You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/03/29 05:42:48 UTC
[06/13] hive git commit: HIVE-18770: Additional tests and fixes for
materialized view rewriting (Jesus Camacho Rodriguez,
reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/1b01f9c4/ql/src/test/results/clientpositive/materialized_view_rewrite_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/materialized_view_rewrite_8.q.out b/ql/src/test/results/clientpositive/materialized_view_rewrite_8.q.out
new file mode 100644
index 0000000..1ca06d3
--- /dev/null
+++ b/ql/src/test/results/clientpositive/materialized_view_rewrite_8.q.out
@@ -0,0 +1,642 @@
+PREHOOK: query: create table if not exists source_table_001 (
+MY_DATE date,
+MY_ID bigint,
+MY_ID2 bigint,
+ENVIRONMENT string,
+DOWN_VOLUME bigint,
+UP_VOLUME bigint
+)
+stored AS ORC
+TBLPROPERTIES("transactional"="true")
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@source_table_001
+POSTHOOK: query: create table if not exists source_table_001 (
+MY_DATE date,
+MY_ID bigint,
+MY_ID2 bigint,
+ENVIRONMENT string,
+DOWN_VOLUME bigint,
+UP_VOLUME bigint
+)
+stored AS ORC
+TBLPROPERTIES("transactional"="true")
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@source_table_001
+PREHOOK: query: insert into table source_table_001
+ values ('2010-10-10', 1, 1, 'env', 1, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@source_table_001
+POSTHOOK: query: insert into table source_table_001
+ values ('2010-10-10', 1, 1, 'env', 1, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@source_table_001
+POSTHOOK: Lineage: source_table_001.down_volume SCRIPT []
+POSTHOOK: Lineage: source_table_001.environment SCRIPT []
+POSTHOOK: Lineage: source_table_001.my_date SCRIPT []
+POSTHOOK: Lineage: source_table_001.my_id SCRIPT []
+POSTHOOK: Lineage: source_table_001.my_id2 SCRIPT []
+POSTHOOK: Lineage: source_table_001.up_volume SCRIPT []
+PREHOOK: query: analyze table source_table_001 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@source_table_001
+PREHOOK: Output: default@source_table_001
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table source_table_001 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@source_table_001
+POSTHOOK: Output: default@source_table_001
+#### A masked pattern was here ####
+PREHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv ENABLE REWRITE AS
+SELECT
+SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
+SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+from source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+PREHOOK: type: CREATE_MATERIALIZED_VIEW
+PREHOOK: Input: default@source_table_001
+PREHOOK: Output: database:default
+PREHOOK: Output: default@source_table_001_mv
+POSTHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv ENABLE REWRITE AS
+SELECT
+SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
+SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+from source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+POSTHOOK: type: CREATE_MATERIALIZED_VIEW
+POSTHOOK: Input: default@source_table_001
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@source_table_001_mv
+PREHOOK: query: analyze table source_table_001_mv compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@source_table_001_mv
+PREHOOK: Output: default@source_table_001_mv
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table source_table_001_mv compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@source_table_001_mv
+POSTHOOK: Output: default@source_table_001_mv
+#### A masked pattern was here ####
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint), my_date (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+LIMIT 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+LIMIT 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint), my_date (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: explain
+select
+1,
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+1,
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: 1 (type: int), down_volume_sum (type: bigint), my_date (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 163 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) + 0 AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) + 0 AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: (down_volume_sum + 0L) (type: bigint), my_date (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+ORDER BY A.MY_ID2
+LIMIT 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+ORDER BY A.MY_ID2
+LIMIT 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint), my_date (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col2 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: bigint), _col1 (type: date), _col3 (type: string)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: bigint), VALUE._col1 (type: date), KEY.reducesinkkey0 (type: bigint), VALUE._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+distinct A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+distinct A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: my_date (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: my_date, my_id2, environment
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: my_date (type: date), my_id2 (type: bigint), environment (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: date), _col1 (type: bigint), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: date), _col1 (type: bigint), _col2 (type: string)
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: date), KEY._col1 (type: bigint), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (my_date = DATE'2010-01-10') (type: boolean)
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint), DATE'2010-01-10' (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) + SUM(A.UP_VOLUME) AS TOTAL_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) + SUM(A.UP_VOLUME) AS TOTAL_VOLUME_BYTES,
+A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (my_date = DATE'2010-01-10') (type: boolean)
+ Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: (down_volume_sum + up_volume_sum) (type: bigint), DATE'2010-01-10' (type: date), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 159 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (my_date = DATE'2010-01-10') (type: boolean)
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint)
+ outputColumnNames: down_volume_sum
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(down_volume_sum)
+ 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)
+ 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: 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.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+TO_DATE('2010-01-10')
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+TO_DATE('2010-01-10')
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (my_date = DATE'2010-01-10') (type: boolean)
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint)
+ outputColumnNames: down_volume_sum
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(down_volume_sum)
+ 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)
+ 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: COMPLETE
+ Select Operator
+ expressions: _col0 (type: bigint), DATE'2010-01-10' (type: date)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+group by A.MY_DATE
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+A.MY_DATE
+FROM source_table_001 AS A
+where A.MY_DATE=TO_DATE('2010-01-10')
+group by A.MY_DATE
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (my_date = DATE'2010-01-10') (type: boolean)
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col0)
+ keys: DATE'2010-01-10' (type: date)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: date)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: date)
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: date)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint), DATE'2010-01-10' (type: date)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: drop materialized view source_table_001_mv
+PREHOOK: type: DROP_MATERIALIZED_VIEW
+PREHOOK: Input: default@source_table_001_mv
+PREHOOK: Output: default@source_table_001_mv
+POSTHOOK: query: drop materialized view source_table_001_mv
+POSTHOOK: type: DROP_MATERIALIZED_VIEW
+POSTHOOK: Input: default@source_table_001_mv
+POSTHOOK: Output: default@source_table_001_mv
http://git-wip-us.apache.org/repos/asf/hive/blob/1b01f9c4/ql/src/test/results/clientpositive/materialized_view_rewrite_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/materialized_view_rewrite_9.q.out b/ql/src/test/results/clientpositive/materialized_view_rewrite_9.q.out
new file mode 100644
index 0000000..3120e0d
--- /dev/null
+++ b/ql/src/test/results/clientpositive/materialized_view_rewrite_9.q.out
@@ -0,0 +1,361 @@
+PREHOOK: query: create table if not exists source_table_001 (
+MY_DATE timestamp,
+MY_ID bigint,
+MY_ID2 bigint,
+ENVIRONMENT string,
+DOWN_VOLUME bigint,
+UP_VOLUME bigint
+)
+stored AS ORC
+TBLPROPERTIES("transactional"="true")
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@source_table_001
+POSTHOOK: query: create table if not exists source_table_001 (
+MY_DATE timestamp,
+MY_ID bigint,
+MY_ID2 bigint,
+ENVIRONMENT string,
+DOWN_VOLUME bigint,
+UP_VOLUME bigint
+)
+stored AS ORC
+TBLPROPERTIES("transactional"="true")
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@source_table_001
+PREHOOK: query: insert into table source_table_001
+ values ('2010-10-10 00:00:00', 1, 1, 'env', 1, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@source_table_001
+POSTHOOK: query: insert into table source_table_001
+ values ('2010-10-10 00:00:00', 1, 1, 'env', 1, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@source_table_001
+POSTHOOK: Lineage: source_table_001.down_volume SCRIPT []
+POSTHOOK: Lineage: source_table_001.environment SCRIPT []
+POSTHOOK: Lineage: source_table_001.my_date SCRIPT []
+POSTHOOK: Lineage: source_table_001.my_id SCRIPT []
+POSTHOOK: Lineage: source_table_001.my_id2 SCRIPT []
+POSTHOOK: Lineage: source_table_001.up_volume SCRIPT []
+PREHOOK: query: analyze table source_table_001 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@source_table_001
+PREHOOK: Output: default@source_table_001
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table source_table_001 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@source_table_001
+POSTHOOK: Output: default@source_table_001
+#### A masked pattern was here ####
+PREHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv ENABLE REWRITE AS
+SELECT
+SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
+SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
+A.MY_ID,A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+from source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+PREHOOK: type: CREATE_MATERIALIZED_VIEW
+PREHOOK: Input: default@source_table_001
+PREHOOK: Output: database:default
+PREHOOK: Output: default@source_table_001_mv
+POSTHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv ENABLE REWRITE AS
+SELECT
+SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
+SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
+A.MY_ID,A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
+from source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE
+POSTHOOK: type: CREATE_MATERIALIZED_VIEW
+POSTHOOK: Input: default@source_table_001
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@source_table_001_mv
+PREHOOK: query: analyze table source_table_001_mv compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@source_table_001_mv
+PREHOOK: Output: default@source_table_001_mv
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table source_table_001_mv compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@source_table_001_mv
+POSTHOOK: Output: default@source_table_001_mv
+#### A masked pattern was here ####
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to hour),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to hour)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to hour),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to hour)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint), my_id (type: bigint), my_id2 (type: bigint), environment (type: string), floor_hour(my_date) (type: timestamp)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col0)
+ keys: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: timestamp)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: string), _col3 (type: timestamp)
+ sort order: ++++
+ Map-reduce partition columns: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: string), _col3 (type: timestamp)
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col4 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: bigint), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: timestamp)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col4 (type: bigint), _col3 (type: timestamp), _col1 (type: bigint), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: DROP MATERIALIZED VIEW source_table_001_mv
+PREHOOK: type: DROP_MATERIALIZED_VIEW
+PREHOOK: Input: default@source_table_001_mv
+PREHOOK: Output: default@source_table_001_mv
+POSTHOOK: query: DROP MATERIALIZED VIEW source_table_001_mv
+POSTHOOK: type: DROP_MATERIALIZED_VIEW
+POSTHOOK: Input: default@source_table_001_mv
+POSTHOOK: Output: default@source_table_001_mv
+PREHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv ENABLE REWRITE AS
+SELECT
+SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
+SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
+A.MY_ID,FLOOR(A.MY_DATE to hour),A.MY_ID2,A.ENVIRONMENT
+from source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to hour)
+PREHOOK: type: CREATE_MATERIALIZED_VIEW
+PREHOOK: Input: default@source_table_001
+PREHOOK: Output: database:default
+PREHOOK: Output: default@source_table_001_mv
+POSTHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv ENABLE REWRITE AS
+SELECT
+SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
+SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
+A.MY_ID,FLOOR(A.MY_DATE to hour),A.MY_ID2,A.ENVIRONMENT
+from source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to hour)
+POSTHOOK: type: CREATE_MATERIALIZED_VIEW
+POSTHOOK: Input: default@source_table_001
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@source_table_001_mv
+PREHOOK: query: analyze table source_table_001_mv compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@source_table_001_mv
+PREHOOK: Output: default@source_table_001_mv
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table source_table_001_mv compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@source_table_001_mv
+POSTHOOK: Output: default@source_table_001_mv
+#### A masked pattern was here ####
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to day),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to day)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to day),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to day)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint), my_id (type: bigint), my_id2 (type: bigint), environment (type: string), floor_day(_c3) (type: timestamp)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col0)
+ keys: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: timestamp)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: string), _col3 (type: timestamp)
+ sort order: ++++
+ Map-reduce partition columns: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: string), _col3 (type: timestamp)
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col4 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: bigint), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: timestamp)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col4 (type: bigint), _col3 (type: timestamp), _col1 (type: bigint), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to hour),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to hour)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to hour),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to hour)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: default.source_table_001_mv
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: down_volume_sum (type: bigint), _c3 (type: timestamp), my_id2 (type: bigint), environment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to second),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to second)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
+FLOOR(A.MY_DATE to second),A.MY_ID2,A.ENVIRONMENT
+FROM source_table_001 AS A
+group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to second)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: my_id (type: bigint), my_id2 (type: bigint), environment (type: string), floor_second(my_date) (type: timestamp), down_volume (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col4)
+ keys: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: string), _col3 (type: timestamp)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: string), _col3 (type: timestamp)
+ sort order: ++++
+ Map-reduce partition columns: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: string), _col3 (type: timestamp)
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col4 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: bigint), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: timestamp)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col4 (type: bigint), _col3 (type: timestamp), _col1 (type: bigint), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 143 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: DROP MATERIALIZED VIEW source_table_001_mv
+PREHOOK: type: DROP_MATERIALIZED_VIEW
+PREHOOK: Input: default@source_table_001_mv
+PREHOOK: Output: default@source_table_001_mv
+POSTHOOK: query: DROP MATERIALIZED VIEW source_table_001_mv
+POSTHOOK: type: DROP_MATERIALIZED_VIEW
+POSTHOOK: Input: default@source_table_001_mv
+POSTHOOK: Output: default@source_table_001_mv
http://git-wip-us.apache.org/repos/asf/hive/blob/1b01f9c4/ql/src/test/results/clientpositive/outer_reference_windowed.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/outer_reference_windowed.q.out b/ql/src/test/results/clientpositive/outer_reference_windowed.q.out
index aef80c5..3d918b7 100644
--- a/ql/src/test/results/clientpositive/outer_reference_windowed.q.out
+++ b/ql/src/test/results/clientpositive/outer_reference_windowed.q.out
@@ -578,36 +578,36 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
- alias: e011_03
- Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ alias: e011_01
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: c1 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2))
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ expressions: c1 (type: decimal(15,2))
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: decimal(15,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(15,2))
- Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: decimal(15,2))
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
TableScan
- alias: e011_01
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ alias: e011_03
+ Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: c1 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: c1 (type: decimal(15,2))
- outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: decimal(15,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(15,2))
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(15,2))
Reduce Operator Tree:
Join Operator
condition map:
@@ -616,13 +616,13 @@ STAGE PLANS:
0 _col0 (type: decimal(15,2))
1 _col0 (type: decimal(15,2))
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: sum(_col2)
- keys: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2))
+ aggregations: sum(_col0)
+ keys: _col1 (type: decimal(15,2)), _col2 (type: decimal(15,2))
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -638,7 +638,7 @@ STAGE PLANS:
key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2))
sort order: ++
Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2))
- Statistics: Num rows: 4 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: decimal(25,2))
Reduce Operator Tree:
Group By Operator
@@ -646,7 +646,7 @@ STAGE PLANS:
keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2))
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 19 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -662,13 +662,13 @@ STAGE PLANS:
key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2))
sort order: ++
Map-reduce partition columns: _col1 (type: decimal(15,2))
- Statistics: Num rows: 2 Data size: 19 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: decimal(25,2))
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2))
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 19 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
@@ -688,14 +688,14 @@ STAGE PLANS:
name: sum
window function: GenericUDAFSumHiveDecimal
window frame: RANGE PRECEDING(MAX)~CURRENT
- Statistics: Num rows: 2 Data size: 19 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sum_window_0 (type: decimal(35,2))
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 19 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 19 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -821,41 +821,37 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)), _col2 (type: double)
- outputColumnNames: _col0, _col1, _col2
+ PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: double
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1 ASC NULLS FIRST
+ partition by: _col0
+ raw input shape:
+ window functions:
+ window function definition
+ alias: sum_window_0
+ arguments: _col2
+ name: sum
+ window function: GenericUDAFSumDouble
+ window frame: RANGE PRECEDING(MAX)~CURRENT
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: double
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col0 ASC NULLS FIRST
- partition by: _col1
- raw input shape:
- window functions:
- window function definition
- alias: sum_window_0
- arguments: _col2
- name: sum
- window function: GenericUDAFSumDouble
- window frame: RANGE PRECEDING(MAX)~CURRENT
+ Select Operator
+ expressions: sum_window_0 (type: double)
+ outputColumnNames: _col0
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: sum_window_0 (type: double)
- outputColumnNames: _col0
+ File Output Operator
+ compressed: false
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/1b01f9c4/ql/src/test/results/clientpositive/perf/spark/query12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query12.q.out b/ql/src/test/results/clientpositive/perf/spark/query12.q.out
index 411ad88..af21058 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query12.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query12.q.out
@@ -178,20 +178,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2))
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2))
+ value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2))
Reducer 4
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2))
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
PTF Operator
@@ -203,8 +199,8 @@ STAGE PLANS:
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col3 ASC NULLS FIRST
- partition by: _col3
+ order by: _col1 ASC NULLS FIRST
+ partition by: _col1
raw input shape:
window functions:
window function definition
@@ -215,7 +211,7 @@ STAGE PLANS:
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col0 (type: string)
+ expressions: _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/1b01f9c4/ql/src/test/results/clientpositive/perf/spark/query20.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query20.q.out b/ql/src/test/results/clientpositive/perf/spark/query20.q.out
index 8aa57e1..9097b35 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query20.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query20.q.out
@@ -170,20 +170,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2))
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2))
+ value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2))
Reducer 4
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2))
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
PTF Operator
@@ -195,8 +191,8 @@ STAGE PLANS:
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col3 ASC NULLS FIRST
- partition by: _col3
+ order by: _col1 ASC NULLS FIRST
+ partition by: _col1
raw input shape:
window functions:
window function definition
@@ -207,7 +203,7 @@ STAGE PLANS:
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col0 (type: string)
+ expressions: _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/1b01f9c4/ql/src/test/results/clientpositive/perf/spark/query47.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query47.q.out b/ql/src/test/results/clientpositive/perf/spark/query47.q.out
index a61afcd..5175f80 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query47.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query47.q.out
@@ -415,33 +415,29 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int), _col6 (type: decimal(17,2))
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Reduce Output Operator
+ key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int)
+ sort order: +++++
+ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int)
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int)
- sort order: +++++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int)
- Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col5 (type: int), _col6 (type: decimal(17,2))
+ value expressions: _col1 (type: int), _col6 (type: decimal(17,2))
Reducer 15
Reduce Operator Tree:
Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: decimal(17,2))
+ expressions: KEY.reducesinkkey4 (type: int), VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col1 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
input alias: ptf_0
- output shape: _col0: string, _col1: string, _col2: string, _col3: string, _col4: int, _col5: int, _col6: decimal(17,2)
+ output shape: _col0: int, _col1: int, _col2: string, _col3: string, _col4: string, _col5: string, _col6: decimal(17,2)
type: WINDOWING
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col3 ASC NULLS FIRST, _col4 ASC NULLS FIRST
- partition by: _col0, _col1, _col2, _col3, _col4
+ order by: _col3 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST, _col0 ASC NULLS FIRST
+ partition by: _col3, _col2, _col4, _col5, _col0
raw input shape:
window functions:
window function definition
@@ -452,54 +448,54 @@ STAGE PLANS:
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(17,2))
+ expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2))
outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int)
+ key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int)
sort order: ++++++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string)
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
value expressions: avg_window_0 (type: decimal(21,6)), _col6 (type: decimal(17,2))
Reducer 16
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col0 (type: decimal(21,6)), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), VALUE._col1 (type: decimal(17,2))
+ expressions: VALUE._col0 (type: decimal(21,6)), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col1 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
input alias: ptf_0
- output shape: _col0: decimal(21,6), _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: int, _col7: decimal(17,2)
+ output shape: _col0: decimal(21,6), _col1: int, _col2: int, _col3: string, _col4: string, _col5: string, _col6: string, _col7: decimal(17,2)
type: WINDOWING
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col5 ASC NULLS FIRST, _col6 ASC NULLS FIRST
- partition by: _col1, _col2, _col3, _col4
+ order by: _col1 ASC NULLS FIRST, _col2 ASC NULLS FIRST
+ partition by: _col4, _col3, _col5, _col6
raw input shape:
window functions:
window function definition
alias: rank_window_1
- arguments: _col5, _col6
+ arguments: _col1, _col2
name: rank
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > 0) and (_col5 = 2000) and rank_window_1 is not null) (type: boolean)
+ predicate: ((_col0 > 0) and (_col1 = 2000) and rank_window_1 is not null) (type: boolean)
Statistics: Num rows: 63887519 Data size: 5636175475 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: rank_window_1 (type: int), _col0 (type: decimal(21,6)), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: decimal(17,2))
+ expressions: rank_window_1 (type: int), _col0 (type: decimal(21,6)), _col1 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: decimal(17,2))
outputColumnNames: rank_window_1, _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
Statistics: Num rows: 63887519 Data size: 5636175475 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: CASE WHEN ((_col0 > 0)) THEN (((abs((_col7 - _col0)) / _col0) > 0.1)) ELSE (null) END (type: boolean)
Statistics: Num rows: 31943759 Data size: 2818087693 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: decimal(17,2)), _col0 (type: decimal(21,6)), rank_window_1 (type: int)
+ expressions: _col4 (type: string), _col3 (type: string), _col5 (type: string), _col6 (type: string), _col1 (type: int), _col2 (type: int), _col7 (type: decimal(17,2)), _col0 (type: decimal(21,6)), rank_window_1 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 31943759 Data size: 2818087693 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -582,38 +578,34 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int), _col6 (type: decimal(17,2))
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Reduce Output Operator
+ key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int)
+ sort order: ++++++
+ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string)
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int)
- sort order: ++++++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col6 (type: decimal(17,2))
+ value expressions: _col6 (type: decimal(17,2))
Reducer 24
Reduce Operator Tree:
Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), VALUE._col0 (type: decimal(17,2))
+ expressions: KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
input alias: ptf_0
- output shape: _col0: string, _col1: string, _col2: string, _col3: string, _col4: int, _col5: int, _col6: decimal(17,2)
+ output shape: _col0: int, _col1: int, _col2: string, _col3: string, _col4: string, _col5: string, _col6: decimal(17,2)
type: WINDOWING
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST
- partition by: _col0, _col1, _col2, _col3
+ order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST
+ partition by: _col3, _col2, _col4, _col5
raw input shape:
window functions:
window function definition
alias: rank_window_0
- arguments: _col4, _col5
+ arguments: _col0, _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
@@ -623,7 +615,7 @@ STAGE PLANS:
predicate: rank_window_0 is not null (type: boolean)
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: decimal(17,2)), rank_window_0 (type: int)
+ expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -674,38 +666,34 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int), _col6 (type: decimal(17,2))
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Reduce Output Operator
+ key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int)
+ sort order: ++++++
+ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string)
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int)
- sort order: ++++++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col6 (type: decimal(17,2))
+ value expressions: _col6 (type: decimal(17,2))
Reducer 5
Reduce Operator Tree:
Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), VALUE._col0 (type: decimal(17,2))
+ expressions: KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
input alias: ptf_0
- output shape: _col0: string, _col1: string, _col2: string, _col3: string, _col4: int, _col5: int, _col6: decimal(17,2)
+ output shape: _col0: int, _col1: int, _col2: string, _col3: string, _col4: string, _col5: string, _col6: decimal(17,2)
type: WINDOWING
Windowing table definition
input alias: ptf_1
name: windowingtablefunction
- order by: _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST
- partition by: _col0, _col1, _col2, _col3
+ order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST
+ partition by: _col3, _col2, _col4, _col5
raw input shape:
window functions:
window function definition
alias: rank_window_0
- arguments: _col4, _col5
+ arguments: _col0, _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
@@ -715,7 +703,7 @@ STAGE PLANS:
predicate: rank_window_0 is not null (type: boolean)
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: decimal(17,2)), rank_window_0 (type: int)
+ expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator