PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) PARTITIONED BY (ds string)
CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T1
POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) PARTITIONED BY (ds string)
CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T1
PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 PARTITION (ds='1')
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@t1
POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 PARTITION (ds='1')
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@t1
POSTHOOK: Output: default@t1@ds=1
PREHOOK: query: -- perform an insert to make sure there are 2 files
INSERT OVERWRITE TABLE T1 PARTITION (ds='1') select key, val from T1 where ds = '1'
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t1@ds=1
PREHOOK: Output: default@t1@ds=1
POSTHOOK: query: -- perform an insert to make sure there are 2 files
INSERT OVERWRITE TABLE T1 PARTITION (ds='1') select key, val from T1 where ds = '1'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t1@ds=1
POSTHOOK: Output: default@t1@ds=1
POSTHOOK: Lineage: t1 PARTITION(ds=1).key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: t1 PARTITION(ds=1).val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ]
PREHOOK: query: -- The plan is not converted to a map-side, since although the sorting columns and grouping
-- columns match, the user is issueing a distinct.
-- However, after HIVE-4310, partial aggregation is performed on the mapper
EXPLAIN
select count(distinct key) from T1
PREHOOK: type: QUERY
POSTHOOK: query: -- The plan is not converted to a map-side, since although the sorting columns and grouping
-- columns match, the user is issueing a distinct.
-- However, after HIVE-4310, partial aggregation is performed on the mapper
EXPLAIN
select count(distinct key) from T1
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: t1
            Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
            Select Operator
              expressions: key (type: string)
              outputColumnNames: _col0
              Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
              Group By Operator
                aggregations: count(DISTINCT _col0)
                bucketGroup: true
                keys: _col0 (type: string)
                mode: hash
                outputColumnNames: _col0, _col1
                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                Reduce Output Operator
                  key expressions: _col0 (type: string)
                  sort order: +
                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                  value expressions: _col1 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          mode: mergepartial
          outputColumnNames: _col0
          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
          Select Operator
            expressions: _col0 (type: bigint)
            outputColumnNames: _col0
            Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 1 Data size: 16 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

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

PREHOOK: query: select count(distinct key) from T1
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t1@ds=1
#### A masked pattern was here ####
POSTHOOK: query: select count(distinct key) from T1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t1@ds=1
#### A masked pattern was here ####
5
PREHOOK: query: -- In testmode, the plan is not changed
EXPLAIN
select count(distinct key) from T1
PREHOOK: type: QUERY
POSTHOOK: query: -- In testmode, the plan is not changed
EXPLAIN
select count(distinct key) from T1
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: t1
            Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
            Select Operator
              expressions: key (type: string)
              outputColumnNames: _col0
              Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
              Group By Operator
                aggregations: count(DISTINCT _col0)
                keys: _col0 (type: string)
                mode: hash
                outputColumnNames: _col0, _col1
                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                Reduce Output Operator
                  key expressions: _col0 (type: string)
                  sort order: +
                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(DISTINCT KEY._col0:0._col0)
          mode: mergepartial
          outputColumnNames: _col0
          Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
          Select Operator
            expressions: _col0 (type: bigint)
            outputColumnNames: _col0
            Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 1 Data size: 16 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

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

PREHOOK: query: select count(distinct key) from T1
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t1@ds=1
#### A masked pattern was here ####
POSTHOOK: query: select count(distinct key) from T1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t1@ds=1
#### A masked pattern was here ####
5
PREHOOK: query: DROP TABLE T1
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@t1
PREHOOK: Output: default@t1
POSTHOOK: query: DROP TABLE T1
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@t1
POSTHOOK: Output: default@t1