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 STRING, value1 STRING, value2 string) PARTITIONED BY (ds STRING)
CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
PREHOOK: type: CREATETABLE
POSTHOOK: query: CREATE TABLE test_table2 (key STRING, value1 STRING, value2 string) PARTITIONED BY (ds STRING)
CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: default@test_table2
PREHOOK: query: FROM src
INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT *
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 *
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: -- Insert data into the bucketed table by selecting from another bucketed table
-- with different datatypes. This should be a map-reduce operation
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1'
PREHOOK: type: QUERY
POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
-- with different datatypes. This should be a map-reduce operation
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.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), ]
ABSTRACT SYNTAX TREE:
  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table1) a)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table2) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL a) 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
            Select Operator
              expressions:
                    expr: key
                    type: int
                    expr: value
                    type: string
                    expr: value
                    type: string
              outputColumnNames: _col0, _col1, _col2
              Reduce Output Operator
                key expressions:
                      expr: UDFToString(_col0)
                      type: string
                sort order: +
                Map-reduce partition columns:
                      expr: UDFToString(_col0)
                      type: string
                tag: -1
                value expressions:
                      expr: _col0
                      type: int
                      expr: _col1
                      type: string
                      expr: _col2
                      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_table2

  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_table2

  Stage: Stage-2
    Stats-Aggr Operator


PREHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1'
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table1
PREHOOK: Input: default@test_table1@ds=1
PREHOOK: Output: default@test_table2@ds=1
POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table1
POSTHOOK: Input: default@test_table1@ds=1
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 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
PREHOOK: query: select count(*) from test_table2 where ds = '1'
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table2
PREHOOK: Input: default@test_table2@ds=1
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from test_table2 where ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table2
POSTHOOK: Input: default@test_table2@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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
500
PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 0
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table2
PREHOOK: Input: default@test_table2@ds=1
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 0
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table2
POSTHOOK: Input: default@test_table2@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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
242
PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 1
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table2
PREHOOK: Input: default@test_table2@ds=1
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table2
POSTHOOK: Input: default@test_table2@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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
258
PREHOOK: query: CREATE TABLE test_table3 (key STRING, value1 int, value2 string) PARTITIONED BY (ds STRING)
CLUSTERED BY (value1) SORTED BY (value1) INTO 2 BUCKETS
PREHOOK: type: CREATETABLE
POSTHOOK: query: CREATE TABLE test_table3 (key STRING, value1 int, value2 string) PARTITIONED BY (ds STRING)
CLUSTERED BY (value1) SORTED BY (value1) INTO 2 BUCKETS
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: default@test_table3
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 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
-- This should be a map-only operation, although the bucketing positions dont match
EXPLAIN
INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
SELECT a.value, a.key, a.value FROM test_table1 a WHERE a.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, although the bucketing positions dont match
EXPLAIN
INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
SELECT a.value, a.key, a.value FROM test_table1 a WHERE a.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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
ABSTRACT SYNTAX TREE:
  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table1) a)) (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) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL a) 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
            Select Operator
              expressions:
                    expr: value
                    type: string
                    expr: key
                    type: int
                    expr: value
                    type: string
              outputColumnNames: _col0, _col1, _col2
              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.value, a.key, a.value FROM test_table1 a WHERE a.ds = '1'
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table1
PREHOOK: Input: default@test_table1@ds=1
PREHOOK: Output: default@test_table3@ds=1
POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1')
SELECT a.value, a.key, a.value FROM test_table1 a WHERE a.ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table1
POSTHOOK: Input: default@test_table1@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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
PREHOOK: query: select count(*) from test_table3 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 count(*) from test_table3 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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
500
PREHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 0
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table3
PREHOOK: Input: default@test_table3@ds=1
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 0
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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
247
PREHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 1
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table3
PREHOOK: Input: default@test_table3@ds=1
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
253
PREHOOK: query: select count(*) 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 count(*) 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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
247
PREHOOK: query: select count(*) 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 count(*) 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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
253
PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
-- However, since an expression is being selected, it should involve a reducer
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
SELECT a.key+a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1'
PREHOOK: type: QUERY
POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
-- However, since an expression is being selected, it should involve a reducer
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
SELECT a.key+a.key, a.value, a.value FROM test_table1 a WHERE a.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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
ABSTRACT SYNTAX TREE:
  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test_table1) a)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME test_table2) (TOK_PARTSPEC (TOK_PARTVAL ds '2')))) (TOK_SELECT (TOK_SELEXPR (+ (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL a) key))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL a) 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
            Select Operator
              expressions:
                    expr: (key + key)
                    type: int
                    expr: value
                    type: string
                    expr: value
                    type: string
              outputColumnNames: _col0, _col1, _col2
              Reduce Output Operator
                key expressions:
                      expr: UDFToString(_col0)
                      type: string
                sort order: +
                Map-reduce partition columns:
                      expr: UDFToString(_col0)
                      type: string
                tag: -1
                value expressions:
                      expr: _col0
                      type: int
                      expr: _col1
                      type: string
                      expr: _col2
                      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_table2

  Stage: Stage-0
    Move Operator
      tables:
          partition:
            ds 2
          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_table2

  Stage: Stage-2
    Stats-Aggr Operator