You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jv...@apache.org on 2011/09/13 04:20:53 UTC
svn commit: r1170007 [3/3] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ data/files/
ql/src/java/org/apache/hadoop/hive/ql/index/
ql/src/java/org/apache/hadoop/hive/ql/index/bitmap/
ql/src/java/org/apache/hadoop/hive/ql/index/compact/ ...
Added: hive/trunk/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx.q.out?rev=1170007&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx.q.out Tue Sep 13 02:20:52 2011
@@ -0,0 +1,4083 @@
+PREHOOK: query: DROP TABLE lineitem
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE lineitem
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE lineitem (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
+POSTHOOK: query: CREATE TABLE lineitem (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: default@lineitem
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/lineitem.txt' OVERWRITE INTO TABLE lineitem
+PREHOOK: type: LOAD
+PREHOOK: Output: default@lineitem
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/lineitem.txt' OVERWRITE INTO TABLE lineitem
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@lineitem
+PREHOOK: query: CREATE INDEX lineitem_lshipdate_idx ON TABLE lineitem(l_shipdate) AS 'org.apache.hadoop.hive.ql.index.AggregateIndexHandler' WITH DEFERRED REBUILD IDXPROPERTIES("AGGREGATES"="count(l_shipdate)")
+PREHOOK: type: CREATEINDEX
+POSTHOOK: query: CREATE INDEX lineitem_lshipdate_idx ON TABLE lineitem(l_shipdate) AS 'org.apache.hadoop.hive.ql.index.AggregateIndexHandler' WITH DEFERRED REBUILD IDXPROPERTIES("AGGREGATES"="count(l_shipdate)")
+POSTHOOK: type: CREATEINDEX
+PREHOOK: query: ALTER INDEX lineitem_lshipdate_idx ON lineitem REBUILD
+PREHOOK: type: ALTERINDEX_REBUILD
+PREHOOK: Input: default@lineitem
+PREHOOK: Output: default@default__lineitem_lineitem_lshipdate_idx__
+POSTHOOK: query: ALTER INDEX lineitem_lshipdate_idx ON lineitem REBUILD
+POSTHOOK: type: ALTERINDEX_REBUILD
+POSTHOOK: Input: default@lineitem
+POSTHOOK: Output: default@default__lineitem_lineitem_lshipdate_idx__
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+PREHOOK: query: explain select l_shipdate, count(l_shipdate)
+from lineitem
+group by l_shipdate
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select l_shipdate, count(l_shipdate)
+from lineitem
+group by l_shipdate
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL l_shipdate)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL l_shipdate)))) (TOK_GROUPBY (TOK_TABLE_OR_COL l_shipdate))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ lineitem
+ TableScan
+ alias: lineitem
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ outputColumnNames: l_shipdate
+ Group By Operator
+ aggregations:
+ expr: count(l_shipdate)
+ bucketGroup: false
+ keys:
+ expr: l_shipdate
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select l_shipdate, count(l_shipdate)
+from lineitem
+group by l_shipdate
+order by l_shipdate
+PREHOOK: type: QUERY
+PREHOOK: Input: default@lineitem
+PREHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-15_607_7496076940735084300/-mr-10000
+POSTHOOK: query: select l_shipdate, count(l_shipdate)
+from lineitem
+group by l_shipdate
+order by l_shipdate
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@lineitem
+POSTHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-15_607_7496076940735084300/-mr-10000
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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
+group by l_shipdate
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select l_shipdate, count(l_shipdate)
+from lineitem
+group by l_shipdate
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL l_shipdate)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL l_shipdate)))) (TOK_GROUPBY (TOK_TABLE_OR_COL l_shipdate))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ default__lineitem_lineitem_lshipdate_idx__
+ TableScan
+ alias: default__lineitem_lineitem_lshipdate_idx__
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ expr: _count_of_l_shipdate
+ type: bigint
+ outputColumnNames: l_shipdate, _count_of_l_shipdate
+ Group By Operator
+ aggregations:
+ expr: sum(_count_of_l_shipdate)
+ bucketGroup: false
+ keys:
+ expr: l_shipdate
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select l_shipdate, count(l_shipdate)
+from lineitem
+group by l_shipdate
+order by l_shipdate
+PREHOOK: type: QUERY
+PREHOOK: Input: default@default__lineitem_lineitem_lshipdate_idx__
+PREHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-22_855_895293760897912959/-mr-10000
+POSTHOOK: query: select l_shipdate, count(l_shipdate)
+from lineitem
+group by l_shipdate
+order by l_shipdate
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@default__lineitem_lineitem_lshipdate_idx__
+POSTHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-22_855_895293760897912959/-mr-10000
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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
+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
+group by year(l_shipdate), month(l_shipdate)
+order by year, month
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) year) (TOK_SELEXPR (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate)) month) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL l_shipdate)) monthly_shipments)) (TOK_GROUPBY (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL year)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL month)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ lineitem
+ TableScan
+ alias: lineitem
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ outputColumnNames: l_shipdate
+ Group By Operator
+ aggregations:
+ expr: count(l_shipdate)
+ bucketGroup: false
+ keys:
+ expr: year(l_shipdate)
+ type: int
+ expr: month(l_shipdate)
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/tmp/pkalmegh/hive_2011-09-09_23-00-30_024_5096135849560451670/-mr-10002
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select year(l_shipdate) as year,
+ month(l_shipdate) as month,
+ count(l_shipdate) as monthly_shipments
+from lineitem
+group by year(l_shipdate), month(l_shipdate)
+order by year, month
+PREHOOK: type: QUERY
+PREHOOK: Input: default@lineitem
+PREHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-30_147_2427796324376692796/-mr-10000
+POSTHOOK: query: select year(l_shipdate) as year,
+ month(l_shipdate) as month,
+ count(l_shipdate) as monthly_shipments
+from lineitem
+group by year(l_shipdate), month(l_shipdate)
+order by year, month
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@lineitem
+POSTHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-30_147_2427796324376692796/-mr-10000
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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
+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
+group by year(l_shipdate), month(l_shipdate)
+order by year, month
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) year) (TOK_SELEXPR (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate)) month) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL l_shipdate)) monthly_shipments)) (TOK_GROUPBY (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL year)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL month)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ default__lineitem_lineitem_lshipdate_idx__
+ TableScan
+ alias: default__lineitem_lineitem_lshipdate_idx__
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ expr: _count_of_l_shipdate
+ type: bigint
+ outputColumnNames: l_shipdate, _count_of_l_shipdate
+ Group By Operator
+ aggregations:
+ expr: sum(_count_of_l_shipdate)
+ bucketGroup: false
+ keys:
+ expr: year(l_shipdate)
+ type: int
+ expr: month(l_shipdate)
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/tmp/pkalmegh/hive_2011-09-09_23-00-38_808_7637699591714847173/-mr-10002
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select year(l_shipdate) as year,
+ month(l_shipdate) as month,
+ count(l_shipdate) as monthly_shipments
+from lineitem
+group by year(l_shipdate), month(l_shipdate)
+order by year, month
+PREHOOK: type: QUERY
+PREHOOK: Input: default@default__lineitem_lineitem_lshipdate_idx__
+PREHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-38_987_3606694174449969948/-mr-10000
+POSTHOOK: query: select year(l_shipdate) as year,
+ month(l_shipdate) as month,
+ count(l_shipdate) as monthly_shipments
+from lineitem
+group by year(l_shipdate), month(l_shipdate)
+order by year, month
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@default__lineitem_lineitem_lshipdate_idx__
+POSTHOOK: Output: file:/tmp/pkalmegh/hive_2011-09-09_23-00-38_987_3606694174449969948/-mr-10000
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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
+ 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
+ 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
+ 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
+ where year(l_shipdate) = 1998
+ group by year(l_shipdate), month(l_shipdate)
+ ) thisyear
+ on lastyear.month = thisyear.month
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) year) (TOK_SELEXPR (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate)) month) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL l_shipdate)) monthly_shipments)) (TOK_WHERE (= (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) 1997)) (TOK_GROUPBY (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate))))) lastyear) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) year) (TOK_SELEXPR (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate)) month) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL l_shipdate)) monthly_shipments)) (TOK_WHERE (= (TOK_FUNCTION year (TO
K_TABLE_OR_COL l_shipdate)) 1998)) (TOK_GROUPBY (TOK_FUNCTION year (TOK_TABLE_OR_COL l_shipdate)) (TOK_FUNCTION month (TOK_TABLE_OR_COL l_shipdate))))) thisyear) (= (. (TOK_TABLE_OR_COL lastyear) month) (. (TOK_TABLE_OR_COL thisyear) month)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL lastyear) month)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL thisyear) month)) (TOK_SELEXPR (/ (- (. (TOK_TABLE_OR_COL thisyear) monthly_shipments) (. (TOK_TABLE_OR_COL lastyear) monthly_shipments)) (. (TOK_TABLE_OR_COL lastyear) monthly_shipments)) monthly_shipments_delta))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-3
+ Stage-3 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ lastyear:default__lineitem_lineitem_lshipdate_idx__
+ TableScan
+ alias: lastyear:default__lineitem_lineitem_lshipdate_idx__
+ Filter Operator
+ predicate:
+ expr: (year(l_shipdate) = 1997)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ expr: _count_of_l_shipdate
+ type: bigint
+ outputColumnNames: l_shipdate, _count_of_l_shipdate
+ Group By Operator
+ aggregations:
+ expr: sum(_count_of_l_shipdate)
+ bucketGroup: false
+ keys:
+ expr: year(l_shipdate)
+ type: int
+ expr: month(l_shipdate)
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col1
+ type: int
+ tag: 0
+ value expressions:
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col1
+ type: int
+ tag: 1
+ value expressions:
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col1} {VALUE._col2}
+ 1 {VALUE._col1} {VALUE._col2}
+ handleSkewJoin: false
+ outputColumnNames: _col1, _col2, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col1
+ type: int
+ expr: _col4
+ type: int
+ expr: ((_col5 - _col2) / _col2)
+ type: double
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ thisyear:default__lineitem_lineitem_lshipdate_idx__
+ TableScan
+ alias: thisyear:default__lineitem_lineitem_lshipdate_idx__
+ Filter Operator
+ predicate:
+ expr: (year(l_shipdate) = 1998)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ expr: _count_of_l_shipdate
+ type: bigint
+ outputColumnNames: l_shipdate, _count_of_l_shipdate
+ Group By Operator
+ aggregations:
+ expr: sum(_count_of_l_shipdate)
+ bucketGroup: false
+ keys:
+ expr: year(l_shipdate)
+ type: int
+ expr: month(l_shipdate)
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: explain select l_shipdate, cnt
+from (select l_shipdate, count(l_shipdate) as cnt from lineitem group by l_shipdate
+union all
+select l_shipdate, l_orderkey as cnt
+from lineitem) dummy
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select l_shipdate, cnt
+from (select l_shipdate, count(l_shipdate) as cnt from lineitem group by l_shipdate
+union all
+select l_shipdate, l_orderkey as cnt
+from lineitem) dummy
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL l_shipdate)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL l_shipdate)) cnt)) (TOK_GROUPBY (TOK_TABLE_OR_COL l_shipdate)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME lineitem))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL l_shipdate)) (TOK_SELEXPR (TOK_TABLE_OR_COL l_orderkey) cnt))))) dummy)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL l_shipdate)) (TOK_SELEXPR (TOK_TABLE_OR_COL cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-3
+ Stage-3 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery1:default__lineitem_lineitem_lshipdate_idx__
+ TableScan
+ alias: null-subquery1:default__lineitem_lineitem_lshipdate_idx__
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ expr: _count_of_l_shipdate
+ type: bigint
+ outputColumnNames: l_shipdate, _count_of_l_shipdate
+ Group By Operator
+ aggregations:
+ expr: sum(_count_of_l_shipdate)
+ bucketGroup: false
+ keys:
+ expr: l_shipdate
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/tmp/pkalmegh/hive_2011-09-09_23-00-46_925_984970650390933497/-mr-10002
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ file:/tmp/pkalmegh/hive_2011-09-09_23-00-46_925_984970650390933497/-mr-10003
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery2:dummy-subquery2:lineitem
+ TableScan
+ alias: lineitem
+ Select Operator
+ expressions:
+ expr: l_shipdate
+ type: string
+ expr: l_orderkey
+ type: int
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: CREATE TABLE tbl(key int, value int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE tbl(key int, value int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@tbl
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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
+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: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL key)))) (TOK_WHERE (= (TOK_TABLE_OR_COL key) 1)) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ default__tbl_tbl_key_idx__
+ TableScan
+ alias: default__tbl_tbl_key_idx__
+ Filter Operator
+ predicate:
+ expr: (key = 1)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ expr: _count_of_key
+ type: bigint
+ outputColumnNames: key, _count_of_key
+ Group By Operator
+ aggregations:
+ expr: sum(_count_of_key)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: 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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL key)))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ default__tbl_tbl_key_idx__
+ TableScan
+ alias: default__tbl_tbl_key_idx__
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ expr: _count_of_key
+ type: bigint
+ outputColumnNames: key, _count_of_key
+ Group By Operator
+ aggregations:
+ expr: sum(_count_of_key)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: EXPLAIN select count(1) from tbl
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN select count(1) from tbl
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: EXPLAIN select count(key) from tbl
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN select count(key) from tbl
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL key))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(key)
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: EXPLAIN select key FROM tbl GROUP BY key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN select key FROM tbl GROUP BY key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: int
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: 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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_GROUPBY (TOK_TABLE_OR_COL value) (TOK_TABLE_OR_COL key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Select Operator
+ expressions:
+ expr: value
+ type: int
+ expr: key
+ type: int
+ outputColumnNames: value, key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: value
+ type: int
+ expr: key
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ tag: -1
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col1
+ type: int
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: 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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_WHERE (= (TOK_TABLE_OR_COL key) 3)) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Filter Operator
+ predicate:
+ expr: (key = 3)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: int
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: 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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_WHERE (= (TOK_TABLE_OR_COL value) 2)) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Filter Operator
+ predicate:
+ expr: (value = 2)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: int
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: 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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) (TOK_FUNCTION substr (TOK_TABLE_OR_COL key) 2 3))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: int
+ expr: substr(key, 2, 3)
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ tag: -1
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: 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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_GROUPBY (TOK_TABLE_OR_COL value) (TOK_TABLE_OR_COL key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Select Operator
+ expressions:
+ expr: value
+ type: int
+ expr: key
+ type: int
+ outputColumnNames: value, key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: value
+ type: int
+ expr: key
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ tag: -1
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col1
+ type: int
+ expr: _col0
+ type: int
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: 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
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._bucketname SIMPLE [(lineitem)lineitem.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._count_of_l_shipdate EXPRESSION [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__._offsets EXPRESSION [(lineitem)lineitem.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ]
+POSTHOOK: Lineage: default__lineitem_lineitem_lshipdate_idx__.l_shipdate SIMPLE [(lineitem)lineitem.FieldSchema(name:l_shipdate, type:string, comment:null), ]
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (= (TOK_TABLE_OR_COL value) 1)) (TOK_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL value))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tbl
+ TableScan
+ alias: tbl
+ Filter Operator
+ predicate:
+ expr: (value = 1)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ expr: value
+ type: int
+ outputColumnNames: key, value
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: int
+ expr: value
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
[... 1990 lines stripped ...]