This is an automated email from the ASF dual-hosted git repository.
krisztiankasa pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new 21020a75196 HIVE-27088: Incorrect results when inner and outer joins
with post join filters are merged (Ryu Kobayashi, reviewed by Krisztian Kasa)
21020a75196 is described below
commit 21020a75196f13b7276b600d15d626af59d15ac3
Author: Ryu Kobayashi <[email protected]>
AuthorDate: Tue May 23 17:28:30 2023 +0900
HIVE-27088: Incorrect results when inner and outer joins with post join
filters are merged (Ryu Kobayashi, reviewed by Krisztian Kasa)
---
.../hadoop/hive/ql/parse/SemanticAnalyzer.java | 9 +-
.../clientpositive/tez_nway_join_with_filters.q | 94 +++
.../llap/tez_nway_join_with_filters.q.out | 729 +++++++++++++++++++++
3 files changed, 828 insertions(+), 4 deletions(-)
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
index fb9ae347ed0..3f15bc37c17 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
@@ -10766,9 +10766,10 @@ public class SemanticAnalyzer extends
BaseSemanticAnalyzer {
isTargetSemiJoin= !target.getNoSemiJoin();
hasTargetPostJoinFilters = target.getPostJoinFilters().size() !=0;
- if((hasNodePostJoinFilters && (isNodeOuterJoin || isNodeSemiJoin))
- || (hasTargetPostJoinFilters && (isTargetOuterJoin ||
isTargetSemiJoin))) {
- return false;
+ if (hasNodePostJoinFilters || hasTargetPostJoinFilters) {
+ if (isNodeOuterJoin || isNodeSemiJoin || isTargetOuterJoin ||
isTargetSemiJoin) {
+ return false;
+ }
}
return true;
}
@@ -10810,7 +10811,7 @@ public class SemanticAnalyzer extends
BaseSemanticAnalyzer {
break;
}
if(!shouldMerge(node, target)) {
- // Outer joins with post-filtering conditions cannot be merged
+ // Outer joins or outer and not outer with post-filtering
conditions cannot be merged
break;
}
Pair<Integer, int[]> mergeDetails = findMergePos(node, target);
diff --git a/ql/src/test/queries/clientpositive/tez_nway_join_with_filters.q
b/ql/src/test/queries/clientpositive/tez_nway_join_with_filters.q
new file mode 100644
index 00000000000..aab2529951a
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/tez_nway_join_with_filters.q
@@ -0,0 +1,94 @@
+set hive.mapred.mode=nonstrict;
+set hive.explain.user=false;
+set hive.auto.convert.join=true;
+
+create temporary table foo (id bigint, code string) stored as orc;
+create temporary table bar (id bigint, code string) stored as orc;
+create temporary table baz (id bigint) stored as orc;
+
+-- SORT_QUERY_RESULTS
+
+INSERT INTO foo values
+ (29999000052073, '01'),
+ (29999000052107, '01'),
+ (29999000052111, '01'),
+ (29999000052112, '01'),
+ (29999000052113, '01'),
+ (29999000052114, '01'),
+ (29999000052071, '01A'),
+ (29999000052072, '01A'),
+ (29999000052116, '01A'),
+ (29999000052117, '01A'),
+ (29999000052118, '01A'),
+ (29999000052119, '01A'),
+ (29999000052120, '01A'),
+ (29999000052076, '06'),
+ (29999000052074, '06A'),
+ (29999000052075, '06A');
+INSERT INTO bar values
+ (29999000052071, '01'),
+ (29999000052072, '01'),
+ (29999000052073, '01'),
+ (29999000052116, '01'),
+ (29999000052117, '01'),
+ (29999000052071, '01A'),
+ (29999000052072, '01A'),
+ (29999000052073, '01A'),
+ (29999000052116, '01AS'),
+ (29999000052117, '01AS'),
+ (29999000052071, '01B'),
+ (29999000052072, '01B'),
+ (29999000052073, '01B'),
+ (29999000052116, '01BS'),
+ (29999000052117, '01BS'),
+ (29999000052071, '01C'),
+ (29999000052072, '01C'),
+ (29999000052073, '01C7'),
+ (29999000052116, '01CS'),
+ (29999000052117, '01CS'),
+ (29999000052071, '01D'),
+ (29999000052072, '01D'),
+ (29999000052073, '01D'),
+ (29999000052116, '01DS'),
+ (29999000052117, '01DS');
+INSERT INTO baz values
+ (29999000052071),
+ (29999000052072),
+ (29999000052073),
+ (29999000052074),
+ (29999000052075),
+ (29999000052076),
+ (29999000052107),
+ (29999000052111),
+ (29999000052112),
+ (29999000052113),
+ (29999000052114),
+ (29999000052116),
+ (29999000052117),
+ (29999000052118),
+ (29999000052119),
+ (29999000052120);
+
+set hive.merge.nway.joins=true;
+explain select a.id, b.code, c.id from foo a left outer join bar b on a.id =
b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id =
c.id;
+
+set hive.merge.nway.joins=false;
+explain select a.id, b.code, c.id from foo a left outer join bar b on a.id =
b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id =
c.id;
+
+set hive.merge.nway.joins=true;
+select a.id, b.code, c.id from foo a left outer join bar b on a.id = b.id and
(a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id = c.id;
+
+set hive.merge.nway.joins=false;
+select a.id, b.code, c.id from foo a left outer join bar b on a.id = b.id and
(a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id = c.id;
+
+set hive.merge.nway.joins=true;
+explain select a.id, b.code, c.id from foo a inner join bar b on a.id = b.id
and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id = c.id;
+
+set hive.merge.nway.joins=false;
+explain select a.id, b.code, c.id from foo a inner join bar b on a.id = b.id
and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id = c.id;
+
+set hive.merge.nway.joins=true;
+select a.id, b.code, c.id from foo a inner join bar b on a.id = b.id and
(a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id = c.id;
+
+set hive.merge.nway.joins=false;
+select a.id, b.code, c.id from foo a inner join bar b on a.id = b.id and
(a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id = c.id;
diff --git
a/ql/src/test/results/clientpositive/llap/tez_nway_join_with_filters.q.out
b/ql/src/test/results/clientpositive/llap/tez_nway_join_with_filters.q.out
new file mode 100644
index 00000000000..ce098e4748d
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/tez_nway_join_with_filters.q.out
@@ -0,0 +1,729 @@
+PREHOOK: query: create temporary table foo (id bigint, code string) stored as
orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@foo
+POSTHOOK: query: create temporary table foo (id bigint, code string) stored as
orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@foo
+PREHOOK: query: create temporary table bar (id bigint, code string) stored as
orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bar
+POSTHOOK: query: create temporary table bar (id bigint, code string) stored as
orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bar
+PREHOOK: query: create temporary table baz (id bigint) stored as orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@baz
+POSTHOOK: query: create temporary table baz (id bigint) stored as orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@baz
+PREHOOK: query: INSERT INTO foo values
+ (29999000052073, '01'),
+ (29999000052107, '01'),
+ (29999000052111, '01'),
+ (29999000052112, '01'),
+ (29999000052113, '01'),
+ (29999000052114, '01'),
+ (29999000052071, '01A'),
+ (29999000052072, '01A'),
+ (29999000052116, '01A'),
+ (29999000052117, '01A'),
+ (29999000052118, '01A'),
+ (29999000052119, '01A'),
+ (29999000052120, '01A'),
+ (29999000052076, '06'),
+ (29999000052074, '06A'),
+ (29999000052075, '06A')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@foo
+POSTHOOK: query: INSERT INTO foo values
+ (29999000052073, '01'),
+ (29999000052107, '01'),
+ (29999000052111, '01'),
+ (29999000052112, '01'),
+ (29999000052113, '01'),
+ (29999000052114, '01'),
+ (29999000052071, '01A'),
+ (29999000052072, '01A'),
+ (29999000052116, '01A'),
+ (29999000052117, '01A'),
+ (29999000052118, '01A'),
+ (29999000052119, '01A'),
+ (29999000052120, '01A'),
+ (29999000052076, '06'),
+ (29999000052074, '06A'),
+ (29999000052075, '06A')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@foo
+POSTHOOK: Lineage: foo.code SCRIPT []
+POSTHOOK: Lineage: foo.id SCRIPT []
+PREHOOK: query: INSERT INTO bar values
+ (29999000052071, '01'),
+ (29999000052072, '01'),
+ (29999000052073, '01'),
+ (29999000052116, '01'),
+ (29999000052117, '01'),
+ (29999000052071, '01A'),
+ (29999000052072, '01A'),
+ (29999000052073, '01A'),
+ (29999000052116, '01AS'),
+ (29999000052117, '01AS'),
+ (29999000052071, '01B'),
+ (29999000052072, '01B'),
+ (29999000052073, '01B'),
+ (29999000052116, '01BS'),
+ (29999000052117, '01BS'),
+ (29999000052071, '01C'),
+ (29999000052072, '01C'),
+ (29999000052073, '01C7'),
+ (29999000052116, '01CS'),
+ (29999000052117, '01CS'),
+ (29999000052071, '01D'),
+ (29999000052072, '01D'),
+ (29999000052073, '01D'),
+ (29999000052116, '01DS'),
+ (29999000052117, '01DS')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@bar
+POSTHOOK: query: INSERT INTO bar values
+ (29999000052071, '01'),
+ (29999000052072, '01'),
+ (29999000052073, '01'),
+ (29999000052116, '01'),
+ (29999000052117, '01'),
+ (29999000052071, '01A'),
+ (29999000052072, '01A'),
+ (29999000052073, '01A'),
+ (29999000052116, '01AS'),
+ (29999000052117, '01AS'),
+ (29999000052071, '01B'),
+ (29999000052072, '01B'),
+ (29999000052073, '01B'),
+ (29999000052116, '01BS'),
+ (29999000052117, '01BS'),
+ (29999000052071, '01C'),
+ (29999000052072, '01C'),
+ (29999000052073, '01C7'),
+ (29999000052116, '01CS'),
+ (29999000052117, '01CS'),
+ (29999000052071, '01D'),
+ (29999000052072, '01D'),
+ (29999000052073, '01D'),
+ (29999000052116, '01DS'),
+ (29999000052117, '01DS')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@bar
+POSTHOOK: Lineage: bar.code SCRIPT []
+POSTHOOK: Lineage: bar.id SCRIPT []
+PREHOOK: query: INSERT INTO baz values
+ (29999000052071),
+ (29999000052072),
+ (29999000052073),
+ (29999000052074),
+ (29999000052075),
+ (29999000052076),
+ (29999000052107),
+ (29999000052111),
+ (29999000052112),
+ (29999000052113),
+ (29999000052114),
+ (29999000052116),
+ (29999000052117),
+ (29999000052118),
+ (29999000052119),
+ (29999000052120)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@baz
+POSTHOOK: query: INSERT INTO baz values
+ (29999000052071),
+ (29999000052072),
+ (29999000052073),
+ (29999000052074),
+ (29999000052075),
+ (29999000052076),
+ (29999000052107),
+ (29999000052111),
+ (29999000052112),
+ (29999000052113),
+ (29999000052114),
+ (29999000052116),
+ (29999000052117),
+ (29999000052118),
+ (29999000052119),
+ (29999000052120)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@baz
+POSTHOOK: Lineage: baz.id SCRIPT []
+PREHOOK: query: explain select a.id, b.code, c.id from foo a left outer join
bar b on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join
baz c on a.id = c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: explain select a.id, b.code, c.id from foo a left outer join
bar b on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join
baz c on a.id = c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), (code = '01AS') (type:
boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ input vertices:
+ 1 Map 2
+ residual filter predicates: {(_col1 or _col4)}
+ Statistics: Num rows: 26 Data size: 5068 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col3, _col5
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 28 Data size: 5574 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col3 (type:
string), _col5 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: llap
+ LLAP IO: all inputs
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: b
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 4800 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), code (type: string),
(code = '01BS') (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type:
boolean)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: c
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain select a.id, b.code, c.id from foo a left outer join
bar b on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join
baz c on a.id = c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: explain select a.id, b.code, c.id from foo a left outer join
bar b on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join
baz c on a.id = c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), (code = '01AS') (type:
boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ input vertices:
+ 1 Map 2
+ residual filter predicates: {(_col1 or _col4)}
+ Statistics: Num rows: 26 Data size: 5068 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col3, _col5
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 28 Data size: 5574 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col3 (type:
string), _col5 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: llap
+ LLAP IO: all inputs
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: b
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 4800 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), code (type: string),
(code = '01BS') (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type:
boolean)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: c
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select a.id, b.code, c.id from foo a left outer join bar b on
a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on
a.id = c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: select a.id, b.code, c.id from foo a left outer join bar b on
a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on
a.id = c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+29999000052071 NULL 29999000052071
+29999000052072 NULL 29999000052072
+29999000052073 NULL 29999000052073
+29999000052074 NULL 29999000052074
+29999000052075 NULL 29999000052075
+29999000052076 NULL 29999000052076
+29999000052107 NULL 29999000052107
+29999000052111 NULL 29999000052111
+29999000052112 NULL 29999000052112
+29999000052113 NULL 29999000052113
+29999000052114 NULL 29999000052114
+29999000052116 01BS 29999000052116
+29999000052117 01BS 29999000052117
+29999000052118 NULL 29999000052118
+29999000052119 NULL 29999000052119
+29999000052120 NULL 29999000052120
+PREHOOK: query: select a.id, b.code, c.id from foo a left outer join bar b on
a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on
a.id = c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: select a.id, b.code, c.id from foo a left outer join bar b on
a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on
a.id = c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+29999000052071 NULL 29999000052071
+29999000052072 NULL 29999000052072
+29999000052073 NULL 29999000052073
+29999000052074 NULL 29999000052074
+29999000052075 NULL 29999000052075
+29999000052076 NULL 29999000052076
+29999000052107 NULL 29999000052107
+29999000052111 NULL 29999000052111
+29999000052112 NULL 29999000052112
+29999000052113 NULL 29999000052113
+29999000052114 NULL 29999000052114
+29999000052116 01BS 29999000052116
+29999000052117 01BS 29999000052117
+29999000052118 NULL 29999000052118
+29999000052119 NULL 29999000052119
+29999000052120 NULL 29999000052120
+PREHOOK: query: explain select a.id, b.code, c.id from foo a inner join bar b
on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c
on a.id = c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: explain select a.id, b.code, c.id from foo a inner join bar b
on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c
on a.id = c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ filterExpr: id is not null (type: boolean)
+ probeDecodeDetails: cacheKey:HASH_MAP_MAPJOIN_38_container,
bigKeyColName:id, smallTablePos:1, keyRatio:1.04
+ Statistics: Num rows: 25 Data size: 4800 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), code (type: string),
(code = '01BS') (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col1, _col2, _col3, _col4
+ input vertices:
+ 1 Map 2
+ residual filter predicates: {(_col4 or _col2)}
+ Statistics: Num rows: 26 Data size: 5068 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col3 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col1, _col3, _col5
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: bigint), _col1 (type:
string), _col5 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: llap
+ LLAP IO: all inputs
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), (code = '01AS') (type:
boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: boolean)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: c
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain select a.id, b.code, c.id from foo a inner join bar b
on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c
on a.id = c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: explain select a.id, b.code, c.id from foo a inner join bar b
on a.id = b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c
on a.id = c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ filterExpr: id is not null (type: boolean)
+ probeDecodeDetails: cacheKey:HASH_MAP_MAPJOIN_38_container,
bigKeyColName:id, smallTablePos:1, keyRatio:1.04
+ Statistics: Num rows: 25 Data size: 4800 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), code (type: string),
(code = '01BS') (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4608 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col1, _col2, _col3, _col4
+ input vertices:
+ 1 Map 2
+ residual filter predicates: {(_col4 or _col2)}
+ Statistics: Num rows: 26 Data size: 5068 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col3 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col1, _col3, _col5
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: bigint), _col1 (type:
string), _col5 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 28 Data size: 5574 Basic
stats: COMPLETE Column stats: NONE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: llap
+ LLAP IO: all inputs
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint), (code = '01AS') (type:
boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 16 Data size: 3072 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: boolean)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: c
+ filterExpr: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: id (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 16 Data size: 128 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select a.id, b.code, c.id from foo a inner join bar b on a.id
= b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id =
c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: select a.id, b.code, c.id from foo a inner join bar b on a.id
= b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id =
c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+29999000052116 01BS 29999000052116
+29999000052117 01BS 29999000052117
+PREHOOK: query: select a.id, b.code, c.id from foo a inner join bar b on a.id
= b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id =
c.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Input: default@baz
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: select a.id, b.code, c.id from foo a inner join bar b on a.id
= b.id and (a.code = '01AS' or b.code = '01BS') left outer join baz c on a.id =
c.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Input: default@baz
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+29999000052116 01BS 29999000052116
+29999000052117 01BS 29999000052117
