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
PREHOOK: Output: database:default
PREHOOK: Output: default@test_table1
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: database:default
POSTHOOK: Output: default@test_table1
PREHOOK: query: CREATE TABLE test_table2 (value STRING, key INT) PARTITIONED BY (ds STRING)
CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@test_table2
POSTHOOK: query: CREATE TABLE test_table2 (value STRING, key INT) PARTITIONED BY (ds STRING)
CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
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
-- The bucketing positions dont match - although the actual bucketing do.
-- This should be a map-only operation
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT x.value, x.key from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
PREHOOK: type: QUERY
POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
-- The bucketing positions dont match - although the actual bucketing do.
-- This should be a map-only operation
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT x.value, x.key from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
POSTHOOK: type: QUERY
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
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
            Select Operator
              expressions: value (type: string), key (type: int)
              outputColumnNames: _col0, _col1
              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
              File Output Operator
                compressed: false
                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                table:
                    input format: org.apache.hadoop.mapred.TextInputFormat
                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                    name: default.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 x.value, x.key from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
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 x.value, x.key from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
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_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value 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 ####
500
PREHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s 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 tablesample (bucket 1 out of 2) s where ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table2
POSTHOOK: Input: default@test_table2@ds=1
#### A masked pattern was here ####
247
PREHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s 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 tablesample (bucket 2 out of 2) s where ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table2
POSTHOOK: Input: default@test_table2@ds=1
#### A masked pattern was here ####
253
PREHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) PARTITIONED BY (ds STRING)
CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@test_table3
POSTHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) PARTITIONED BY (ds STRING)
CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@test_table3
PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
-- The bucketing positions dont match - this should be a map-reduce operation
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT x.key, x.value from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
PREHOOK: type: QUERY
POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
-- The bucketing positions dont match - this should be a map-reduce operation
EXPLAIN
INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
SELECT x.key, x.value from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
POSTHOOK: type: QUERY
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
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
            Select Operator
              expressions: key (type: int), value (type: string)
              outputColumnNames: _col0, _col1
              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
              Reduce Output Operator
                key expressions: UDFToInteger(_col1) (type: int)
                sort order: +
                Map-reduce partition columns: UDFToInteger(_col1) (type: int)
                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                value expressions: _col0 (type: int), _col1 (type: string)
      Reduce Operator Tree:
        Extract
          Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
          Select Operator
            expressions: _col0 (type: int), UDFToInteger(_col1) (type: int)
            outputColumnNames: _col0, _col1
            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
              table:
                  input format: org.apache.hadoop.mapred.TextInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                  name: default.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 x.key, x.value from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
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 x.key, x.value from 
(SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1')x
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_table2 PARTITION(ds=1).key EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, 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 ####
500
PREHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s 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 tablesample (bucket 1 out of 2) s where ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table2
POSTHOOK: Input: default@test_table2@ds=1
#### A masked pattern was here ####
500
PREHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s 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 tablesample (bucket 2 out of 2) s where ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table2
POSTHOOK: Input: default@test_table2@ds=1
#### A masked pattern was here ####
0