You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by na...@apache.org on 2013/04/12 08:39:38 UTC
svn commit: r1467174 [2/5] - in /hive/trunk/ql/src:
java/org/apache/hadoop/hive/ql/exec/
java/org/apache/hadoop/hive/ql/optimizer/ test/queries/clientpositive/
test/results/clientpositive/
Added: hive/trunk/ql/src/test/results/clientpositive/bucketsortoptimize_insert_2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/bucketsortoptimize_insert_2.q.out?rev=1467174&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/bucketsortoptimize_insert_2.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/bucketsortoptimize_insert_2.q.out Fri Apr 12 06:39:37 2013
@@ -0,0 +1,1384 @@
+PREHOOK: query: -- Create two bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: -- Create two bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@test_table1
+PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@test_table2
+PREHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@test_table3
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table1@ds=1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table1@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') SELECT * where key < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table2@ds=1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') SELECT * where key < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table2@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '2') SELECT * where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table1@ds=2
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '2') SELECT * where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table1@ds=2
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2') SELECT * where key < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table2@ds=2
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2') SELECT * where key < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table2@ds=2
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds = '1'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test_table1) a) (TOK_TABREF (TOK_TABNAME test_table2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table3) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (TOK_FUNCTION concat (. (TOK_TABLE_OR_COL a) value) (. (TOK_TABLE_OR_COL b) value)))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL a) ds) '1') (= (. (TOK_TABLE_OR_COL b) ds) '1')))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1, _col6
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: concat(_col1, _col6)
+ type: string
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+PREHOOK: Output: default@test_table3@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+POSTHOOK: Output: default@test_table3@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+2 val_2val_2 1
+4 val_4val_4 1
+8 val_8val_8 1
+PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+9 val_9val_9 1
+PREHOOK: query: -- Since more than one partition of 'a' (the big table) is being selected,
+-- it should be a map-reduce job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds is not null and b.ds = '1'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Since more than one partition of 'a' (the big table) is being selected,
+-- it should be a map-reduce job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds is not null and b.ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test_table1) a) (TOK_TABREF (TOK_TABNAME test_table2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table3) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (TOK_FUNCTION concat (. (TOK_TABLE_OR_COL a) value) (. (TOK_TABLE_OR_COL b) value)))) (TOK_WHERE (and (TOK_FUNCTION TOK_ISNOTNULL (. (TOK_TABLE_OR_COL a) ds)) (= (. (TOK_TABLE_OR_COL b) ds) '1')))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1, _col6
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: concat(_col1, _col6)
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds is not null and b.ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Input: default@test_table1@ds=2
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+PREHOOK: Output: default@test_table3@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds is not null and b.ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Input: default@test_table1@ds=2
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+POSTHOOK: Output: default@test_table3@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+2 val_2val_2 1
+2 val_2val_2 1
+4 val_4val_4 1
+4 val_4val_4 1
+8 val_8val_8 1
+8 val_8val_8 1
+PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+9 val_9val_9 1
+9 val_9val_9 1
+PREHOOK: query: -- Since a single partition of the big table ('a') is being selected, it should be a map-only
+-- job even though multiple partitions of 'b' are being selected
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds is not null
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Since a single partition of the big table ('a') is being selected, it should be a map-only
+-- job even though multiple partitions of 'b' are being selected
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds is not null
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test_table1) a) (TOK_TABREF (TOK_TABNAME test_table2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table3) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (TOK_FUNCTION concat (. (TOK_TABLE_OR_COL a) value) (. (TOK_TABLE_OR_COL b) value)))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL a) ds) '1') (TOK_FUNCTION TOK_ISNOTNULL (. (TOK_TABLE_OR_COL b) ds))))))
+
+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:
+ a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1, _col6
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: concat(_col1, _col6)
+ type: string
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds is not null
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+PREHOOK: Input: default@test_table2@ds=2
+PREHOOK: Output: default@test_table3@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM test_table1 a JOIN test_table2 b
+ON a.key = b.key WHERE a.ds = '1' and b.ds is not null
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+POSTHOOK: Input: default@test_table2@ds=2
+POSTHOOK: Output: default@test_table3@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+2 val_2val_2 1
+2 val_2val_2 1
+4 val_4val_4 1
+4 val_4val_4 1
+8 val_8val_8 1
+8 val_8val_8 1
+PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+9 val_9val_9 1
+9 val_9val_9 1
+PREHOOK: query: -- This should be a map-only job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- This should be a map-only job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '1')))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '1')))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table3) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (TOK_FUNCTION concat (. (TOK_TABLE_OR_COL a) value) (. (TOK_TABLE_OR_COL b) value))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a:test_table1
+ TableScan
+ alias: test_table1
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: concat(_col1, _col3)
+ type: string
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+PREHOOK: Output: default@test_table3@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+POSTHOOK: Output: default@test_table3@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+2 val_2val_2 1
+4 val_4val_4 1
+8 val_8val_8 1
+PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+5 val_5val_5 1
+9 val_9val_9 1
+PREHOOK: query: -- This should be a map-only job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.v1, b.v2)
+FROM
+(select key, concat(value, value) as v1 from test_table1 where ds = '1') a
+JOIN
+(select key, concat(value, value) as v2 from test_table2 where ds = '1') b
+ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- This should be a map-only job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.v1, b.v2)
+FROM
+(select key, concat(value, value) as v1 from test_table1 where ds = '1') a
+JOIN
+(select key, concat(value, value) as v2 from test_table2 where ds = '1') b
+ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_TABLE_OR_COL value) (TOK_TABLE_OR_COL value)) v1)) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '1')))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_TABLE_OR_COL value) (TOK_TABLE_OR_COL value)) v2)) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '1')))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table3) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (TOK_FUNCTION concat (. (TOK_TABLE_OR_COL a) v1) (. (TOK_TABLE_OR_COL b) v2))))))
+
+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:
+ a:test_table1
+ TableScan
+ alias: test_table1
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ expr: concat(value, value)
+ type: string
+ outputColumnNames: _col0, _col1
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: concat(_col1, _col3)
+ type: string
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.v1, b.v2)
+FROM
+(select key, concat(value, value) as v1 from test_table1 where ds = '1') a
+JOIN
+(select key, concat(value, value) as v2 from test_table2 where ds = '1') b
+ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+PREHOOK: Output: default@test_table3@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key, concat(a.v1, b.v2)
+FROM
+(select key, concat(value, value) as v1 from test_table1 where ds = '1') a
+JOIN
+(select key, concat(value, value) as v2 from test_table2 where ds = '1') b
+ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+POSTHOOK: Output: default@test_table3@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+0 val_0val_0val_0val_0 1
+2 val_2val_2val_2val_2 1
+4 val_4val_4val_4val_4 1
+8 val_8val_8val_8val_8 1
+PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+5 val_5val_5val_5val_5 1
+9 val_9val_9val_9val_9 1
+PREHOOK: query: -- This should be a map-reduce job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key+a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- This should be a map-reduce job
+EXPLAIN
+INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key+a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '1')))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '1')))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table3) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR (+ (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL a) key))) (TOK_SELEXPR (TOK_FUNCTION concat (. (TOK_TABLE_OR_COL a) value) (. (TOK_TABLE_OR_COL b) value))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a:test_table1
+ TableScan
+ alias: test_table1
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: (_col0 + _col0)
+ type: int
+ expr: concat(_col1, _col3)
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_table3
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key+a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+PREHOOK: Output: default@test_table3@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
+SELECT a.key+a.key, concat(a.value, b.value)
+FROM
+(select key, value from test_table1 where ds = '1') a
+JOIN
+(select key, value from test_table2 where ds = '1') b
+ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+POSTHOOK: Output: default@test_table3@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key EXPRESSION [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key EXPRESSION [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ]
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+0 val_0val_0 1
+4 val_2val_2 1
+8 val_4val_4 1
+10 val_5val_5 1
+10 val_5val_5 1
+10 val_5val_5 1
+10 val_5val_5 1
+10 val_5val_5 1
+10 val_5val_5 1
+10 val_5val_5 1
+10 val_5val_5 1
+10 val_5val_5 1
+16 val_8val_8 1
+18 val_9val_9 1
+PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table3@ds=1
+#### A masked pattern was here ####
[... 21 lines stripped ...]