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 2015/08/10 12:37:54 UTC
[1/3] hive git commit: HIVE-9069: Simplify filter predicates for CBO
(Jesus Camacho Rodriguez, reviewed by Laljo John Pullokkaran)
Repository: hive
Updated Branches:
refs/heads/branch-1 14c5e446d -> e2f1caf39
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainuser_1.q.out b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
index e49f0c8..e689528 100644
--- a/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
@@ -687,157 +687,154 @@ Stage-0
limit:-1
Stage-1
Reducer 6
- File Output Operator [FS_42]
+ File Output Operator [FS_45]
compressed:false
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
- Select Operator [SEL_41]
+ Select Operator [SEL_44]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 5 [SIMPLE_EDGE]
- Reduce Output Operator [RS_40]
+ Reduce Output Operator [RS_43]
key expressions:(UDFToLong(_col0) % _col1) (type: bigint), _col0 (type: int)
sort order:+-
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: bigint), _col2 (type: bigint)
- Group By Operator [GBY_38]
+ Group By Operator [GBY_41]
| aggregations:["count(VALUE._col0)"]
| keys:KEY._col0 (type: int), KEY._col1 (type: bigint)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 4 [SIMPLE_EDGE]
- Reduce Output Operator [RS_37]
+ Reduce Output Operator [RS_40]
key expressions:_col0 (type: int), _col1 (type: bigint)
Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint)
sort order:++
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col2 (type: bigint)
- Group By Operator [GBY_36]
+ Group By Operator [GBY_39]
aggregations:["count()"]
keys:_col0 (type: int), _col1 (type: bigint)
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_34]
+ Select Operator [SEL_35]
outputColumnNames:["_col0","_col1"]
Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_33]
- predicate:(((_col1 > 0) or (_col6 >= 0)) and (((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0))) (type: boolean)
+ Filter Operator [FIL_49]
+ predicate:((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean)
Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_52]
- | condition map:[{"":"Inner Join 0 to 1"}]
+ Merge Join Operator [MERGEJOIN_55]
+ | condition map:[{"":"Left Outer Join0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col6"]
- | Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
+ | Statistics:Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 10 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_31]
+ | Reduce Output Operator [RS_32]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
- | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
+ | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: int)
- | Select Operator [SEL_27]
+ | Select Operator [SEL_30]
| outputColumnNames:["_col0","_col1"]
- | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_50]
- | predicate:((c_int > 0) and key is not null) (type: boolean)
- | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
- | TableScan [TS_25]
- | alias:cbo_t3
- | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
+ | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE
+ | TableScan [TS_29]
+ | alias:cbo_t3
+ | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 3 [SIMPLE_EDGE]
- Reduce Output Operator [RS_29]
+ Reduce Output Operator [RS_31]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint)
- Select Operator [SEL_22]
+ Select Operator [SEL_26]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_47]
+ Filter Operator [FIL_50]
predicate:((_col3 + _col1) >= 0) (type: boolean)
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_51]
+ Merge Join Operator [MERGEJOIN_54]
| condition map:[{"":"Right Outer Join0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col3","_col4"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 2 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_19]
+ | Reduce Output Operator [RS_23]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: int)
- | Select Operator [SEL_7]
+ | Select Operator [SEL_9]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_6]
+ | Group By Operator [GBY_8]
| | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| | outputColumnNames:["_col0","_col1","_col2"]
| | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| |<-Map 1 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_5]
+ | Reduce Output Operator [RS_7]
| key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| sort order:+++
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_4]
+ | Group By Operator [GBY_6]
| keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| Select Operator [SEL_2]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_48]
- | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean)
+ | Filter Operator [FIL_51]
+ | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean)
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_0]
| alias:cbo_t2
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 9 [SIMPLE_EDGE]
- Reduce Output Operator [RS_20]
+ Reduce Output Operator [RS_24]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint)
- Select Operator [SEL_17]
+ Select Operator [SEL_21]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 8 [SIMPLE_EDGE]
- Reduce Output Operator [RS_16]
+ Reduce Output Operator [RS_20]
key expressions:_col3 (type: bigint), _col1 (type: int)
sort order:+-
Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col0 (type: string), _col2 (type: bigint)
- Select Operator [SEL_15]
+ Select Operator [SEL_19]
outputColumnNames:["_col0","_col1","_col2","_col3"]
Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator [GBY_14]
+ Group By Operator [GBY_18]
| aggregations:["sum(VALUE._col0)"]
| keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2","_col3"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 7 [SIMPLE_EDGE]
- Reduce Output Operator [RS_13]
+ Reduce Output Operator [RS_17]
key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
sort order:+++
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col3 (type: bigint)
- Group By Operator [GBY_12]
+ Group By Operator [GBY_16]
aggregations:["sum(_col1)"]
keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
outputColumnNames:["_col0","_col1","_col2","_col3"]
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_10]
+ Select Operator [SEL_12]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_49]
- predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean)
+ Filter Operator [FIL_52]
+ predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean)
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- TableScan [TS_8]
+ TableScan [TS_10]
alias:cbo_t1
Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c
@@ -859,142 +856,142 @@ Stage-0
limit:-1
Stage-1
Reducer 5
- File Output Operator [FS_35]
+ File Output Operator [FS_39]
compressed:false
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
- Group By Operator [GBY_33]
+ Group By Operator [GBY_37]
| aggregations:["count(VALUE._col0)"]
| keys:KEY._col0 (type: int), KEY._col1 (type: bigint)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 4 [SIMPLE_EDGE]
- Reduce Output Operator [RS_32]
+ Reduce Output Operator [RS_36]
key expressions:_col0 (type: int), _col1 (type: bigint)
Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint)
sort order:++
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col2 (type: bigint)
- Group By Operator [GBY_31]
+ Group By Operator [GBY_35]
aggregations:["count()"]
keys:_col0 (type: int), _col1 (type: bigint)
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_29]
+ Select Operator [SEL_33]
outputColumnNames:["_col0","_col1"]
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_39]
+ Filter Operator [FIL_43]
predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean)
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_44]
+ Merge Join Operator [MERGEJOIN_48]
| condition map:[{"":"Right Outer Join0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col4","_col6"]
| Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 9 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_26]
+ | Reduce Output Operator [RS_30]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: int)
- | Select Operator [SEL_24]
+ | Select Operator [SEL_28]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE
- | TableScan [TS_23]
+ | TableScan [TS_27]
| alias:cbo_t3
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 3 [SIMPLE_EDGE]
- Reduce Output Operator [RS_25]
+ Reduce Output Operator [RS_29]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint), _col4 (type: int)
- Select Operator [SEL_22]
+ Select Operator [SEL_26]
outputColumnNames:["_col0","_col1","_col2","_col4"]
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_43]
+ Merge Join Operator [MERGEJOIN_47]
| condition map:[{"":"Left Outer Join0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col3","_col4"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 2 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_19]
+ | Reduce Output Operator [RS_23]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: int)
- | Select Operator [SEL_7]
+ | Select Operator [SEL_9]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_6]
+ | Group By Operator [GBY_8]
| | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| | outputColumnNames:["_col0","_col1","_col2"]
| | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| |<-Map 1 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_5]
+ | Reduce Output Operator [RS_7]
| key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| sort order:+++
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_4]
+ | Group By Operator [GBY_6]
| keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| Select Operator [SEL_2]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_41]
+ | Filter Operator [FIL_45]
| predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean)
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_0]
| alias:cbo_t2
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 8 [SIMPLE_EDGE]
- Reduce Output Operator [RS_20]
+ Reduce Output Operator [RS_24]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint)
- Select Operator [SEL_17]
+ Select Operator [SEL_21]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 7 [SIMPLE_EDGE]
- Reduce Output Operator [RS_16]
+ Reduce Output Operator [RS_20]
key expressions:_col3 (type: bigint), _col0 (type: string)
sort order:+-
Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint)
- Select Operator [SEL_15]
+ Select Operator [SEL_19]
outputColumnNames:["_col0","_col1","_col2","_col3"]
Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator [GBY_14]
+ Group By Operator [GBY_18]
| aggregations:["sum(VALUE._col0)"]
| keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2","_col3"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 6 [SIMPLE_EDGE]
- Reduce Output Operator [RS_13]
+ Reduce Output Operator [RS_17]
key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
sort order:+++
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col3 (type: bigint)
- Group By Operator [GBY_12]
+ Group By Operator [GBY_16]
aggregations:["sum(_col1)"]
keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
outputColumnNames:["_col0","_col1","_col2","_col3"]
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_10]
+ Select Operator [SEL_12]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_42]
+ Filter Operator [FIL_46]
predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean)
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- TableScan [TS_8]
+ TableScan [TS_10]
alias:cbo_t1
Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int
@@ -1018,155 +1015,152 @@ Stage-0
limit:-1
Stage-1
Reducer 7
- File Output Operator [FS_41]
+ File Output Operator [FS_46]
compressed:false
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
- Select Operator [SEL_40]
+ Select Operator [SEL_45]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 6 [SIMPLE_EDGE]
- Reduce Output Operator [RS_39]
+ Reduce Output Operator [RS_44]
key expressions:_col0 (type: int)
sort order:+
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: bigint), _col2 (type: bigint)
- Group By Operator [GBY_37]
+ Group By Operator [GBY_42]
| aggregations:["count(VALUE._col0)"]
| keys:KEY._col0 (type: int), KEY._col1 (type: bigint)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 5 [SIMPLE_EDGE]
- Reduce Output Operator [RS_36]
+ Reduce Output Operator [RS_41]
key expressions:_col0 (type: int), _col1 (type: bigint)
Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint)
sort order:++
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col2 (type: bigint)
- Group By Operator [GBY_35]
+ Group By Operator [GBY_40]
aggregations:["count()"]
keys:_col0 (type: int), _col1 (type: bigint)
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_33]
+ Select Operator [SEL_36]
outputColumnNames:["_col0","_col1"]
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_44]
- predicate:(((((_col1 + _col4) >= 0) and ((_col1 > 0) or (_col6 >= 0))) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) (type: boolean)
+ Filter Operator [FIL_48]
+ predicate:(((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 + _col4) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean)
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_50]
- | condition map:[{"":"Right Outer Join0 to 1"}]
+ Merge Join Operator [MERGEJOIN_52]
+ | condition map:[{"":"Outer Join 0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col4","_col6"]
- | Statistics:Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE
+ | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 11 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_30]
+ | Reduce Output Operator [RS_33]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
- | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
+ | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: int)
- | Select Operator [SEL_28]
+ | Select Operator [SEL_31]
| outputColumnNames:["_col0","_col1"]
- | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_48]
- | predicate:(c_int > 0) (type: boolean)
- | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
- | TableScan [TS_26]
- | alias:cbo_t3
- | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
+ | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE
+ | TableScan [TS_30]
+ | alias:cbo_t3
+ | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 4 [SIMPLE_EDGE]
- Reduce Output Operator [RS_29]
+ Reduce Output Operator [RS_32]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint), _col4 (type: int)
- Select Operator [SEL_25]
+ Select Operator [SEL_29]
outputColumnNames:["_col0","_col1","_col2","_col4"]
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_49]
+ Merge Join Operator [MERGEJOIN_51]
| condition map:[{"":"Outer Join 0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col3","_col4"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 10 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_23]
+ | Reduce Output Operator [RS_27]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: int), _col2 (type: bigint)
- | Select Operator [SEL_20]
+ | Select Operator [SEL_24]
| | outputColumnNames:["_col0","_col1","_col2"]
| | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
| |<-Reducer 9 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_19]
+ | Reduce Output Operator [RS_23]
| key expressions:_col3 (type: double)
| sort order:-
| Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: bigint)
- | Select Operator [SEL_18]
+ | Select Operator [SEL_22]
| outputColumnNames:["_col0","_col1","_col2","_col3"]
| Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_17]
+ | Group By Operator [GBY_21]
| | aggregations:["sum(VALUE._col0)"]
| | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| | outputColumnNames:["_col0","_col1","_col2","_col3"]
| | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
| |<-Map 8 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_16]
+ | Reduce Output Operator [RS_20]
| key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| sort order:+++
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col3 (type: bigint)
- | Group By Operator [GBY_15]
+ | Group By Operator [GBY_19]
| aggregations:["sum(_col1)"]
| keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2","_col3"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- | Select Operator [SEL_13]
+ | Select Operator [SEL_15]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_47]
+ | Filter Operator [FIL_50]
| predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean)
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | TableScan [TS_11]
+ | TableScan [TS_13]
| alias:cbo_t1
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 3 [SIMPLE_EDGE]
- Reduce Output Operator [RS_22]
+ Reduce Output Operator [RS_26]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int)
- Select Operator [SEL_9]
+ Select Operator [SEL_11]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 2 [SIMPLE_EDGE]
- Reduce Output Operator [RS_8]
+ Reduce Output Operator [RS_10]
key expressions:_col3 (type: double), _col2 (type: bigint)
sort order:-+
Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col0 (type: string), _col1 (type: int)
- Select Operator [SEL_7]
+ Select Operator [SEL_9]
outputColumnNames:["_col0","_col1","_col2","_col3"]
Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator [GBY_6]
+ Group By Operator [GBY_8]
| aggregations:["sum(VALUE._col0)"]
| keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2","_col3"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 1 [SIMPLE_EDGE]
- Reduce Output Operator [RS_5]
+ Reduce Output Operator [RS_7]
key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
sort order:+++
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col3 (type: bigint)
- Group By Operator [GBY_4]
+ Group By Operator [GBY_6]
aggregations:["sum(_col1)"]
keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
outputColumnNames:["_col0","_col1","_col2","_col3"]
@@ -1174,7 +1168,7 @@ Stage-0
Select Operator [SEL_2]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_46]
+ Filter Operator [FIL_49]
predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean)
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
TableScan [TS_0]
@@ -1198,40 +1192,40 @@ Stage-0
limit:-1
Stage-1
Reducer 3
- File Output Operator [FS_39]
+ File Output Operator [FS_43]
compressed:false
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
- Group By Operator [GBY_37]
+ Group By Operator [GBY_41]
| aggregations:["count(VALUE._col0)"]
| keys:KEY._col0 (type: int), KEY._col1 (type: bigint)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 2 [SIMPLE_EDGE]
- Reduce Output Operator [RS_36]
+ Reduce Output Operator [RS_40]
key expressions:_col0 (type: int), _col1 (type: bigint)
Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint)
sort order:++
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col2 (type: bigint)
- Group By Operator [GBY_35]
+ Group By Operator [GBY_39]
aggregations:["count()"]
keys:_col0 (type: int), _col1 (type: bigint)
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_31]
+ Select Operator [SEL_35]
outputColumnNames:["_col0","_col1"]
Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_45]
+ Filter Operator [FIL_49]
predicate:((_col3 > 0) or (_col1 >= 0)) (type: boolean)
Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_51]
+ Merge Join Operator [MERGEJOIN_55]
| condition map:[{"":"Inner Join 0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col3","_col4"]
| Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 1 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_27]
+ | Reduce Output Operator [RS_31]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
@@ -1240,97 +1234,97 @@ Stage-0
| Select Operator [SEL_1]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_46]
+ | Filter Operator [FIL_50]
| predicate:key is not null (type: boolean)
| Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_0]
| alias:cbo_t3
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 6 [SIMPLE_EDGE]
- Reduce Output Operator [RS_29]
+ Reduce Output Operator [RS_33]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint)
- Select Operator [SEL_23]
+ Select Operator [SEL_27]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_47]
+ Filter Operator [FIL_51]
predicate:((_col3 + _col1) >= 0) (type: boolean)
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_50]
+ Merge Join Operator [MERGEJOIN_54]
| condition map:[{"":"Inner Join 0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col3","_col4"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 5 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_19]
+ | Reduce Output Operator [RS_23]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: int)
- | Select Operator [SEL_9]
+ | Select Operator [SEL_11]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_8]
+ | Group By Operator [GBY_10]
| | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| | outputColumnNames:["_col0","_col1","_col2"]
| | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| |<-Map 4 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_7]
+ | Reduce Output Operator [RS_9]
| key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| sort order:+++
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_6]
+ | Group By Operator [GBY_8]
| keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| Select Operator [SEL_4]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_48]
+ | Filter Operator [FIL_52]
| predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean)
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_2]
| alias:cbo_t2
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 8 [SIMPLE_EDGE]
- Reduce Output Operator [RS_21]
+ Reduce Output Operator [RS_25]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: bigint)
- Select Operator [SEL_17]
+ Select Operator [SEL_21]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator [GBY_16]
+ Group By Operator [GBY_20]
| aggregations:["sum(VALUE._col0)"]
| keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string)
| outputColumnNames:["_col0","_col1","_col2","_col3"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 7 [SIMPLE_EDGE]
- Reduce Output Operator [RS_15]
+ Reduce Output Operator [RS_19]
key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string)
Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string)
sort order:+++
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col3 (type: bigint)
- Group By Operator [GBY_14]
+ Group By Operator [GBY_18]
aggregations:["sum(_col1)"]
keys:_col0 (type: float), _col1 (type: int), _col2 (type: string)
outputColumnNames:["_col0","_col1","_col2","_col3"]
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_12]
+ Select Operator [SEL_14]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_49]
+ Filter Operator [FIL_53]
predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean)
Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
- TableScan [TS_10]
+ TableScan [TS_12]
alias:cbo_t1
Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
PREHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc
@@ -1952,17 +1946,17 @@ Stage-0
limit:-1
Stage-1
Reducer 3
- File Output Operator [FS_20]
+ File Output Operator [FS_22]
compressed:false
- Statistics:Num rows: 8 Data size: 808 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics:Num rows: 4 Data size: 404 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
Select Operator [SEL_19]
outputColumnNames:["_col0","_col1","_col2","_col3","_col4"]
- Statistics:Num rows: 8 Data size: 808 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics:Num rows: 4 Data size: 404 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator [FIL_18]
- predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean)
- Statistics:Num rows: 8 Data size: 808 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_29]
+ predicate:(((_col4 + 1) = 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean)
+ Statistics:Num rows: 4 Data size: 404 Basic stats: COMPLETE Column stats: COMPLETE
+ Merge Join Operator [MERGEJOIN_32]
| condition map:[{"":"Inner Join 0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col3","_col4","_col6"]
@@ -1977,7 +1971,7 @@ Stage-0
| Select Operator [SEL_12]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_27]
+ | Filter Operator [FIL_30]
| predicate:key is not null (type: boolean)
| Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_11]
@@ -1990,10 +1984,10 @@ Stage-0
sort order:+
Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int)
- Filter Operator [FIL_24]
- predicate:((((_col1 + _col4) = 2) and ((_col4 + 1) = 2)) and _col0 is not null) (type: boolean)
+ Filter Operator [FIL_27]
+ predicate:((((_col1 + _col4) = 2) and _col0 is not null) and ((_col4 + 1) = 2)) (type: boolean)
Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_28]
+ Merge Join Operator [MERGEJOIN_31]
| condition map:[{"":"Outer Join 0 to 1"}]
| keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col0","_col1","_col2","_col3","_col4"]
@@ -2008,7 +2002,7 @@ Stage-0
| Select Operator [SEL_2]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_25]
+ | Filter Operator [FIL_28]
| predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean)
| Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_0]
@@ -2024,7 +2018,7 @@ Stage-0
Select Operator [SEL_5]
outputColumnNames:["_col0","_col1"]
Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_26]
+ Filter Operator [FIL_29]
predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean)
Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
TableScan [TS_3]
@@ -2044,17 +2038,17 @@ Stage-0
limit:-1
Stage-1
Reducer 2
- File Output Operator [FS_14]
+ File Output Operator [FS_16]
compressed:false
Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
Select Operator [SEL_13]
outputColumnNames:["_col0","_col1","_col2","_col3","_col4"]
Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_17]
- predicate:((((_col1 + _col4) = 2) and ((_col1 > 0) or (_col6 >= 0))) and ((_col4 + 1) = 2)) (type: boolean)
+ Filter Operator [FIL_20]
+ predicate:((((_col4 + 1) = 2) and ((_col1 > 0) or (_col6 >= 0))) and ((_col1 + _col4) = 2)) (type: boolean)
Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_20]
+ Merge Join Operator [MERGEJOIN_23]
| condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}]
| keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col1","_col2","_col3","_col4","_col6"]
@@ -2069,7 +2063,7 @@ Stage-0
| Select Operator [SEL_2]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_18]
+ | Filter Operator [FIL_21]
| predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean)
| Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_0]
@@ -2085,7 +2079,7 @@ Stage-0
| Select Operator [SEL_5]
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_19]
+ | Filter Operator [FIL_22]
| predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean)
| Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_3]
@@ -2633,20 +2627,20 @@ Stage-0
limit:-1
Stage-1
Reducer 2
- File Output Operator [FS_20]
+ File Output Operator [FS_24]
compressed:false
Statistics:Num rows: 12 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
- Select Operator [SEL_19]
+ Select Operator [SEL_23]
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 12 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_30]
+ Merge Join Operator [MERGEJOIN_34]
| condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}]
| keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 12 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 1 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_13]
+ | Reduce Output Operator [RS_17]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
@@ -2655,48 +2649,48 @@ Stage-0
| Select Operator [SEL_2]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_27]
+ | Filter Operator [FIL_31]
| predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean)
| Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
| TableScan [TS_0]
| alias:cbo_t1
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 3 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_15]
+ | Reduce Output Operator [RS_19]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_9]
+ | Group By Operator [GBY_13]
| keys:_col0 (type: string)
| outputColumnNames:["_col0"]
| Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE
- | Select Operator [SEL_5]
+ | Select Operator [SEL_9]
| outputColumnNames:["_col0"]
| Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_28]
+ | Filter Operator [FIL_32]
| predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean)
| Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
- | TableScan [TS_3]
+ | TableScan [TS_7]
| alias:cbo_t2
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 4 [SIMPLE_EDGE]
- Reduce Output Operator [RS_17]
+ Reduce Output Operator [RS_21]
key expressions:_col0 (type: string)
Map-reduce partition columns:_col0 (type: string)
sort order:+
Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator [GBY_11]
+ Group By Operator [GBY_15]
keys:_col0 (type: string)
outputColumnNames:["_col0"]
Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator [SEL_7]
+ Select Operator [SEL_11]
outputColumnNames:["_col0"]
Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator [FIL_29]
+ Filter Operator [FIL_33]
predicate:key is not null (type: boolean)
Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE
- TableScan [TS_6]
+ TableScan [TS_10]
alias:cbo_t3
Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
PREHOOK: query: explain select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a
@@ -2719,98 +2713,98 @@ Stage-0
limit:-1
Stage-1
Reducer 6
- File Output Operator [FS_44]
+ File Output Operator [FS_50]
compressed:false
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}
- Select Operator [SEL_43]
+ Select Operator [SEL_49]
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 5 [SIMPLE_EDGE]
- Reduce Output Operator [RS_42]
+ Reduce Output Operator [RS_48]
key expressions:_col1 (type: bigint), _col0 (type: string)
sort order:++
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col2 (type: bigint)
- Group By Operator [GBY_40]
+ Group By Operator [GBY_46]
| aggregations:["count(VALUE._col0)"]
| keys:KEY._col0 (type: string), KEY._col1 (type: bigint)
| outputColumnNames:["_col0","_col1","_col2"]
| Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 4 [SIMPLE_EDGE]
- Reduce Output Operator [RS_39]
+ Reduce Output Operator [RS_45]
key expressions:_col0 (type: string), _col1 (type: bigint)
Map-reduce partition columns:_col0 (type: string), _col1 (type: bigint)
sort order:++
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
value expressions:_col2 (type: bigint)
- Group By Operator [GBY_38]
+ Group By Operator [GBY_44]
aggregations:["count()"]
keys:_col0 (type: string), _col1 (type: bigint)
outputColumnNames:["_col0","_col1","_col2"]
Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE
- Merge Join Operator [MERGEJOIN_56]
+ Merge Join Operator [MERGEJOIN_62]
| condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}]
| keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"}
| outputColumnNames:["_col0","_col1"]
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
|<-Map 10 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_35]
+ | Reduce Output Operator [RS_41]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE
- | Group By Operator [GBY_29]
+ | Group By Operator [GBY_35]
| keys:_col0 (type: string)
| outputColumnNames:["_col0"]
| Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE
- | Select Operator [SEL_25]
+ | Select Operator [SEL_31]
| outputColumnNames:["_col0"]
| Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE
- | Filter Operator [FIL_55]
+ | Filter Operator [FIL_61]
| predicate:key is not null (type: boolean)
| Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE
- | TableScan [TS_24]
+ | TableScan [TS_30]
| alias:cbo_t3
| Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE
|<-Reducer 3 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_31]
+ | Reduce Output Operator [RS_37]
| key expressions:_col0 (type: string)
| Map-reduce partition columns:_col0 (type: string)
| sort order:+
| Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| value expressions:_col1 (type: bigint)
- | Select Operator [SEL_9]
+ | Select Operator [SEL_11]
| | outputColumnNames:["_col0","_col1"]
| | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
| |<-Reducer 2 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_8]
+ | Reduce Output Operator [RS_10]
| key expressions:_col3 (type: double), _col2 (type: bigint)
| sort order:-+
| Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
<TRUNCATED>
[2/3] hive git commit: HIVE-9069: Simplify filter predicates for CBO
(Jesus Camacho Rodriguez, reviewed by Laljo John Pullokkaran)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_udf_col.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_udf_col.q.out b/ql/src/test/results/clientpositive/ppd_udf_col.q.out
index 8f064c0..7c963fb 100644
--- a/ql/src/test/results/clientpositive/ppd_udf_col.q.out
+++ b/ql/src/test/results/clientpositive/ppd_udf_col.q.out
@@ -20,19 +20,24 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) = 100.0) and (rand() <= 0.1)) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ predicate: (UDFToDouble(key) = 100.0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: '100' (type: string), rand() (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (rand() <= 0.1) (type: boolean)
Statistics: Num rows: 83 Data size: 881 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
+ Select Operator
+ expressions: '100' (type: string), rand() (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 83 Data size: 881 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
@@ -66,22 +71,30 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) = 100.0) and ((rand() <= 0.1) and (rand() > 0.1))) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ predicate: (UDFToDouble(key) = 100.0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: '100' (type: string), rand() (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 20
- Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 20 Data size: 200 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
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (rand() <= 0.1) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (rand() > 0.1) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '100' (type: string), rand() (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 200 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
@@ -113,17 +126,20 @@ STAGE PLANS:
Filter Operator
predicate: false (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
- Select Operator
- expressions: '100' (type: string), rand() (type: double), '4' (type: string)
- outputColumnNames: _col0, _col1, _col2
+ Filter Operator
+ predicate: false (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
- File Output Operator
- compressed: false
+ Select Operator
+ expressions: '100' (type: string), rand() (type: double), '4' (type: string)
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -153,19 +169,26 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((UDFToDouble(value) * 10.0) <= 200.0) and (UDFToDouble(key) = 100.0)) (type: boolean)
+ predicate: ((UDFToDouble(key) = 100.0) and ((UDFToDouble(value) * 10.0) <= 200.0)) (type: boolean)
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: '100' (type: string), rand() (type: double), (UDFToDouble(value) * 10.0) (type: double)
- outputColumnNames: _col0, _col1, _col2
+ expressions: value (type: string)
+ outputColumnNames: _col1
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 83 Data size: 881 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
+ Filter Operator
+ predicate: ((UDFToDouble(_col1) * 10.0) <= 200.0) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '100' (type: string), rand() (type: double), (UDFToDouble(_col1) * 10.0) (type: double)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 27 Data size: 286 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
@@ -195,19 +218,24 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) = 100.0) and (rand() <= 0.1)) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ predicate: (UDFToDouble(key) = 100.0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: '100' (type: string), rand() (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (rand() <= 0.1) (type: boolean)
Statistics: Num rows: 83 Data size: 881 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
+ Select Operator
+ expressions: '100' (type: string), rand() (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 83 Data size: 881 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
@@ -241,22 +269,30 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) = 100.0) and ((rand() <= 0.1) and (rand() > 0.1))) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ predicate: (UDFToDouble(key) = 100.0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: '100' (type: string), rand() (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 20
- Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 20 Data size: 200 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
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (rand() <= 0.1) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (rand() > 0.1) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '100' (type: string), rand() (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 200 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
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_union.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_union.q.out b/ql/src/test/results/clientpositive/ppd_union.q.out
index 4b0c6a4..166eff1 100644
--- a/ql/src/test/results/clientpositive/ppd_union.q.out
+++ b/ql/src/test/results/clientpositive/ppd_union.q.out
@@ -34,15 +34,18 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- Union
- Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 36 Data size: 382 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
+ Filter Operator
+ predicate: ((_col0 > '4') and (_col1 > 'val_4')) (type: boolean)
+ Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Union
+ Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 4 Data size: 42 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
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -53,15 +56,18 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- Union
- Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 36 Data size: 382 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
+ Filter Operator
+ predicate: ((_col0 > '4') and (_col1 > 'val_4')) (type: boolean)
+ Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Union
+ Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 4 Data size: 42 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
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_vc.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_vc.q.out b/ql/src/test/results/clientpositive/ppd_vc.q.out
index f058526..a16058c 100644
--- a/ql/src/test/results/clientpositive/ppd_vc.q.out
+++ b/ql/src/test/results/clientpositive/ppd_vc.q.out
@@ -680,10 +680,10 @@ STAGE PLANS:
name: default.srcpart
Truncated Path -> Alias:
/src [$hdt$_0:a]
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:srcpart]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:srcpart]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:srcpart]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:$hdt$_1:srcpart]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join2.q.out b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
index dd4d129..cf81423 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
@@ -47,17 +47,24 @@ STAGE PLANS:
predicate: (((key <> '306') and (sqrt(key) <> 13.0)) and value is not null) (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ predicate: (sqrt(_col0) <> 13.0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
Map 3
Map Operator Tree:
TableScan
@@ -71,17 +78,20 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '302') and ((_col0 <> '311') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '14') (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ predicate: ((_col0 <> '302') and ((_col0 <> '311') and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Map 5
Map Operator Tree:
TableScan
@@ -95,17 +105,20 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean)
- Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 <> '311') and (((_col1 <> 'val_50') or (_col0 > '1')) and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean)
+ Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -136,26 +149,26 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col1 is not null (type: boolean)
- Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col3 (type: string)
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
index c93994c..d2343c4 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
@@ -51,16 +51,19 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '11') and ((_col0 > '0') and ((_col0 < '400') and ((_col0 <> '12') and (_col0 <> '4'))))) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '1') (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ predicate: ((_col0 <> '11') and ((_col0 > '0') and ((_col0 < '400') and ((_col0 <> '12') and (_col0 <> '4'))))) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
Map 3
Map Operator Tree:
TableScan
@@ -74,17 +77,20 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '11') and ((_col0 > '0') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '4') (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ predicate: ((_col0 <> '11') and ((_col0 > '0') and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Map 5
Map Operator Tree:
TableScan
@@ -94,20 +100,27 @@ STAGE PLANS:
predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '12') and (_col0 <> '4')) (type: boolean)
- Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 19 Data size: 201 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 19 Data size: 201 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 > '0') and (((_col1 <> 'val_500') or (_col0 > '1')) and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 <> '12') and (_col0 <> '4')) (type: boolean)
+ Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -117,14 +130,14 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col1, _col3
- Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -138,29 +151,29 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col0 <> '13') and (_col0 <> '1')) (type: boolean)
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: string)
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/subquery_notin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_notin.q.out b/ql/src/test/results/clientpositive/subquery_notin.q.out
index 0b6f33f..fd6d53b 100644
--- a/ql/src/test/results/clientpositive/subquery_notin.q.out
+++ b/ql/src/test/results/clientpositive/subquery_notin.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: -- non agg, non corr
explain
select *
@@ -151,7 +151,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select *
from src
where src.key not in ( select key from src s1 where s1.key > '2')
@@ -285,7 +285,7 @@ POSTHOOK: Input: default@src
199 val_199
199 val_199
2 val_2
-Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: -- non agg, corr
explain
select p_mfgr, b.p_name, p_size
@@ -528,7 +528,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select p_mfgr, b.p_name, p_size
from part b
where b.p_name not in
@@ -1243,7 +1243,7 @@ Manufacturer#5 almond antique medium spring khaki 6
Manufacturer#5 almond azure blanched chiffon midnight 23
Manufacturer#5 almond antique blue firebrick mint 31
Manufacturer#5 almond aquamarine dodger light gainsboro 46
-Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: -- non agg, non corr, Group By in Parent Query
select li.l_partkey, count(*)
from lineitem li
@@ -1278,7 +1278,7 @@ POSTHOOK: Input: default@lineitem
139636 1
175839 1
182052 1
-Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: -- alternate not in syntax
select *
from src
@@ -1442,7 +1442,7 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@t1_v
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T2_v
-Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain
select *
from T1_v where T1_v.key not in (select T2_v.key from T2_v)
@@ -1587,7 +1587,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select *
from T1_v where T1_v.key not in (select T2_v.key from T2_v)
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out
index 24c56bd..c32504e 100644
--- a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out
+++ b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: -- non agg, non corr
-- JAVA_VERSION_SPECIFIC_OUTPUT
@@ -188,7 +188,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: -- non agg, corr
explain
select b.p_mfgr, min(p_retailprice)
@@ -335,7 +335,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: max(_col1), min(_col1)
+ aggregations: min(_col1), max(_col1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -348,13 +348,13 @@ STAGE PLANS:
value expressions: _col1 (type: double), _col2 (type: double)
Reduce Operator Tree:
Group By Operator
- aggregations: max(VALUE._col0), min(VALUE._col1)
+ aggregations: min(VALUE._col0), max(VALUE._col1)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 is null or _col2 is null) and ((_col1 - _col2) > 600.0)) (type: boolean)
+ predicate: ((_col0 is null or _col1 is null) and ((_col2 - _col1) > 600.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
Select Operator
Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
@@ -445,7 +445,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: select b.p_mfgr, min(p_retailprice)
from part b
group by b.p_mfgr
@@ -470,7 +470,7 @@ POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 1173.15
Manufacturer#2 1690.68
-Warning: Shuffle Join JOIN[38][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
PREHOOK: query: -- agg, non corr
explain
select b.p_mfgr, min(p_retailprice)
@@ -729,7 +729,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[38][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
PREHOOK: query: select b.p_mfgr, min(p_retailprice)
from part b
group by b.p_mfgr
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
index c393e4b..2256f6e 100644
--- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
+++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
@@ -781,7 +781,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: -- non agg, corr
explain
select p_mfgr, b.p_name, p_size
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/subquery_views.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_views.q.out b/ql/src/test/results/clientpositive/subquery_views.q.out
index bdab9ea..41834a3 100644
--- a/ql/src/test/results/clientpositive/subquery_views.q.out
+++ b/ql/src/test/results/clientpositive/subquery_views.q.out
@@ -69,8 +69,8 @@ POSTHOOK: type: CREATEVIEW
POSTHOOK: Input: default@src
POSTHOOK: Output: database:default
POSTHOOK: Output: default@cv2
-Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[46][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product
PREHOOK: query: explain
select *
from cv2 where cv2.key in (select key from cv2 c where c.key < '11')
@@ -378,8 +378,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[46][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product
PREHOOK: query: select *
from cv2 where cv2.key in (select key from cv2 c where c.key < '11')
PREHOOK: type: QUERY
[3/3] hive git commit: HIVE-9069: Simplify filter predicates for CBO
(Jesus Camacho Rodriguez, reviewed by Laljo John Pullokkaran)
Posted by jc...@apache.org.
HIVE-9069: Simplify filter predicates for CBO (Jesus Camacho Rodriguez, reviewed by Laljo John Pullokkaran)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/e2f1caf3
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/e2f1caf3
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/e2f1caf3
Branch: refs/heads/branch-1
Commit: e2f1caf39484fe9fc7c1598a2dcff0a459f16148
Parents: 14c5e44
Author: Jesus Camacho Rodriguez <jc...@apache.org>
Authored: Mon Aug 10 13:37:06 2015 +0300
Committer: Jesus Camacho Rodriguez <jc...@apache.org>
Committed: Mon Aug 10 13:37:06 2015 +0300
----------------------------------------------------------------------
.../calcite/rules/HivePreFilteringRule.java | 218 +++++++
.../hadoop/hive/ql/parse/CalcitePlanner.java | 16 +-
.../clientpositive/filter_cond_pushdown.q | 19 +
.../results/clientpositive/auto_join16.q.out | 4 +-
.../results/clientpositive/auto_join8.q.out | 14 +-
.../clientpositive/cbo_rp_auto_join1.q.out | 4 +-
.../clientpositive/explain_logical.q.out | 22 +-
.../clientpositive/filter_cond_pushdown.q.out | 382 ++++++++++++
ql/src/test/results/clientpositive/join8.q.out | 16 +-
.../list_bucket_query_oneskew_2.q.out | 2 +-
.../test/results/clientpositive/ppd_gby.q.out | 41 +-
.../test/results/clientpositive/ppd_gby2.q.out | 49 +-
.../results/clientpositive/ppd_gby_join.q.out | 42 +-
.../test/results/clientpositive/ppd_join.q.out | 44 +-
.../test/results/clientpositive/ppd_join2.q.out | 81 +--
.../test/results/clientpositive/ppd_join3.q.out | 91 +--
.../results/clientpositive/ppd_udf_col.q.out | 178 +++---
.../test/results/clientpositive/ppd_union.q.out | 42 +-
ql/src/test/results/clientpositive/ppd_vc.q.out | 8 +-
.../clientpositive/spark/ppd_join2.q.out | 81 +--
.../clientpositive/spark/ppd_join3.q.out | 91 +--
.../results/clientpositive/subquery_notin.q.out | 16 +-
.../subquery_notin_having.q.java1.7.out | 16 +-
.../subquery_unqualcolumnrefs.q.out | 2 +-
.../results/clientpositive/subquery_views.q.out | 8 +-
.../clientpositive/tez/explainuser_1.q.out | 592 +++++++++----------
26 files changed, 1411 insertions(+), 668 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePreFilteringRule.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePreFilteringRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePreFilteringRule.java
new file mode 100644
index 0000000..dde6288
--- /dev/null
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePreFilteringRule.java
@@ -0,0 +1,218 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hive.ql.optimizer.calcite.rules;
+
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.List;
+import java.util.Map.Entry;
+import java.util.Set;
+
+import org.apache.calcite.plan.RelOptPredicateList;
+import org.apache.calcite.plan.RelOptRule;
+import org.apache.calcite.plan.RelOptRuleCall;
+import org.apache.calcite.plan.RelOptUtil;
+import org.apache.calcite.rel.RelNode;
+import org.apache.calcite.rel.core.Filter;
+import org.apache.calcite.rel.core.RelFactories.FilterFactory;
+import org.apache.calcite.rel.core.TableScan;
+import org.apache.calcite.rel.metadata.RelMetadataQuery;
+import org.apache.calcite.rex.RexBuilder;
+import org.apache.calcite.rex.RexCall;
+import org.apache.calcite.rex.RexInputRef;
+import org.apache.calcite.rex.RexLiteral;
+import org.apache.calcite.rex.RexNode;
+import org.apache.calcite.rex.RexUtil;
+import org.apache.calcite.sql.SqlKind;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.hive.ql.exec.Description;
+import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBetween;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFIn;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPEqual;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPEqualNS;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPEqualOrGreaterThan;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPEqualOrLessThan;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPGreaterThan;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPLessThan;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPNotEqual;
+
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.LinkedHashMultimap;
+import com.google.common.collect.Multimap;
+import com.google.common.collect.Sets;
+
+
+public class HivePreFilteringRule extends RelOptRule {
+
+ protected static final Log LOG = LogFactory
+ .getLog(HivePreFilteringRule.class.getName());
+
+
+ public static final HivePreFilteringRule INSTANCE =
+ new HivePreFilteringRule();
+
+ private final FilterFactory filterFactory;
+
+
+ private static final Set<String> COMPARISON_UDFS = Sets.newHashSet(
+ GenericUDFOPEqual.class.getAnnotation(Description.class).name(),
+ GenericUDFOPEqualNS.class.getAnnotation(Description.class).name(),
+ GenericUDFOPEqualOrGreaterThan.class.getAnnotation(Description.class).name(),
+ GenericUDFOPEqualOrLessThan.class.getAnnotation(Description.class).name(),
+ GenericUDFOPGreaterThan.class.getAnnotation(Description.class).name(),
+ GenericUDFOPLessThan.class.getAnnotation(Description.class).name(),
+ GenericUDFOPNotEqual.class.getAnnotation(Description.class).name());
+ private static final String IN_UDF =
+ GenericUDFIn.class.getAnnotation(Description.class).name();
+ private static final String BETWEEN_UDF =
+ GenericUDFBetween.class.getAnnotation(Description.class).name();
+
+
+ private HivePreFilteringRule() {
+ super(operand(Filter.class,
+ operand(RelNode.class, any())));
+ this.filterFactory = HiveFilter.DEFAULT_FILTER_FACTORY;
+ }
+
+ public void onMatch(RelOptRuleCall call) {
+ final Filter filter = call.rel(0);
+ final RelNode filterChild = call.rel(1);
+
+ // 0. If the filter is already on top of a TableScan,
+ // we can bail out
+ if (filterChild instanceof TableScan) {
+ return;
+ }
+
+ final RexBuilder rexBuilder = filter.getCluster().getRexBuilder();
+
+ final RexNode condition = RexUtil.pullFactors(rexBuilder, filter.getCondition());
+
+ // 1. We extract possible candidates to be pushed down
+ List<RexNode> commonOperands = new ArrayList<>();
+ switch (condition.getKind()) {
+ case AND:
+ ImmutableList<RexNode> operands = RexUtil.flattenAnd(((RexCall) condition).getOperands());
+ for (RexNode operand: operands) {
+ if (operand.getKind() == SqlKind.OR) {
+ commonOperands.addAll(extractCommonOperands(rexBuilder,operand));
+ }
+ }
+ break;
+ case OR:
+ commonOperands = extractCommonOperands(rexBuilder,condition);
+ break;
+ default:
+ return;
+ }
+
+ // 2. If we did not generate anything for the new predicate, we bail out
+ if (commonOperands.isEmpty()) {
+ return;
+ }
+
+ // 3. If the new conjuncts are already present in the plan, we bail out
+ final RelOptPredicateList predicates = RelMetadataQuery.getPulledUpPredicates(filter);
+ final List<RexNode> newConjuncts = new ArrayList<>();
+ for (RexNode commonOperand : commonOperands) {
+ boolean found = false;
+ for (RexNode conjunct : predicates.pulledUpPredicates) {
+ if (commonOperand.toString().equals(conjunct.toString())) {
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ newConjuncts.add(commonOperand);
+ }
+ }
+ if (newConjuncts.isEmpty()) {
+ return;
+ }
+
+ // 4. Otherwise, we create a new condition
+ final RexNode newCondition = RexUtil.pullFactors(rexBuilder,
+ RexUtil.composeConjunction(rexBuilder, newConjuncts, false));
+
+ // 5. We create the new filter that might be pushed down
+ RelNode newFilter = filterFactory.createFilter(filterChild, newCondition);
+ RelNode newTopFilter = filterFactory.createFilter(newFilter, condition);
+
+ call.transformTo(newTopFilter);
+
+ }
+
+ private static List<RexNode> extractCommonOperands(RexBuilder rexBuilder, RexNode condition) {
+ assert condition.getKind() == SqlKind.OR;
+ Multimap<String,RexNode> reductionCondition = LinkedHashMultimap.create();
+
+ // 1. We extract the information necessary to create the predicate for the new
+ // filter; currently we support comparison functions, in and between
+ ImmutableList<RexNode> operands = RexUtil.flattenOr(((RexCall) condition).getOperands());
+ for (RexNode operand: operands) {
+ final RexNode operandCNF = RexUtil.toCnf(rexBuilder, operand);
+ final List<RexNode> conjunctions = RelOptUtil.conjunctions(operandCNF);
+ boolean addedToReductionCondition = false; // Flag to control whether we have added a new factor
+ // to the reduction predicate
+ for (RexNode conjunction: conjunctions) {
+ if (!(conjunction instanceof RexCall)) {
+ continue;
+ }
+ RexCall conjCall = (RexCall) conjunction;
+ if(COMPARISON_UDFS.contains(conjCall.getOperator().getName())) {
+ if (conjCall.operands.get(0) instanceof RexInputRef &&
+ conjCall.operands.get(1) instanceof RexLiteral) {
+ reductionCondition.put(conjCall.operands.get(0).toString(),
+ conjCall);
+ addedToReductionCondition = true;
+ } else if (conjCall.operands.get(1) instanceof RexInputRef &&
+ conjCall.operands.get(0) instanceof RexLiteral) {
+ reductionCondition.put(conjCall.operands.get(1).toString(),
+ conjCall);
+ addedToReductionCondition = true;
+ }
+ } else if(conjCall.getOperator().getName().equals(IN_UDF)) {
+ reductionCondition.put(conjCall.operands.get(0).toString(),
+ conjCall);
+ addedToReductionCondition = true;
+ } else if(conjCall.getOperator().getName().equals(BETWEEN_UDF)) {
+ reductionCondition.put(conjCall.operands.get(1).toString(),
+ conjCall);
+ addedToReductionCondition = true;
+ }
+ }
+
+ // If we did not add any factor, we can bail out
+ if (!addedToReductionCondition) {
+ return new ArrayList<>();
+ }
+ }
+
+ // 2. We gather the common factors and return them
+ List<RexNode> commonOperands = new ArrayList<>();
+ for (Entry<String,Collection<RexNode>> pair : reductionCondition.asMap().entrySet()) {
+ if (pair.getValue().size() == operands.size()) {
+ commonOperands.add(RexUtil.composeDisjunction(rexBuilder, pair.getValue(), false));
+ }
+ }
+ return commonOperands;
+ }
+
+}
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
index 130d525..38f2014 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
@@ -144,6 +144,7 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveInsertExchange4Join
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveJoinAddNotNullRule;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveJoinToMultiJoinRule;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HivePartitionPruneRule;
+import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HivePreFilteringRule;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveRelFieldTrimmer;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveWindowingFixRule;
import org.apache.hadoop.hive.ql.optimizer.calcite.translator.ASTConverter;
@@ -937,17 +938,18 @@ public class CalcitePlanner extends SemanticAnalyzer {
basePlan = hepPlan(basePlan, true, mdProvider, HiveJoinAddNotNullRule.INSTANCE);
}
- // 3. PPD
+ // 3. Constant propagation, common filter extraction, and PPD
basePlan = hepPlan(basePlan, true, mdProvider,
ReduceExpressionsRule.PROJECT_INSTANCE,
ReduceExpressionsRule.FILTER_INSTANCE,
ReduceExpressionsRule.JOIN_INSTANCE,
- new HiveFilterProjectTransposeRule(
- Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, HiveProject.class,
- HiveProject.DEFAULT_PROJECT_FACTORY), new HiveFilterSetOpTransposeRule(
- HiveFilter.DEFAULT_FILTER_FACTORY),
- new FilterMergeRule(HiveFilter.DEFAULT_FILTER_FACTORY), HiveFilterJoinRule.JOIN,
- HiveFilterJoinRule.FILTER_ON_JOIN, new FilterAggregateTransposeRule(Filter.class,
+ HivePreFilteringRule.INSTANCE,
+ new HiveFilterProjectTransposeRule(Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY,
+ HiveProject.class, HiveProject.DEFAULT_PROJECT_FACTORY),
+ new HiveFilterSetOpTransposeRule(HiveFilter.DEFAULT_FILTER_FACTORY),
+ HiveFilterJoinRule.JOIN,
+ HiveFilterJoinRule.FILTER_ON_JOIN,
+ new FilterAggregateTransposeRule(Filter.class,
HiveFilter.DEFAULT_FILTER_FACTORY, Aggregate.class));
// 4. Transitive inference & Partition Pruning
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/queries/clientpositive/filter_cond_pushdown.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/filter_cond_pushdown.q b/ql/src/test/queries/clientpositive/filter_cond_pushdown.q
new file mode 100644
index 0000000..5e23b71
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/filter_cond_pushdown.q
@@ -0,0 +1,19 @@
+EXPLAIN
+SELECT f.key, g.value
+FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AND m.value !='')
+WHERE (f.key = m.key AND f.value='2008-04-08' AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09');
+
+EXPLAIN
+SELECT f.key, g.value
+FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AND m.value !='')
+WHERE (f.key = m.key AND f.value IN ('2008-04-08','2008-04-10') AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09');
+
+EXPLAIN
+SELECT t1.key
+FROM cbo_t1 t1
+JOIN (
+ SELECT t2.key
+ FROM cbo_t2 t2
+ JOIN (SELECT * FROM cbo_t3 t3 WHERE c_int=1) t3 ON t2.key=t3.c_int
+ WHERE ((t2.key=t3.key) AND (t2.c_float + t3.c_float > 2)) OR
+ ((t2.key=t3.key) AND (t2.c_int + t3.c_int > 2))) t4 ON t1.key=t4.key;
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/auto_join16.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_join16.q.out b/ql/src/test/results/clientpositive/auto_join16.q.out
index b07eaf6..1bad0f9 100644
--- a/ql/src/test/results/clientpositive/auto_join16.q.out
+++ b/ql/src/test/results/clientpositive/auto_join16.q.out
@@ -23,11 +23,11 @@ STAGE PLANS:
Stage: Stage-5
Map Reduce Local Work
Alias -> Map Local Tables:
- $hdt$_0:$hdt$_0:$hdt$_0:a
+ $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:a
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
- $hdt$_0:$hdt$_0:$hdt$_0:a
+ $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:a
TableScan
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/auto_join8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_join8.q.out b/ql/src/test/results/clientpositive/auto_join8.q.out
index f0cb77b..2ca26aa 100644
--- a/ql/src/test/results/clientpositive/auto_join8.q.out
+++ b/ql/src/test/results/clientpositive/auto_join8.q.out
@@ -73,12 +73,12 @@ STAGE PLANS:
alias: src1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join0 to 1
@@ -86,17 +86,17 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col2 is null (type: boolean)
- Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out
index 2e23197..f4b25ae 100644
--- a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out
+++ b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out
@@ -610,7 +610,7 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
- alias: a
+ alias: b
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean)
@@ -1277,7 +1277,7 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
- alias: a
+ alias: b
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean)
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/explain_logical.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/explain_logical.q.out b/ql/src/test/results/clientpositive/explain_logical.q.out
index 831535e..545034a 100644
--- a/ql/src/test/results/clientpositive/explain_logical.q.out
+++ b/ql/src/test/results/clientpositive/explain_logical.q.out
@@ -503,23 +503,23 @@ TOK_QUERY
LOGICAL PLAN:
-$hdt$_0:srcpart
+$hdt$_0:$hdt$_0:srcpart
TableScan (TS_0)
alias: srcpart
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Filter Operator (FIL_12)
+ Filter Operator (FIL_14)
predicate: key is not null (type: boolean)
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Select Operator (SEL_2)
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator (RS_6)
+ Reduce Output Operator (RS_8)
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Join Operator (JOIN_9)
+ Join Operator (JOIN_11)
condition map:
Inner Join 0 to 1
keys:
@@ -527,11 +527,11 @@ $hdt$_0:srcpart
1 _col0 (type: string)
outputColumnNames: _col0, _col2
Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- Select Operator (SEL_10)
+ Select Operator (SEL_12)
expressions: _col0 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- File Output Operator (FS_11)
+ File Output Operator (FS_13)
compressed: false
Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
table:
@@ -539,23 +539,23 @@ $hdt$_0:srcpart
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
$hdt$_1:src2
- TableScan (TS_3)
+ TableScan (TS_5)
alias: src2
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator (FIL_13)
+ Filter Operator (FIL_15)
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator (SEL_4)
+ Select Operator (SEL_6)
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator (RS_8)
+ Reduce Output Operator (RS_10)
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Join Operator (JOIN_9)
+ Join Operator (JOIN_11)
condition map:
Inner Join 0 to 1
keys:
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out
new file mode 100644
index 0000000..e09057a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out
@@ -0,0 +1,382 @@
+PREHOOK: query: EXPLAIN
+SELECT f.key, g.value
+FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AND m.value !='')
+WHERE (f.key = m.key AND f.value='2008-04-08' AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09')
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT f.key, g.value
+FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AND m.value !='')
+WHERE (f.key = m.key AND f.value='2008-04-08' AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09')
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: f
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((value = '2008-04-08') or (value = '2008-04-09')) and key is not null) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ alias: f
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((value <> '') and key is not null) and value is not null) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col1 = '2008-04-08') and (_col3 = '2008-04-08')) or (_col1 = '2008-04-09')) (type: boolean)
+ Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col3 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ TableScan
+ alias: f
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (value <> '') (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col4
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: EXPLAIN
+SELECT f.key, g.value
+FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AND m.value !='')
+WHERE (f.key = m.key AND f.value IN ('2008-04-08','2008-04-10') AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09')
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT f.key, g.value
+FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AND m.value !='')
+WHERE (f.key = m.key AND f.value IN ('2008-04-08','2008-04-10') AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09')
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: f
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((value) IN ('2008-04-08', '2008-04-10') or (value = '2008-04-09')) and key is not null) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ alias: f
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((value <> '') and key is not null) and value is not null) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col1) IN ('2008-04-08', '2008-04-10') and (_col3 = '2008-04-08')) or (_col1 = '2008-04-09')) (type: boolean)
+ Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col3 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ TableScan
+ alias: f
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (value <> '') (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col4
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: EXPLAIN
+SELECT t1.key
+FROM cbo_t1 t1
+JOIN (
+ SELECT t2.key
+ FROM cbo_t2 t2
+ JOIN (SELECT * FROM cbo_t3 t3 WHERE c_int=1) t3 ON t2.key=t3.c_int
+ WHERE ((t2.key=t3.key) AND (t2.c_float + t3.c_float > 2)) OR
+ ((t2.key=t3.key) AND (t2.c_int + t3.c_int > 2))) t4 ON t1.key=t4.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT t1.key
+FROM cbo_t1 t1
+JOIN (
+ SELECT t2.key
+ FROM cbo_t2 t2
+ JOIN (SELECT * FROM cbo_t3 t3 WHERE c_int=1) t3 ON t2.key=t3.c_int
+ WHERE ((t2.key=t3.key) AND (t2.c_float + t3.c_float > 2)) OR
+ ((t2.key=t3.key) AND (t2.c_int + t3.c_int > 2))) t4 ON t1.key=t4.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-1 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: t2
+ Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (UDFToDouble(key) = 1.0) (type: boolean)
+ Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: c_int (type: int), c_float (type: float)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: '1.0' (type: string)
+ sort order: +
+ Map-reduce partition columns: '1.0' (type: string)
+ Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: float)
+ TableScan
+ alias: t3
+ Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((c_int = 1) and (UDFToDouble(key) = 1.0)) (type: boolean)
+ Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: c_float (type: float)
+ outputColumnNames: _col2
+ Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: '1.0' (type: string)
+ sort order: +
+ Map-reduce partition columns: '1.0' (type: string)
+ Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: float)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col2 + _col5) > 2.0) or ((_col1 + 1) > 2)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (UDFToDouble(key) = 1.0) (type: boolean)
+ Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: '1.0' (type: string)
+ sort order: +
+ Map-reduce partition columns: '1.0' (type: string)
+ Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: '1.0' (type: string)
+ sort order: +
+ Map-reduce partition columns: '1.0' (type: string)
+ Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '1.0' (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 11 Data size: 144 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
+
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/join8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join8.q.out b/ql/src/test/results/clientpositive/join8.q.out
index 493341d..6ff3e33 100644
--- a/ql/src/test/results/clientpositive/join8.q.out
+++ b/ql/src/test/results/clientpositive/join8.q.out
@@ -53,17 +53,17 @@ STAGE PLANS:
alias: src1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
TableScan
alias: src1
@@ -89,17 +89,17 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col2 is null (type: boolean)
- Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out
index aab5506..177da44 100644
--- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out
@@ -758,7 +758,7 @@ STAGE PLANS:
name: default.fact_daily
name: default.fact_daily
Truncated Path -> Alias:
- /fact_tz/ds=1/x=484 [$hdt$_0:fact_daily]
+ /fact_tz/ds=1/x=484 [$hdt$_0:$hdt$_0:fact_daily]
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_gby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_gby.q.out b/ql/src/test/results/clientpositive/ppd_gby.q.out
index 523842e..87cb907 100644
--- a/ql/src/test/results/clientpositive/ppd_gby.q.out
+++ b/ql/src/test/results/clientpositive/ppd_gby.q.out
@@ -25,38 +25,45 @@ STAGE PLANS:
predicate: ((value > 'val_10') and (value > 'val_200')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string), key (type: string)
+ expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
+ Filter Operator
+ predicate: (_col1 > 'val_200') (type: boolean)
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean)
- Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_gby2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_gby2.q.out b/ql/src/test/results/clientpositive/ppd_gby2.q.out
index 1ee4b49..bc00149 100644
--- a/ql/src/test/results/clientpositive/ppd_gby2.q.out
+++ b/ql/src/test/results/clientpositive/ppd_gby2.q.out
@@ -28,41 +28,48 @@ STAGE PLANS:
predicate: ((value > 'val_10') and (value > 'val_200')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string), key (type: string)
+ expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
+ Filter Operator
+ predicate: (_col1 > 'val_200') (type: boolean)
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean)
- Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: bigint), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(_col1)
keys: _col0 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -78,7 +85,7 @@ STAGE PLANS:
key expressions: _col0 (type: bigint)
sort order: +
Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reduce Operator Tree:
Group By Operator
@@ -86,14 +93,14 @@ STAGE PLANS:
keys: KEY._col0 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string), _col0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_gby_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/ppd_gby_join.q.out
index 60ae8f9..579c827 100644
--- a/ql/src/test/results/clientpositive/ppd_gby_join.q.out
+++ b/ql/src/test/results/clientpositive/ppd_gby_join.q.out
@@ -42,16 +42,19 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '4') (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
+ predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -59,20 +62,27 @@ STAGE PLANS:
predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean)
+ predicate: ((_col0 > '20') and (((_col1 < 'val_50') or (_col0 > '2')) and (_col0 < '400'))) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ Filter Operator
+ predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_join.q.out b/ql/src/test/results/clientpositive/ppd_join.q.out
index 8fde2d7..ae5fb27 100644
--- a/ql/src/test/results/clientpositive/ppd_join.q.out
+++ b/ql/src/test/results/clientpositive/ppd_join.q.out
@@ -39,17 +39,20 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '4') (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
+ predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -57,20 +60,27 @@ STAGE PLANS:
predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean)
+ predicate: ((_col0 > '20') and (((_col1 < 'val_50') or (_col0 > '2')) and (_col0 < '400'))) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ Filter Operator
+ predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_join2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_join2.q.out b/ql/src/test/results/clientpositive/ppd_join2.q.out
index b821d91..88624ea 100644
--- a/ql/src/test/results/clientpositive/ppd_join2.q.out
+++ b/ql/src/test/results/clientpositive/ppd_join2.q.out
@@ -46,17 +46,20 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '302') and ((_col0 <> '311') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '14') (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ predicate: ((_col0 <> '302') and ((_col0 <> '311') and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -68,17 +71,20 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean)
- Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 <> '311') and (((_col1 <> 'val_50') or (_col0 > '1')) and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean)
+ Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
@@ -87,21 +93,21 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col1 is not null (type: boolean)
- Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -119,23 +125,30 @@ STAGE PLANS:
predicate: (((key <> '306') and (sqrt(key) <> 13.0)) and value is not null) (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ predicate: (sqrt(_col0) <> 13.0) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
TableScan
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col3 (type: string)
Reduce Operator Tree:
Join Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/e2f1caf3/ql/src/test/results/clientpositive/ppd_join3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_join3.q.out b/ql/src/test/results/clientpositive/ppd_join3.q.out
index 49da9e0..6c5c0da 100644
--- a/ql/src/test/results/clientpositive/ppd_join3.q.out
+++ b/ql/src/test/results/clientpositive/ppd_join3.q.out
@@ -46,17 +46,20 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '11') and ((_col0 > '0') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '4') (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ predicate: ((_col0 <> '11') and ((_col0 > '0') and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -64,20 +67,27 @@ STAGE PLANS:
predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '12') and (_col0 <> '4')) (type: boolean)
- Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 19 Data size: 201 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 19 Data size: 201 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 > '0') and (((_col1 <> 'val_500') or (_col0 > '1')) and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 <> '12') and (_col0 <> '4')) (type: boolean)
+ Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -86,24 +96,24 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((_col0 <> '13') and (_col0 <> '1')) (type: boolean)
- Statistics: Num rows: 20 Data size: 221 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -125,22 +135,25 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '11') and ((_col0 > '0') and ((_col0 < '400') and ((_col0 <> '12') and (_col0 <> '4'))))) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '1') (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ predicate: ((_col0 <> '11') and ((_col0 > '0') and ((_col0 < '400') and ((_col0 <> '12') and (_col0 <> '4'))))) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
TableScan
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: string)
Reduce Operator Tree:
Join Operator
@@ -150,14 +163,14 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col1, _col3
- Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat