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
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: 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
POSTHOOK: query: CREATE TABLE test_table2 (key INT, value 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 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
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), ]
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_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST b))) (TOK_SELEXPR (TOK_FUNCTIONSTAR count)))))

STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-0 is a root stage

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 
                1 
              handleSkewJoin: false
              keys:
                0 [Column[key]]
                1 [Column[key]]
              Position of Big Table: 0
              Select Operator
                Group By Operator
                  aggregations:
                        expr: count()
                  bucketGroup: false
                  mode: hash
                  outputColumnNames: _col0
                  Reduce Output Operator
                    sort order: 
                    tag: -1
                    value expressions:
                          expr: _col0
                          type: bigint
      Reduce Operator Tree:
        Group By Operator
          aggregations:
                expr: count(VALUE._col0)
          bucketGroup: false
          mode: mergepartial
          outputColumnNames: _col0
          Select Operator
            expressions:
                  expr: _col0
                  type: bigint
            outputColumnNames: _col0
            File Output Operator
              compressed: false
              GlobalTableId: 0
              table:
                  input format: org.apache.hadoop.mapred.TextInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

  Stage: Stage-0
    Fetch Operator
      limit: -1


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 ####
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), ]
1028