 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1
POSTHOOK: Lineage: dest1.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest1.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-PREHOOK: query: SELECT * FROM dest1 SORT BY key, value
+PREHOOK: query: SELECT * FROM dest1 ORDER BY key, value
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1
#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM dest1 SORT BY key, value
+POSTHOOK: query: SELECT * FROM dest1 ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/b11e43b1/ql/src/test/results/clientpositive/input33.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input33.q.out b/ql/src/test/results/clientpositive/input33.q.out
index b35e2d0..4be5fc5 100644
--- a/ql/src/test/results/clientpositive/input33.q.out
+++ b/ql/src/test/results/clientpositive/input33.q.out
@@ -11,8 +11,7 @@ FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -24,8 +23,7 @@ FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -56,9 +54,8 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string)
+ sort order:
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
@@ -103,8 +100,7 @@ PREHOOK: query: FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -117,8 +113,7 @@ POSTHOOK: query: FROM (
FROM src
MAP src.key, src.key
USING 'cat'
- DISTRIBUTE BY key
- SORT BY key, value
+ DISTRIBUTE BY key, value
) tmap
INSERT OVERWRITE TABLE dest1
REDUCE tmap.key, tmap.value
@@ -129,11 +124,11 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1
POSTHOOK: Lineage: dest1.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest1.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-PREHOOK: query: SELECT * FROM dest1 SORT BY key, value
+PREHOOK: query: SELECT * FROM dest1 ORDER BY key, value
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1
#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM dest1 SORT BY key, value
+POSTHOOK: query: SELECT * FROM dest1 ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1
#### A masked pattern was here ####