You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2015/02/14 21:11:12 UTC
svn commit: r1659857 [5/11] - in /hive/trunk: itests/src/test/resources/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/
ql/src/java/org/apache/hadoop/hive/ql/parse/
ql/src/java/org/apache/hadoop/hive/ql/pla...
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/ptf_matchpath.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/ptf_matchpath.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/ptf_matchpath.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/ptf_matchpath.q.out Sat Feb 14 20:11:11 2015
@@ -37,6 +37,7 @@ POSTHOOK: Output: default@flights_tiny
PREHOOK: query: -- SORT_QUERY_RESULTS
-- 1. basic Matchpath test
+explain
select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
from matchpath(on
flights_tiny
@@ -47,11 +48,10 @@ from matchpath(on
arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
)
PREHOOK: type: QUERY
-PREHOOK: Input: default@flights_tiny
-#### A masked pattern was here ####
POSTHOOK: query: -- SORT_QUERY_RESULTS
-- 1. basic Matchpath test
+explain
select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
from matchpath(on
flights_tiny
@@ -62,6 +62,89 @@ from matchpath(on
arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
)
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: flights_tiny
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int)
+ sort order: ++++
+ Map-reduce partition columns: fl_num (type: string)
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ value expressions: origin_city_name (type: string), dest_city_name (type: string), arr_delay (type: float), BLOCK__OFFSET__INSIDE__FILE (type: bigint), INPUT__FILE__NAME (type: string), ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), VALUE._col2 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: bigint), VALUE._col4 (type: string), VALUE._col5 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Function definitions:
+ Input definition
+ input alias: flights_tiny
+ output shape: _col0: string, _col1: string, _col2: int, _col3: int, _col4: int, _col5: float, _col6: string, _col7: bigint, _col8: string, _col9: struct<transactionid:bigint,bucketid:int,rowid:bigint>
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ arguments: 'LATE.LATE+', 'LATE', (_col5 > 15.0), 'origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath'
+ name: matchpath
+ order by: _col2, _col3, _col4
+ output shape: origin_city_name: string, fl_num: string, year: int, month: int, day_of_month: int, sz: int, tpath: int
+ partition by: _col6
+ raw input shape:
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: origin_city_name (type: string), fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int), sz (type: int), tpath (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
+from matchpath(on
+ flights_tiny
+ distribute by fl_num
+ sort by year, month, day_of_month
+ arg1('LATE.LATE+'),
+ arg2('LATE'), arg3(arr_delay > 15),
+ arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
+ )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@flights_tiny
+#### A masked pattern was here ####
+POSTHOOK: query: select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
+from matchpath(on
+ flights_tiny
+ distribute by fl_num
+ sort by year, month, day_of_month
+ arg1('LATE.LATE+'),
+ arg2('LATE'), arg3(arr_delay > 15),
+ arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
+ )
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@flights_tiny
#### A masked pattern was here ####
Baltimore 1142 2010 10 20 6 20
@@ -81,6 +164,7 @@ Chicago 897 2010 10 21 3 21
Chicago 897 2010 10 22 2 22
Washington 7291 2010 10 27 2 27
PREHOOK: query: -- 2. Matchpath on 1 partition
+explain
select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
from matchpath(on
flights_tiny
@@ -91,9 +175,8 @@ from matchpath(on
)
where fl_num = 1142
PREHOOK: type: QUERY
-PREHOOK: Input: default@flights_tiny
-#### A masked pattern was here ####
POSTHOOK: query: -- 2. Matchpath on 1 partition
+explain
select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
from matchpath(on
flights_tiny
@@ -104,6 +187,92 @@ from matchpath(on
)
where fl_num = 1142
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: flights_tiny
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: 0 (type: int), fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int)
+ sort order: +++++
+ Map-reduce partition columns: 0 (type: int)
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ value expressions: origin_city_name (type: string), dest_city_name (type: string), arr_delay (type: float), BLOCK__OFFSET__INSIDE__FILE (type: bigint), INPUT__FILE__NAME (type: string), ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), VALUE._col2 (type: float), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: bigint), VALUE._col4 (type: string), VALUE._col5 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Function definitions:
+ Input definition
+ input alias: flights_tiny
+ output shape: _col0: string, _col1: string, _col2: int, _col3: int, _col4: int, _col5: float, _col6: string, _col7: bigint, _col8: string, _col9: struct<transactionid:bigint,bucketid:int,rowid:bigint>
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ arguments: 'LATE.LATE+', 'LATE', (_col5 > 15.0), 'origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath'
+ name: matchpath
+ order by: _col6, _col2, _col3, _col4
+ output shape: origin_city_name: string, fl_num: string, year: int, month: int, day_of_month: int, sz: int, tpath: int
+ partition by: 0
+ raw input shape:
+ Statistics: Num rows: 17 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (fl_num = 1142) (type: boolean)
+ Statistics: Num rows: 8 Data size: 2531 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: origin_city_name (type: string), '1142' (type: string), year (type: int), month (type: int), day_of_month (type: int), sz (type: int), tpath (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 8 Data size: 2531 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 8 Data size: 2531 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
+from matchpath(on
+ flights_tiny
+ sort by fl_num, year, month, day_of_month
+ arg1('LATE.LATE+'),
+ arg2('LATE'), arg3(arr_delay > 15),
+ arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
+ )
+where fl_num = 1142
+PREHOOK: type: QUERY
+PREHOOK: Input: default@flights_tiny
+#### A masked pattern was here ####
+POSTHOOK: query: select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
+from matchpath(on
+ flights_tiny
+ sort by fl_num, year, month, day_of_month
+ arg1('LATE.LATE+'),
+ arg2('LATE'), arg3(arr_delay > 15),
+ arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
+ )
+where fl_num = 1142
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@flights_tiny
#### A masked pattern was here ####
Baltimore 1142 2010 10 20 6 20
@@ -112,6 +281,7 @@ Baltimore 1142 2010 10 22 4 22
Baltimore 1142 2010 10 25 3 25
Baltimore 1142 2010 10 26 2 26
PREHOOK: query: -- 3. empty partition.
+explain
select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
from matchpath(on
(select * from flights_tiny where fl_num = -1142) flights_tiny
@@ -121,13 +291,100 @@ from matchpath(on
arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
)
PREHOOK: type: QUERY
-PREHOOK: Input: default@flights_tiny
-#### A masked pattern was here ####
POSTHOOK: query: -- 3. empty partition.
+explain
select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
from matchpath(on
(select * from flights_tiny where fl_num = -1142) flights_tiny
sort by fl_num, year, month, day_of_month
+ arg1('LATE.LATE+'),
+ arg2('LATE'), arg3(arr_delay > 15),
+ arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
+ )
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: flights_tiny
+ Statistics: Num rows: 24 Data size: 5379 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (fl_num = -1142) (type: boolean)
+ Statistics: Num rows: 12 Data size: 2689 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: origin_city_name (type: string), dest_city_name (type: string), year (type: int), month (type: int), day_of_month (type: int), arr_delay (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 12 Data size: 2689 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: 0 (type: int), '-1142' (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: int)
+ sort order: +++++
+ Map-reduce partition columns: 0 (type: int)
+ Statistics: Num rows: 12 Data size: 2689 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col5 (type: float)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), VALUE._col2 (type: float), '-1142' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 12 Data size: 2689 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Function definitions:
+ Input definition
+ input alias: flights_tiny
+ output shape: _col0: string, _col1: string, _col2: int, _col3: int, _col4: int, _col5: float, _col6: string
+ type: SUBQUERY
+ Partition table definition
+ input alias: ptf_1
+ arguments: 'LATE.LATE+', 'LATE', (_col5 > 15.0), 'origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath'
+ name: matchpath
+ order by: _col6, _col2, _col3, _col4
+ output shape: origin_city_name: string, fl_num: string, year: int, month: int, day_of_month: int, sz: int, tpath: int
+ partition by: 0
+ raw input shape:
+ Statistics: Num rows: 12 Data size: 2689 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: origin_city_name (type: string), '-1142' (type: string), year (type: int), month (type: int), day_of_month (type: int), sz (type: int), tpath (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 12 Data size: 2689 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 12 Data size: 2689 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
+from matchpath(on
+ (select * from flights_tiny where fl_num = -1142) flights_tiny
+ sort by fl_num, year, month, day_of_month
+ arg1('LATE.LATE+'),
+ arg2('LATE'), arg3(arr_delay > 15),
+ arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
+ )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@flights_tiny
+#### A masked pattern was here ####
+POSTHOOK: query: select origin_city_name, fl_num, year, month, day_of_month, sz, tpath
+from matchpath(on
+ (select * from flights_tiny where fl_num = -1142) flights_tiny
+ sort by fl_num, year, month, day_of_month
arg1('LATE.LATE+'),
arg2('LATE'), arg3(arr_delay > 15),
arg4('origin_city_name, fl_num, year, month, day_of_month, size(tpath) as sz, tpath[0].day_of_month as tpath')
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out Sat Feb 14 20:11:11 2015
@@ -54,6 +54,18 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -68,6 +80,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col7
+ name: sum
+ window function: GenericUDAFSumDouble
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
@@ -214,6 +258,18 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: j
+ output shape: _col1: string, _col2: string, _col5: int
+ type: SUBQUERY
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -228,6 +284,25 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col5, 1, _col5
+ name: lag
+ window function: GenericUDAFLagEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), (_col5 - _wcol0) (type: int)
@@ -350,6 +425,18 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col0: int, _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: string, _col7: double, _col8: string
+ type: TABLE
+ Partition table definition
+ input alias: abc
+ name: noopstreaming
+ order by: _col1
+ output shape: _col0: int, _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: string, _col7: double, _col8: string
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
@@ -462,7 +549,21 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: p_name: string, p_mfgr: string, p_size: int
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: p_name, p_size(DESC)
+ output shape: p_name: string, p_mfgr: string, p_size: int
+ partition by: p_mfgr
+ raw input shape:
+ transforms raw input: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map-side function: true
Reduce Output Operator
key expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int)
sort order: ++-
@@ -475,6 +576,19 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col1, _col5(DESC)
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int)
@@ -488,6 +602,25 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1, _col5(DESC)
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1, _col5
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int)
@@ -587,7 +720,21 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: p_name: string, p_mfgr: string, p_size: int, p_retailprice: double
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: p_name
+ output shape: p_name: string, p_mfgr: string, p_size: int, p_retailprice: double
+ partition by: p_mfgr
+ raw input shape:
+ transforms raw input: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map-side function: true
Reduce Output Operator
key expressions: p_mfgr (type: string), p_name (type: string)
sort order: ++
@@ -601,6 +748,19 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -615,6 +775,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col7
+ name: sum
+ window function: GenericUDAFSumDouble
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
@@ -733,9 +925,42 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map-side function: true
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
sort order: ++
@@ -749,6 +974,26 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -763,6 +1008,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col7
+ name: sum
+ window function: GenericUDAFSumDouble
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
@@ -883,9 +1160,42 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmap
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map-side function: true
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
sort order: ++
@@ -899,6 +1209,26 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmap
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -913,6 +1243,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col7
+ name: sum
+ window function: GenericUDAFSumDouble
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
@@ -1033,9 +1395,42 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noop
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map-side function: true
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
sort order: ++
@@ -1049,6 +1444,26 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noop
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -1063,6 +1478,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col7
+ name: sum
+ window function: GenericUDAFSumDouble
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
@@ -1200,6 +1647,18 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col5, _col7
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col0: int, _col1: string, _col2: string, _col5: int, _col7: double
+ type: TABLE
+ Partition table definition
+ input alias: abc
+ name: noopstreaming
+ order by: _col1
+ output shape: _col0: int, _col1: string, _col2: string, _col5: int, _col7: double
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
@@ -1233,6 +1692,51 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5, _col7
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int, _col7: double
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col1
+ name: count
+ window function: GenericUDAFCountEvaluator
+ window frame: PRECEDING(MAX)~
+ window function definition
+ alias: _wcol3
+ arguments: _col7
+ name: sum
+ window function: GenericUDAFSumDouble
+ window frame: PRECEDING(MAX)~
+ window function definition
+ alias: _wcol4
+ arguments: _col5, 1, _col5
+ name: lag
+ window function: GenericUDAFLagEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: bigint), _col7 (type: double), _wcol3 (type: double), _col5 (type: int), (_col5 - _wcol4) (type: int)
@@ -1373,9 +1877,49 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col2
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2
+ raw input shape:
+ Partition table definition
+ input alias: ptf_2
+ name: noop
+ order by: _col2
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmap
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map-side function: true
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
sort order: ++
@@ -1389,6 +1933,26 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmap
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
+ transforms raw input: true
+ Partition table definition
+ input alias: ptf_2
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -1403,6 +1967,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col2, _col1
+ partition by: _col2, _col1
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col2, _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col2, _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col5
+ name: sum
+ window function: GenericUDAFSumLong
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint)
@@ -1552,6 +2148,25 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col2
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2
+ raw input shape:
+ Partition table definition
+ input alias: ptf_2
+ name: noop
+ order by: _col2
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -1566,6 +2181,18 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string)
@@ -1580,6 +2207,18 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noop
+ order by: _col2
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -1594,6 +2233,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col5
+ name: sum
+ window function: GenericUDAFSumLong
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint)
@@ -1736,9 +2407,42 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: part
+ output shape: _col1: string, _col2: string, _col5: int
+ type: TABLE
+ Partition table definition
+ input alias: ptf_1
+ name: noopstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
+ Partition table definition
+ input alias: ptf_2
+ name: noop
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
+ transforms raw input: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map-side function: true
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
sort order: ++
@@ -1752,6 +2456,19 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: PTFCOMPONENT
+ Partition table definition
+ input alias: ptf_1
+ name: noopwithmapstreaming
+ order by: _col2, _col1
+ output shape: _col1: string, _col2: string, _col5: int
+ partition by: _col2, _col1
+ raw input shape:
+ transforms raw input: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
@@ -1766,6 +2483,38 @@ STAGE PLANS:
outputColumnNames: _col1, _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col1
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col1
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol1
+ arguments: _col1
+ name: dense_rank
+ window function: GenericUDAFDenseRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ window function definition
+ alias: _wcol2
+ arguments: _col5
+ name: sum
+ window function: GenericUDAFSumLong
+ window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint), _wcol2 (type: bigint)
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/sample10.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/sample10.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/sample10.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/sample10.q.out Sat Feb 14 20:11:11 2015
@@ -102,6 +102,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 4) = 0) (type: boolean)
+ sampleDesc: BUCKET 1 OUT OF 4
Statistics: Num rows: 20 Data size: 120 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ds (type: string)
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/sample2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/sample2.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/sample2.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/sample2.q.out Sat Feb 14 20:11:11 2015
@@ -60,6 +60,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean)
+ sampleDesc: BUCKET 1 OUT OF 2
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/sample4.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/sample4.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/sample4.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/sample4.q.out Sat Feb 14 20:11:11 2015
@@ -62,6 +62,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean)
+ sampleDesc: BUCKET 1 OUT OF 2
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/sample6.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/sample6.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/sample6.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/sample6.q.out Sat Feb 14 20:11:11 2015
@@ -60,6 +60,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 4) = 0) (type: boolean)
+ sampleDesc: BUCKET 1 OUT OF 4
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
@@ -495,6 +496,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 4) = 3) (type: boolean)
+ sampleDesc: BUCKET 4 OUT OF 4
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
@@ -898,6 +900,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean)
+ sampleDesc: BUCKET 1 OUT OF 2
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
@@ -2541,6 +2544,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean)
+ sampleDesc: BUCKET 1 OUT OF 2
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
@@ -2874,6 +2878,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 4) = 1) (type: boolean)
+ sampleDesc: BUCKET 2 OUT OF 4
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/sample9.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/sample9.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/sample9.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/sample9.q.out Sat Feb 14 20:11:11 2015
@@ -58,6 +58,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean)
+ sampleDesc: BUCKET 1 OUT OF 2
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string)
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/smb_mapjoin_11.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/smb_mapjoin_11.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/smb_mapjoin_11.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/smb_mapjoin_11.q.out Sat Feb 14 20:11:11 2015
@@ -1916,6 +1916,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 16) = 1) (type: boolean)
+ sampleDesc: BUCKET 2 OUT OF 16
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string), ds (type: string)
@@ -2007,6 +2008,7 @@ STAGE PLANS:
Filter Operator
isSamplingPred: true
predicate: (((hash(key) & 2147483647) % 16) = 1) (type: boolean)
+ sampleDesc: BUCKET 2 OUT OF 16
Statistics: Num rows: 514 Data size: 5484 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string), ds (type: string)
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/subquery_in.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/subquery_in.q.out?rev=1659857&r1=1659856&r2=1659857&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/subquery_in.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/subquery_in.q.out Sat Feb 14 20:11:11 2015
@@ -314,6 +314,25 @@ STAGE PLANS:
outputColumnNames: _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col5
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col5
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (_wcol0 <= 2) (type: boolean)
@@ -463,6 +482,25 @@ STAGE PLANS:
outputColumnNames: _col2, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col5
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: _wcol0
+ arguments: _col5
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_wcol0 <= 2) and _col2 is not null) (type: boolean)