You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ke...@apache.org on 2012/09/28 21:18:11 UTC
svn commit: r1391608 [3/4] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ conf/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/
ql/src/java/org/apache/hadoop/hive/ql/parse/ ql/src/java/org/ap...
Added: hive/trunk/ql/src/test/results/clientpositive/groupby_sort_skew_1.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/groupby_sort_skew_1.q.out?rev=1391608&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/groupby_sort_skew_1.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/groupby_sort_skew_1.q.out Fri Sep 28 19:18:10 2012
@@ -0,0 +1,6895 @@
+PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t1
+PREHOOK: query: -- perform an insert to make sure there are 2 files
+INSERT OVERWRITE TABLE T1 select key, val from T1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@t1
+POSTHOOK: query: -- perform an insert to make sure there are 2 files
+INSERT OVERWRITE TABLE T1 select key, val from T1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@t1
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: CREATE TABLE outputTbl1(key int, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE outputTbl1(key int, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@outputTbl1
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: -- The plan should be converted to a map-side group by if the group by key
+-- matches the skewed key
+-- addind a order by at the end to make the test results deterministic
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM T1 GROUP BY key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The plan should be converted to a map-side group by if the group by key
+-- matches the skewed key
+-- addind a order by at the end to make the test results deterministic
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM T1 GROUP BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl1))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
+
+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:
+ t1
+ TableScan
+ alias: t1
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: final
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,cnt
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.outputtbl1
+ serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: t1
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.t1
+ name: default.t1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,cnt
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.outputtbl1
+ serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl1
+#### A masked pattern was here ####
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM T1 GROUP BY key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@outputtbl1
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM T1 GROUP BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@outputtbl1
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: SELECT * FROM outputTbl1 ORDER BY key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@outputtbl1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM outputTbl1 ORDER BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@outputtbl1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+1 1
+2 1
+3 1
+7 1
+8 2
+PREHOOK: query: CREATE TABLE outputTbl2(key1 int, key2 string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE outputTbl2(key1 int, key2 string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@outputTbl2
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: -- no map-side group by even if the group by key is a superset of skewed key
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl2
+SELECT key, val, count(1) FROM T1 GROUP BY key, val
+PREHOOK: type: QUERY
+POSTHOOK: query: -- no map-side group by even if the group by key is a superset of skewed key
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl2
+SELECT key, val, count(1) FROM T1 GROUP BY key, val
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl2))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL val))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ t1
+ TableScan
+ alias: t1
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ outputColumnNames: key, val
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: rand()
+ type: double
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: t1
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.t1
+ name: default.t1
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: string
+ mode: partials
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types string,string,bigint
+ escape.delim \
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10002
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types string,string,bigint
+ escape.delim \
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types string,string,bigint
+ escape.delim \
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: string
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: _col1
+ type: string
+ expr: UDFToInteger(_col2)
+ type: int
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,cnt
+ columns.types int:string:int
+#### A masked pattern was here ####
+ name default.outputtbl2
+ serialization.ddl struct outputtbl2 { i32 key1, string key2, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl2
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,cnt
+ columns.types int:string:int
+#### A masked pattern was here ####
+ name default.outputtbl2
+ serialization.ddl struct outputtbl2 { i32 key1, string key2, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl2
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl2
+SELECT key, val, count(1) FROM T1 GROUP BY key, val
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@outputtbl2
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl2
+SELECT key, val, count(1) FROM T1 GROUP BY key, val
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@outputtbl2
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: SELECT * FROM outputTbl2 ORDER BY key1, key2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@outputtbl2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM outputTbl2 ORDER BY key1, key2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@outputtbl2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+1 11 1
+2 12 1
+3 13 1
+7 17 1
+8 18 1
+8 28 1
+PREHOOK: query: -- It should work for sub-queries
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP BY key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- It should work for sub-queries
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val))))) subq1)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl1))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
+
+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:
+ subq1:t1
+ TableScan
+ alias: t1
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: final
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,cnt
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.outputtbl1
+ numFiles 1
+ numPartitions 0
+ numRows 5
+ rawDataSize 15
+ serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 20
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: t1
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.t1
+ name: default.t1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,cnt
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.outputtbl1
+ numFiles 1
+ numPartitions 0
+ numRows 5
+ rawDataSize 15
+ serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 20
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl1
+#### A masked pattern was here ####
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP BY key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@outputtbl1
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl1
+SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@outputtbl1
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: SELECT * FROM outputTbl1 ORDER BY key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@outputtbl1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM outputTbl1 ORDER BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@outputtbl1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+1 1
+2 1
+3 1
+7 1
+8 2
+PREHOOK: query: -- It should work for sub-queries with column aliases
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq1 GROUP BY k
+PREHOOK: type: QUERY
+POSTHOOK: query: -- It should work for sub-queries with column aliases
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq1 GROUP BY k
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key) k) (TOK_SELEXPR (TOK_TABLE_OR_COL val) v)))) subq1)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl1))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL k)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL k))))
+
+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:
+ subq1:t1
+ TableScan
+ alias: t1
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: final
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,cnt
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.outputtbl1
+ numFiles 1
+ numPartitions 0
+ numRows 5
+ rawDataSize 15
+ serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 20
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: t1
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.t1
+ name: default.t1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,cnt
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.outputtbl1
+ numFiles 1
+ numPartitions 0
+ numRows 5
+ rawDataSize 15
+ serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 20
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl1
+#### A masked pattern was here ####
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl1
+SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq1 GROUP BY k
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@outputtbl1
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl1
+SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq1 GROUP BY k
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@outputtbl1
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: SELECT * FROM outputTbl1 ORDER BY key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@outputtbl1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM outputTbl1 ORDER BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@outputtbl1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+1 1
+2 1
+3 1
+7 1
+8 2
+PREHOOK: query: CREATE TABLE outputTbl3(key1 int, key2 int, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE outputTbl3(key1 int, key2 int, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@outputTbl3
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: -- The plan should be converted to a map-side group by if the group by key contains a constant followed
+-- by a match to the skewed key
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl3
+SELECT 1, key, count(1) FROM T1 GROUP BY 1, key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The plan should be converted to a map-side group by if the group by key contains a constant followed
+-- by a match to the skewed key
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl3
+SELECT 1, key, count(1) FROM T1 GROUP BY 1, key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl3))) (TOK_SELECT (TOK_SELEXPR 1) (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY 1 (TOK_TABLE_OR_COL key))))
+
+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:
+ t1
+ TableScan
+ alias: t1
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: 1
+ type: int
+ expr: key
+ type: string
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: UDFToInteger(_col2)
+ type: int
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,cnt
+ columns.types int:int:int
+#### A masked pattern was here ####
+ name default.outputtbl3
+ serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl3
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: t1
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.t1
+ name: default.t1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,cnt
+ columns.types int:int:int
+#### A masked pattern was here ####
+ name default.outputtbl3
+ serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl3
+#### A masked pattern was here ####
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl3
+SELECT 1, key, count(1) FROM T1 GROUP BY 1, key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@outputtbl3
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl3
+SELECT 1, key, count(1) FROM T1 GROUP BY 1, key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@outputtbl3
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: SELECT * FROM outputTbl3 ORDER BY key1, key2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@outputtbl3
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM outputTbl3 ORDER BY key1, key2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@outputtbl3
+#### A masked pattern was here ####
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+1 1 1
+1 2 1
+1 3 1
+1 7 1
+1 8 2
+PREHOOK: query: CREATE TABLE outputTbl4(key1 int, key2 int, key3 string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE outputTbl4(key1 int, key2 int, key3 string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@outputTbl4
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: -- no map-side group by if the group by key contains a constant followed by another column
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl4
+SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val
+PREHOOK: type: QUERY
+POSTHOOK: query: -- no map-side group by if the group by key contains a constant followed by another column
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl4
+SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl4))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR 1) (TOK_SELEXPR (TOK_TABLE_OR_COL val)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) 1 (TOK_TABLE_OR_COL val))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ t1
+ TableScan
+ alias: t1
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ outputColumnNames: key, val
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ expr: 1
+ type: int
+ expr: val
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: rand()
+ type: double
+ tag: -1
+ value expressions:
+ expr: _col3
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: t1
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.t1
+ name: default.t1
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: partials
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string,int,string,bigint
+ escape.delim \
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col3
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10002
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string,int,string,bigint
+ escape.delim \
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string,int,string,bigint
+ escape.delim \
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: final
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ expr: UDFToInteger(_col3)
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,key3,cnt
+ columns.types int:int:string:int
+#### A masked pattern was here ####
+ name default.outputtbl4
+ serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl4
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,key3,cnt
+ columns.types int:int:string:int
+#### A masked pattern was here ####
+ name default.outputtbl4
+ serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl4
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl4
+SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@outputtbl4
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl4
+SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@outputtbl4
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.key2 SIMPLE []
+POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: SELECT * FROM outputTbl4 ORDER BY key1, key2, key3
+PREHOOK: type: QUERY
+PREHOOK: Input: default@outputtbl4
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM outputTbl4 ORDER BY key1, key2, key3
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@outputtbl4
+#### A masked pattern was here ####
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.key2 SIMPLE []
+POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+1 1 11 1
+2 1 12 1
+3 1 13 1
+7 1 17 1
+8 1 18 1
+8 1 28 1
+PREHOOK: query: -- no map-side group by if the group by key contains a function
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl3
+SELECT key, key + 1, count(1) FROM T1 GROUP BY key, key + 1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- no map-side group by if the group by key contains a function
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl3
+SELECT key, key + 1, count(1) FROM T1 GROUP BY key, key + 1
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.key2 SIMPLE []
+POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl3))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (+ (TOK_TABLE_OR_COL key) 1)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) (+ (TOK_TABLE_OR_COL key) 1))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ t1
+ TableScan
+ alias: t1
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ expr: (key + 1)
+ type: double
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: double
+ sort order: ++
+ Map-reduce partition columns:
+ expr: rand()
+ type: double
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: t1
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,val
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.t1
+ numFiles 1
+ numPartitions 0
+ numRows 6
+ rawDataSize 24
+ serialization.ddl struct t1 { string key, string val}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.t1
+ name: default.t1
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: double
+ mode: partials
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types string,double,bigint
+ escape.delim \
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: double
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: double
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10002
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types string,double,bigint
+ escape.delim \
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types string,double,bigint
+ escape.delim \
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: double
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: double
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: UDFToInteger(_col2)
+ type: int
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,cnt
+ columns.types int:int:int
+#### A masked pattern was here ####
+ name default.outputtbl3
+ numFiles 1
+ numPartitions 0
+ numRows 5
+ rawDataSize 25
+ serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl3
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key1,key2,cnt
+ columns.types int:int:int
+#### A masked pattern was here ####
+ name default.outputtbl3
+ numFiles 1
+ numPartitions 0
+ numRows 5
+ rawDataSize 25
+ serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 30
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl3
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl3
+SELECT key, key + 1, count(1) FROM T1 GROUP BY key, key + 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@outputtbl3
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl3
+SELECT key, key + 1, count(1) FROM T1 GROUP BY key, key + 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@outputtbl3
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.key2 SIMPLE []
+POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+PREHOOK: query: SELECT * FROM outputTbl3 ORDER BY key1, key2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@outputtbl3
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM outputTbl3 ORDER BY key1, key2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@outputtbl3
+#### A masked pattern was here ####
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl2.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl3.key1 SIMPLE []
+POSTHOOK: Lineage: outputtbl3.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl3.key2 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl4.key2 SIMPLE []
+POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
+1 2 1
+2 3 1
+3 4 1
+7 8 1
+8 9 2
+PREHOOK: query: -- it should not matter what follows the group by
+-- test various cases
+
+-- group by followed by another group by
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT key + key, sum(cnt) from
+(SELECT key, count(1) as cnt FROM T1 GROUP BY key) subq1
+group by key + key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- it should not matter what follows the group by
+-- test various cases
+
+-- group by followed by another group by
+EXPLAIN EXTENDED
+INSERT OVERWRITE TABLE outputTbl1
+SELECT key + key, sum(cnt) from
+(SELECT key, count(1) as cnt FROM T1 GROUP BY key) subq1
+group by key + key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
[... 4931 lines stripped ...]