PREHOOK: query: -- Create bucketed and sorted tables
CREATE TABLE test_table1 (key INT, value 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 bucketed and sorted tables
CREATE TABLE test_table1 (key INT, value 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 (key INT, value 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 (key INT, value 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 SELECT *
INSERT OVERWRITE TABLE test_table2 SELECT *
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@test_table1
PREHOOK: Output: default@test_table2
POSTHOOK: query: FROM src
INSERT OVERWRITE TABLE test_table1 SELECT *
INSERT OVERWRITE TABLE test_table2 SELECT *
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@test_table1
POSTHOOK: Output: default@test_table2
POSTHOOK: Lineage: test_table1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: test_table1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: test_table2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: test_table2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: -- Mapjoin followed by a aggregation should be performed in a single MR job
EXPLAIN
SELECT /*+mapjoin(b)*/ count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: -- Mapjoin followed by a aggregation should be performed in a single MR job
EXPLAIN
SELECT /*+mapjoin(b)*/ count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-0 depends on stages: Stage-1

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
            Filter Operator
              predicate: key is not null (type: boolean)
              Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
              Sorted Merge Bucket Map Join Operator
                condition map:
                     Inner Join 0 to 1
                keys:
                  0 key (type: int)
                  1 key (type: int)
                Group By Operator
                  aggregations: count()
                  mode: hash
                  outputColumnNames: _col0
                  Reduce Output Operator
                    sort order: 
                    value expressions: _col0 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          mode: mergepartial
          outputColumnNames: _col0
          Select Operator
            expressions: _col0 (type: bigint)
            outputColumnNames: _col0
            File Output Operator
              compressed: false
              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

  Stage: Stage-0
    Fetch Operator
      limit: -1
      Processor Tree:
        ListSink

PREHOOK: query: SELECT /*+mapjoin(b)*/ count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key
PREHOOK: type: QUERY
PREHOOK: Input: default@test_table1
PREHOOK: Input: default@test_table2
#### A masked pattern was here ####
POSTHOOK: query: SELECT /*+mapjoin(b)*/ count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@test_table1
POSTHOOK: Input: default@test_table2
#### A masked pattern was here ####
1028