PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
SKEWED BY (key, val) ON ((2, 12)) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T1
POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
SKEWED BY (key, val) ON ((2, 12)) 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
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
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@t1
PREHOOK: query: CREATE TABLE T2(key STRING, val STRING)
SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T2
POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING)
SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T2
PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@t2
POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@t2
PREHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is
-- skewed by one column. Ths join is performed on the first skewed column
-- The skewed value for the jon key is common to both the tables.
-- In this case, the skewed join value is not repeated in the filter.
-- adding a order by at the end to make the results deterministic

EXPLAIN
SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is
-- skewed by one column. Ths join is performed on the first skewed column
-- The skewed value for the jon key is common to both the tables.
-- In this case, the skewed join value is not repeated in the filter.
-- adding a order by at the end to make the results deterministic

EXPLAIN
SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1, Stage-4
  Stage-4 is a root stage
  Stage-0 depends on stages: Stage-2

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (key is not null and (key = '2')) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string)
                sort order: +
                Map-reduce partition columns: key (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                value expressions: val (type: string)
          TableScan
            alias: b
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (key is not null and (key = '2')) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string)
                sort order: +
                Map-reduce partition columns: key (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                value expressions: val (type: string)
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
          keys:
            0 key (type: string)
            1 key (type: string)
          outputColumnNames: _col0, _col1, _col5, _col6
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
            outputColumnNames: _col0, _col1, _col2, _col3
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-2
    Map Reduce
      Map Operator Tree:
          TableScan
            Union
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              File Output Operator
                compressed: false
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
          TableScan
            Union
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              File Output Operator
                compressed: false
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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-4
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (key is not null and (not (key = '2'))) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string)
                sort order: +
                Map-reduce partition columns: key (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                value expressions: val (type: string)
          TableScan
            alias: b
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (key is not null and (not (key = '2'))) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string)
                sort order: +
                Map-reduce partition columns: key (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                value expressions: val (type: string)
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
          outputColumnNames: _col0, _col1, _col5, _col6
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
            outputColumnNames: _col0, _col1, _col2, _col3
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

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

PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
ORDER BY a.key, b.key, a.val, b.val
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
#### A masked pattern was here ####
POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
ORDER BY a.key, b.key, a.val, b.val
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
#### A masked pattern was here ####
2	12	2	22
3	13	3	13
8	18	8	18
8	18	8	18
8	28	8	18
8	28	8	18
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
PREHOOK: query: DROP TABLE T2
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@t2
PREHOOK: Output: default@t2
POSTHOOK: query: DROP TABLE T2
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@t2
POSTHOOK: Output: default@t2
PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
SKEWED BY (key, val) ON ((2, 12)) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T1
POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
SKEWED BY (key, val) ON ((2, 12)) 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
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
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@t1
PREHOOK: query: CREATE TABLE T2(key STRING, val STRING)
SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T2
POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING)
SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T2
PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@t2
POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@t2
PREHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is
-- skewed by one column. Ths join is performed on the both the columns
-- In this case, the skewed join value is repeated in the filter.

EXPLAIN
SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
PREHOOK: type: QUERY
POSTHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is
-- skewed by one column. Ths join is performed on the both the columns
-- In this case, the skewed join value is repeated in the filter.

EXPLAIN
SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1, Stage-4
  Stage-4 is a root stage
  Stage-0 depends on stages: Stage-2

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string), val (type: string)
                sort order: ++
                Map-reduce partition columns: key (type: string), val (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          TableScan
            alias: b
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string), val (type: string)
                sort order: ++
                Map-reduce partition columns: key (type: string), val (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
          keys:
            0 key (type: string), val (type: string)
            1 key (type: string), val (type: string)
          outputColumnNames: _col0, _col1, _col5, _col6
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
            outputColumnNames: _col0, _col1, _col2, _col3
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-2
    Map Reduce
      Map Operator Tree:
          TableScan
            Union
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              File Output Operator
                compressed: false
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
          TableScan
            Union
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              File Output Operator
                compressed: false
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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-4
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string), val (type: string)
                sort order: ++
                Map-reduce partition columns: key (type: string), val (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          TableScan
            alias: b
            Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Reduce Output Operator
                key expressions: key (type: string), val (type: string)
                sort order: ++
                Map-reduce partition columns: key (type: string), val (type: string)
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
          outputColumnNames: _col0, _col1, _col5, _col6
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
            outputColumnNames: _col0, _col1, _col2, _col3
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

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

PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
ORDER BY a.key, b.key, a.val, b.val
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
#### A masked pattern was here ####
POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
ORDER BY a.key, b.key, a.val, b.val
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
#### A masked pattern was here ####
3	13	3	13
8	18	8	18
8	18	8	18