Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx.q.out?rev=1656573&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/ql_rewrite_gbtoidx.q.out Mon Feb 2 21:10:08 2015 @@ -0,0 +1,2730 @@ +PREHOOK: query: DROP TABLE IF EXISTS lineitem_ix +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS lineitem_ix +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE lineitem_ix (L_ORDERKEY INT, + L_PARTKEY INT, + L_SUPPKEY INT, + L_LINENUMBER INT, + L_QUANTITY DOUBLE, + L_EXTENDEDPRICE DOUBLE, + L_DISCOUNT DOUBLE, + L_TAX DOUBLE, + L_RETURNFLAG STRING, + L_LINESTATUS STRING, + l_shipdate STRING, + L_COMMITDATE STRING, + L_RECEIPTDATE STRING, + L_SHIPINSTRUCT STRING, + L_SHIPMODE STRING, + L_COMMENT STRING) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY '|' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@lineitem_ix +POSTHOOK: query: CREATE TABLE lineitem_ix (L_ORDERKEY INT, + L_PARTKEY INT, + L_SUPPKEY INT, + L_LINENUMBER INT, + L_QUANTITY DOUBLE, + L_EXTENDEDPRICE DOUBLE, + L_DISCOUNT DOUBLE, + L_TAX DOUBLE, + L_RETURNFLAG STRING, + L_LINESTATUS STRING, + l_shipdate STRING, + L_COMMITDATE STRING, + L_RECEIPTDATE STRING, + L_SHIPINSTRUCT STRING, + L_SHIPMODE STRING, + L_COMMENT STRING) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY '|' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@lineitem_ix +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/lineitem.txt' OVERWRITE INTO TABLE lineitem_ix +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@lineitem_ix +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/lineitem.txt' OVERWRITE INTO TABLE lineitem_ix +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@lineitem_ix +PREHOOK: query: CREATE INDEX lineitem_ix_lshipdate_idx ON TABLE lineitem_ix(l_shipdate) AS 'org.apache.hadoop.hive.ql.index.AggregateIndexHandler' WITH DEFERRED REBUILD IDXPROPERTIES("AGGREGATES"="count(l_shipdate)") +PREHOOK: type: CREATEINDEX +PREHOOK: Input: default@lineitem_ix +POSTHOOK: query: CREATE INDEX lineitem_ix_lshipdate_idx ON TABLE lineitem_ix(l_shipdate) AS 'org.apache.hadoop.hive.ql.index.AggregateIndexHandler' WITH DEFERRED REBUILD IDXPROPERTIES("AGGREGATES"="count(l_shipdate)") +POSTHOOK: type: CREATEINDEX +POSTHOOK: Input: default@lineitem_ix +POSTHOOK: Output: default@default__lineitem_ix_lineitem_ix_lshipdate_idx__ +PREHOOK: query: ALTER INDEX lineitem_ix_lshipdate_idx ON lineitem_ix REBUILD +PREHOOK: type: ALTERINDEX_REBUILD +PREHOOK: Input: default@lineitem_ix +PREHOOK: Output: default@default__lineitem_ix_lineitem_ix_lshipdate_idx__ +POSTHOOK: query: ALTER INDEX lineitem_ix_lshipdate_idx ON lineitem_ix REBUILD +POSTHOOK: type: ALTERINDEX_REBUILD +POSTHOOK: Input: default@lineitem_ix +POSTHOOK: Output: default@default__lineitem_ix_lineitem_ix_lshipdate_idx__ +POSTHOOK: Lineage: default__lineitem_ix_lineitem_ix_lshipdate_idx__._bucketname SIMPLE [(lineitem_ix)lineitem_ix.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ] +POSTHOOK: Lineage: default__lineitem_ix_lineitem_ix_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem_ix)lineitem_ix.FieldSchema(name:l_shipdate, type:string, comment:null), ] +POSTHOOK: Lineage: default__lineitem_ix_lineitem_ix_lshipdate_idx__._offsets EXPRESSION [(lineitem_ix)lineitem_ix.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ] +POSTHOOK: Lineage: default__lineitem_ix_lineitem_ix_lshipdate_idx__.l_shipdate SIMPLE [(lineitem_ix)lineitem_ix.FieldSchema(name:l_shipdate, type:string, comment:null), ] +PREHOOK: query: explain select l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +PREHOOK: type: QUERY +POSTHOOK: query: explain select l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lineitem_ix + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_shipdate (type: string) + outputColumnNames: l_shipdate + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(l_shipdate) + keys: l_shipdate (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 6049 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 6049 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 6049 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 l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +order by l_shipdate +PREHOOK: type: QUERY +PREHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +POSTHOOK: query: select l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +order by l_shipdate +POSTHOOK: type: QUERY +POSTHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +1992-04-27 1 +1992-07-02 1 +1992-07-10 1 +1992-07-21 1 +1993-04-01 1 +1993-04-13 1 +1993-05-14 1 +1993-10-29 2 +1993-11-09 2 +1993-12-04 1 +1993-12-09 2 +1993-12-14 1 +1994-01-12 1 +1994-01-16 1 +1994-01-26 2 +1994-02-02 1 +1994-02-13 1 +1994-02-19 1 +1994-02-21 1 +1994-03-03 1 +1994-03-17 1 +1994-06-03 1 +1994-06-06 1 +1994-07-02 1 +1994-07-19 1 +1994-07-31 1 +1994-08-08 1 +1994-08-17 1 +1994-08-24 1 +1994-09-30 1 +1994-10-03 1 +1994-10-16 1 +1994-10-31 1 +1994-12-01 1 +1994-12-24 1 +1994-12-30 1 +1995-04-20 1 +1995-07-06 1 +1995-07-17 1 +1995-07-21 1 +1995-08-04 1 +1995-08-07 1 +1995-08-14 1 +1995-08-28 1 +1995-10-23 1 +1995-11-08 1 +1995-11-26 1 +1996-01-10 1 +1996-01-15 1 +1996-01-16 1 +1996-01-19 1 +1996-01-22 1 +1996-01-29 1 +1996-01-30 1 +1996-02-01 2 +1996-02-03 1 +1996-02-10 1 +1996-02-11 1 +1996-02-21 1 +1996-03-13 1 +1996-03-21 1 +1996-03-30 1 +1996-04-12 1 +1996-04-21 1 +1996-05-07 1 +1996-09-26 1 +1996-09-29 1 +1996-10-02 1 +1996-10-17 1 +1996-11-04 1 +1996-11-14 1 +1996-12-08 1 +1997-01-25 1 +1997-01-27 1 +1997-01-28 1 +1997-02-20 1 +1997-03-18 1 +1997-04-17 1 +1997-04-19 1 +1998-01-29 1 +1998-02-23 1 +1998-03-05 1 +1998-04-10 1 +1998-04-12 1 +1998-05-23 1 +1998-06-19 1 +1998-06-24 1 +1998-06-26 1 +1998-06-27 1 +1998-07-04 1 +1998-08-11 1 +1998-08-13 1 +1998-10-09 1 +1998-10-23 1 +1998-10-30 1 +PREHOOK: query: explain select l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +PREHOOK: type: QUERY +POSTHOOK: query: explain select l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: default.default__lineitem_ix_lineitem_ix_lshipdate_idx__ + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) + outputColumnNames: l_shipdate, _count_of_l_shipdate + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_count_of_l_shipdate) + keys: l_shipdate (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 47 Data size: 4432 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 l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +order by l_shipdate +PREHOOK: type: QUERY +PREHOOK: Input: default@default__lineitem_ix_lineitem_ix_lshipdate_idx__ +PREHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +POSTHOOK: query: select l_shipdate, count(l_shipdate) +from lineitem_ix +group by l_shipdate +order by l_shipdate +POSTHOOK: type: QUERY +POSTHOOK: Input: default@default__lineitem_ix_lineitem_ix_lshipdate_idx__ +POSTHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +1992-04-27 1 +1992-07-02 1 +1992-07-10 1 +1992-07-21 1 +1993-04-01 1 +1993-04-13 1 +1993-05-14 1 +1993-10-29 2 +1993-11-09 2 +1993-12-04 1 +1993-12-09 2 +1993-12-14 1 +1994-01-12 1 +1994-01-16 1 +1994-01-26 2 +1994-02-02 1 +1994-02-13 1 +1994-02-19 1 +1994-02-21 1 +1994-03-03 1 +1994-03-17 1 +1994-06-03 1 +1994-06-06 1 +1994-07-02 1 +1994-07-19 1 +1994-07-31 1 +1994-08-08 1 +1994-08-17 1 +1994-08-24 1 +1994-09-30 1 +1994-10-03 1 +1994-10-16 1 +1994-10-31 1 +1994-12-01 1 +1994-12-24 1 +1994-12-30 1 +1995-04-20 1 +1995-07-06 1 +1995-07-17 1 +1995-07-21 1 +1995-08-04 1 +1995-08-07 1 +1995-08-14 1 +1995-08-28 1 +1995-10-23 1 +1995-11-08 1 +1995-11-26 1 +1996-01-10 1 +1996-01-15 1 +1996-01-16 1 +1996-01-19 1 +1996-01-22 1 +1996-01-29 1 +1996-01-30 1 +1996-02-01 2 +1996-02-03 1 +1996-02-10 1 +1996-02-11 1 +1996-02-21 1 +1996-03-13 1 +1996-03-21 1 +1996-03-30 1 +1996-04-12 1 +1996-04-21 1 +1996-05-07 1 +1996-09-26 1 +1996-09-29 1 +1996-10-02 1 +1996-10-17 1 +1996-11-04 1 +1996-11-14 1 +1996-12-08 1 +1997-01-25 1 +1997-01-27 1 +1997-01-28 1 +1997-02-20 1 +1997-03-18 1 +1997-04-17 1 +1997-04-19 1 +1998-01-29 1 +1998-02-23 1 +1998-03-05 1 +1998-04-10 1 +1998-04-12 1 +1998-05-23 1 +1998-06-19 1 +1998-06-24 1 +1998-06-26 1 +1998-06-27 1 +1998-07-04 1 +1998-08-11 1 +1998-08-13 1 +1998-10-09 1 +1998-10-23 1 +1998-10-30 1 +PREHOOK: query: explain select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +PREHOOK: type: QUERY +POSTHOOK: query: explain select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lineitem_ix + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_shipdate (type: string) + outputColumnNames: l_shipdate + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(l_shipdate) + keys: year(l_shipdate) (type: int), month(l_shipdate) (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 120 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 60 Data size: 6049 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Statistics: Num rows: 60 Data size: 6049 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 60 Data size: 6049 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 6049 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 year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +PREHOOK: type: QUERY +PREHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +POSTHOOK: query: select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +POSTHOOK: type: QUERY +POSTHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +1992 4 1 +1992 7 3 +1993 4 2 +1993 5 1 +1993 10 2 +1993 11 2 +1993 12 4 +1994 1 4 +1994 2 4 +1994 3 2 +1994 6 2 +1994 7 3 +1994 8 3 +1994 9 1 +1994 10 3 +1994 12 3 +1995 4 1 +1995 7 3 +1995 8 4 +1995 10 1 +1995 11 2 +1996 1 7 +1996 2 6 +1996 3 3 +1996 4 2 +1996 5 1 +1996 9 2 +1996 10 2 +1996 11 2 +1996 12 1 +1997 1 3 +1997 2 1 +1997 3 1 +1997 4 2 +1998 1 1 +1998 2 1 +1998 3 1 +1998 4 2 +1998 5 1 +1998 6 4 +1998 7 1 +1998 8 2 +1998 10 3 +PREHOOK: query: explain select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +PREHOOK: type: QUERY +POSTHOOK: query: explain select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: default.default__lineitem_ix_lineitem_ix_lshipdate_idx__ + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) + outputColumnNames: l_shipdate, _count_of_l_shipdate + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_count_of_l_shipdate) + keys: year(l_shipdate) (type: int), month(l_shipdate) (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 47 Data size: 4432 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 year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +PREHOOK: type: QUERY +PREHOOK: Input: default@default__lineitem_ix_lineitem_ix_lshipdate_idx__ +PREHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +POSTHOOK: query: select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments +from lineitem_ix +group by year(l_shipdate), month(l_shipdate) +order by year, month +POSTHOOK: type: QUERY +POSTHOOK: Input: default@default__lineitem_ix_lineitem_ix_lshipdate_idx__ +POSTHOOK: Input: default@lineitem_ix +#### A masked pattern was here #### +1992 4 1 +1992 7 3 +1993 4 2 +1993 5 1 +1993 10 2 +1993 11 2 +1993 12 4 +1994 1 4 +1994 2 4 +1994 3 2 +1994 6 2 +1994 7 3 +1994 8 3 +1994 9 1 +1994 10 3 +1994 12 3 +1995 4 1 +1995 7 3 +1995 8 4 +1995 10 1 +1995 11 2 +1996 1 7 +1996 2 6 +1996 3 3 +1996 4 2 +1996 5 1 +1996 9 2 +1996 10 2 +1996 11 2 +1996 12 1 +1997 1 3 +1997 2 1 +1997 3 1 +1997 4 2 +1998 1 1 +1998 2 1 +1998 3 1 +1998 4 2 +1998 5 1 +1998 6 4 +1998 7 1 +1998 8 2 +1998 10 3 +PREHOOK: query: explain select lastyear.month, + thisyear.month, + (thisyear.monthly_shipments - lastyear.monthly_shipments) / +lastyear.monthly_shipments as monthly_shipments_delta + from (select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments + from lineitem_ix + where year(l_shipdate) = 1997 + group by year(l_shipdate), month(l_shipdate) + ) lastyear join + (select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments + from lineitem_ix + where year(l_shipdate) = 1998 + group by year(l_shipdate), month(l_shipdate) + ) thisyear + on lastyear.month = thisyear.month +PREHOOK: type: QUERY +POSTHOOK: query: explain select lastyear.month, + thisyear.month, + (thisyear.monthly_shipments - lastyear.monthly_shipments) / +lastyear.monthly_shipments as monthly_shipments_delta + from (select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments + from lineitem_ix + where year(l_shipdate) = 1997 + group by year(l_shipdate), month(l_shipdate) + ) lastyear join + (select year(l_shipdate) as year, + month(l_shipdate) as month, + count(l_shipdate) as monthly_shipments + from lineitem_ix + where year(l_shipdate) = 1998 + group by year(l_shipdate), month(l_shipdate) + ) thisyear + on lastyear.month = thisyear.month +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) + Reducer 5 <- Map 4 (GROUP, 4) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 4), Reducer 5 (PARTITION-LEVEL SORT, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lastyear:default.default__lineitem_ix_lineitem_ix_lshipdate_idx__ + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (year(l_shipdate) = 1997) (type: boolean) + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) + outputColumnNames: l_shipdate, _count_of_l_shipdate + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_count_of_l_shipdate) + keys: year(l_shipdate) (type: int), month(l_shipdate) (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col1 is not null (type: boolean) + Statistics: Num rows: 24 Data size: 2263 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 24 Data size: 2263 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Map 4 + Map Operator Tree: + TableScan + alias: thisyear:default.default__lineitem_ix_lineitem_ix_lshipdate_idx__ + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (year(l_shipdate) = 1998) (type: boolean) + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) + outputColumnNames: l_shipdate, _count_of_l_shipdate + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_count_of_l_shipdate) + keys: year(l_shipdate) (type: int), month(l_shipdate) (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 47 Data size: 4432 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col1 is not null (type: boolean) + Statistics: Num rows: 24 Data size: 2263 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 24 Data size: 2263 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 1131 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col2 (type: bigint) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 12 Data size: 1131 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 12 Data size: 1131 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col1, _col2, _col4, _col5 + Statistics: Num rows: 13 Data size: 1244 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col4 (type: int), ((_col5 - _col2) / _col2) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13 Data size: 1244 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 1244 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 + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 1131 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col2 (type: bigint) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 12 Data size: 1131 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 12 Data size: 1131 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select l_shipdate, cnt +from (select l_shipdate, count(l_shipdate) as cnt from lineitem_ix group by l_shipdate +union all +select l_shipdate, l_orderkey as cnt +from lineitem_ix) dummy +PREHOOK: type: QUERY +POSTHOOK: query: explain select l_shipdate, cnt +from (select l_shipdate, count(l_shipdate) as cnt from lineitem_ix group by l_shipdate +union all +select l_shipdate, l_orderkey as cnt +from lineitem_ix) dummy +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 3 <- Map 2 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lineitem_ix + Select Operator + expressions: l_shipdate (type: string), UDFToLong(l_orderkey) (type: bigint) + outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + 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 + Map 2 + Map Operator Tree: + TableScan + alias: null-subquery1:dummy-subquery1:default.default__lineitem_ix_lineitem_ix_lshipdate_idx__ + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_shipdate (type: string), _count_of_l_shipdate (type: bigint) + outputColumnNames: l_shipdate, _count_of_l_shipdate + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_count_of_l_shipdate) + keys: l_shipdate (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 95 Data size: 8960 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + 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: CREATE TABLE tbl(key int, value int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl +POSTHOOK: query: CREATE TABLE tbl(key int, value int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl +PREHOOK: query: CREATE INDEX tbl_key_idx ON TABLE tbl(key) AS 'org.apache.hadoop.hive.ql.index.AggregateIndexHandler' WITH DEFERRED REBUILD IDXPROPERTIES("AGGREGATES"="count(key)") +PREHOOK: type: CREATEINDEX +PREHOOK: Input: default@tbl +POSTHOOK: query: CREATE INDEX tbl_key_idx ON TABLE tbl(key) AS 'org.apache.hadoop.hive.ql.index.AggregateIndexHandler' WITH DEFERRED REBUILD IDXPROPERTIES("AGGREGATES"="count(key)") +POSTHOOK: type: CREATEINDEX +POSTHOOK: Input: default@tbl +POSTHOOK: Output: default@default__tbl_tbl_key_idx__ +PREHOOK: query: ALTER INDEX tbl_key_idx ON tbl REBUILD +PREHOOK: type: ALTERINDEX_REBUILD +PREHOOK: Input: default@tbl +PREHOOK: Output: default@default__tbl_tbl_key_idx__ +POSTHOOK: query: ALTER INDEX tbl_key_idx ON tbl REBUILD +POSTHOOK: type: ALTERINDEX_REBUILD +POSTHOOK: Input: default@tbl +POSTHOOK: Output: default@default__tbl_tbl_key_idx__ +POSTHOOK: Lineage: default__tbl_tbl_key_idx__._bucketname SIMPLE [(tbl)tbl.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ] +POSTHOOK: Lineage: default__tbl_tbl_key_idx__._count_of_key EXPRESSION [(tbl)tbl.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: default__tbl_tbl_key_idx__._offsets EXPRESSION [(tbl)tbl.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ] +POSTHOOK: Lineage: default__tbl_tbl_key_idx__.key SIMPLE [(tbl)tbl.FieldSchema(name:key, type:int, comment:null), ] +PREHOOK: query: EXPLAIN select key, count(key) from tbl where key = 1 group by key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key, count(key) from tbl where key = 1 group by key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (key = 1) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: 1 (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count(key) + keys: key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select key, count(key) from tbl group by key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key, count(key) from tbl group by key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: default.default__tbl_tbl_key_idx__ + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), _count_of_key (type: bigint) + outputColumnNames: key, _count_of_key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(_count_of_key) + keys: key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select count(1) from tbl +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(1) from tbl +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + 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: EXPLAIN select count(key) from tbl +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select count(key) from tbl +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: default.default__tbl_tbl_key_idx__ + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), _count_of_key (type: bigint) + outputColumnNames: key, _count_of_key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum(_count_of_key) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 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: EXPLAIN select key FROM tbl GROUP BY key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key FROM tbl GROUP BY key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select key FROM tbl GROUP BY value, key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key FROM tbl GROUP BY value, key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: value (type: int), key (type: int) + outputColumnNames: value, key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: value (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select key FROM tbl WHERE key = 3 GROUP BY key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key FROM tbl WHERE key = 3 GROUP BY key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (key = 3) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: 3 (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select key FROM tbl WHERE value = 2 GROUP BY key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key FROM tbl WHERE value = 2 GROUP BY key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (value = 2) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select key FROM tbl GROUP BY key, substr(key,2,3) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key FROM tbl GROUP BY key, substr(key,2,3) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), substr(key, 2, 3) (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select key, value FROM tbl GROUP BY value, key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key, value FROM tbl GROUP BY value, key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: value (type: int), key (type: int) + outputColumnNames: value, key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: value (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col0 (type: int) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select key, value FROM tbl WHERE value = 1 GROUP BY key, value +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select key, value FROM tbl WHERE value = 1 GROUP BY key, value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (value = 1) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), 1 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), value (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key FROM tbl +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key FROM tbl +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key FROM tbl +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key FROM tbl +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key FROM tbl +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key FROM tbl +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), value (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl WHERE value = 2 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl WHERE value = 2 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (value = 2) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), 2 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), value (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl WHERE value = 2 AND key = 3 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl WHERE value = 2 AND key = 3 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: ((value = 2) and (key = 3)) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: 3 (type: int), 2 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), value (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl WHERE value = key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key, value FROM tbl WHERE value = key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (value = key) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), value (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key, substr(value,2,3) FROM tbl WHERE value = key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key, substr(value,2,3) FROM tbl WHERE value = key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 4) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (value = key) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), substr(value, 2, 3) (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + 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-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select DISTINCT key, substr(value,2,3) FROM tbl +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN select DISTINCT key, substr(value,2,3) FROM tbl +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS:
[... 593 lines stripped ...]
