This is an automated email from the ASF dual-hosted git repository.
sankarh pushed a commit to branch branch-3
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/branch-3 by this push:
new 639b2dba6a6 HIVE-27604: Backport of HIVE-21167 to branch-3 (#4583)
639b2dba6a6 is described below
commit 639b2dba6a61ad8bff04c924830fe733108bb620
Author: Aman Raj <104416558+amanraj2...@users.noreply.github.com>
AuthorDate: Wed Oct 18 17:14:08 2023 +0530
HIVE-27604: Backport of HIVE-21167 to branch-3 (#4583)
* HIVE-21167: Bucketing: Bucketing version 1 is incorrectly partitioning
data (Deepak Jaiswal, reviewed by Jason Dere and Vineet Garg)
---------
Co-authored-by: Deepak Jaiswal <djais...@apache.org>
Signed-off-by: Sankar Hariappan <sank...@apache.org>
Closes (#4583)
---
.../apache/hadoop/hive/ql/parse/TezCompiler.java | 47 ++-
.../queries/clientpositive/murmur_hash_migration.q | 35 +++
.../llap/murmur_hash_migration.q.out | 332 +++++++++++++++++++++
3 files changed, 390 insertions(+), 24 deletions(-)
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/TezCompiler.java
b/ql/src/java/org/apache/hadoop/hive/ql/parse/TezCompiler.java
index a92d4f643e6..95ef33ffe20 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/TezCompiler.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/TezCompiler.java
@@ -167,9 +167,6 @@ public class TezCompiler extends TaskCompiler {
runStatsAnnotation(procCtx);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.TEZ_COMPILER,
"Setup stats in the operator plan");
- // Update bucketing version of ReduceSinkOp if needed
- updateBucketingVersionForUpgrade(procCtx);
-
perfLogger.PerfLogBegin(this.getClass().getName(),
PerfLogger.TEZ_COMPILER);
// run the optimizations that use stats for optimization
runStatsDependentOptimizations(procCtx, inputs, outputs);
@@ -201,6 +198,15 @@ public class TezCompiler extends TaskCompiler {
new
ConstantPropagate(ConstantPropagateOption.SHORTCUT).transform(procCtx.parseContext);
}
+ // ATTENTION : DO NOT, I REPEAT, DO NOT WRITE ANYTHING AFTER
updateBucketingVersionForUpgrade()
+ // ANYTHING WHICH NEEDS TO BE ADDED MUST BE ADDED ABOVE
+ // This call updates the bucketing version of final ReduceSinkOp based on
+ // the bucketing version of FileSinkOp. This operation must happen at the
+ // end to ensure there is no further rewrite of plan which may end up
+ // removing/updating the ReduceSinkOp as was the case with
SortedDynPartitionOptimizer
+ // Update bucketing version of ReduceSinkOp if needed
+ updateBucketingVersionForUpgrade(procCtx);
+
}
private void runCycleAnalysisForPartitionPruning(OptimizeTezProcContext
procCtx,
@@ -1654,30 +1660,23 @@ public class TezCompiler extends TaskCompiler {
for (FileSinkOperator fsOp : fsOpsAll) {
- Operator<?> parentOfFS = fsOp.getParentOperators().get(0);
- if (parentOfFS instanceof GroupByOperator) {
- GroupByOperator gbyOp = (GroupByOperator) parentOfFS;
- List<String> aggs = gbyOp.getConf().getAggregatorStrings();
- boolean compute_stats = false;
- for (String agg : aggs) {
- if (agg.equalsIgnoreCase("compute_stats")) {
- compute_stats = true;
- break;
- }
- }
- if (compute_stats) {
+ if (!fsOp.getConf().getTableInfo().isSetBucketingVersion()) {
+ continue;
+ }
+ // Look for direct parent ReduceSinkOp
+ // If there are more than 1 parent, bail out.
+ Operator<?> parent = fsOp;
+ List<Operator<?>> parentOps = parent.getParentOperators();
+ while (parentOps != null && parentOps.size() == 1) {
+ parent = parentOps.get(0);
+ if (!(parent instanceof ReduceSinkOperator)) {
+ parentOps = parent.getParentOperators();
continue;
}
- }
- // Not compute_stats
- Set<ReduceSinkOperator> rsOps =
OperatorUtils.findOperatorsUpstream(parentOfFS, ReduceSinkOperator.class);
- if (rsOps.isEmpty()) {
- continue;
- }
- // Skip setting if the bucketing version is not set in FileSinkOp.
- if (fsOp.getConf().getTableInfo().isSetBucketingVersion()) {
-
rsOps.iterator().next().setBucketingVersion(fsOp.getConf().getTableInfo().getBucketingVersion());
+ // Found the target RSOp
+
parent.setBucketingVersion(fsOp.getConf().getTableInfo().getBucketingVersion());
+ break;
}
}
}
diff --git a/ql/src/test/queries/clientpositive/murmur_hash_migration.q
b/ql/src/test/queries/clientpositive/murmur_hash_migration.q
index 2b8da9f6836..7acea46b62b 100644
--- a/ql/src/test/queries/clientpositive/murmur_hash_migration.q
+++ b/ql/src/test/queries/clientpositive/murmur_hash_migration.q
@@ -59,3 +59,38 @@ select t1.key, t1.value, t2.key, t2.value from
srcbucket_mapjoin_n18 t1, srcbuck
explain
select t1.key, t1.value, t2.key, t2.value from tab_part_n11 t1, tab_n10 t2
where t1.key = t2.key order by t1.key, t1.value, t2.key, t2.value;
select t1.key, t1.value, t2.key, t2.value from tab_part_n11 t1, tab_n10 t2
where t1.key = t2.key order by t1.key, t1.value, t2.key, t2.value;
+
+
+set hive.optimize.ppd=true;
+set hive.optimize.index.filter=true;
+set hive.tez.bucket.pruning=true;
+set hive.fetch.task.conversion=none;
+set hive.support.concurrency=true;
+set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager;
+
+set hive.exec.dynamic.partition.mode=nonstrict;
+
+create transactional table acid_ptn_bucket1 (a int, b int) partitioned by(ds
string)
+clustered by (a) into 2 buckets stored as ORC
+TBLPROPERTIES('bucketing_version'='1', 'transactional'='true',
'transactional_properties'='default');
+
+explain extended insert into acid_ptn_bucket1 partition (ds)
values(1,2,'today'),(1,3,'today'),(1,4,'yesterday'),(2,2,'yesterday'),(2,3,'today'),(2,4,'today');
+insert into acid_ptn_bucket1 partition (ds)
values(1,2,'today'),(1,3,'today'),(1,4,'yesterday'),(2,2,'yesterday'),(2,3,'today'),(2,4,'today');
+
+alter table acid_ptn_bucket1 add columns(c int);
+
+insert into acid_ptn_bucket1 partition (ds)
values(3,2,1000,'yesterday'),(3,3,1001,'today'),(3,4,1002,'yesterday'),(4,2,1003,'today'),
(4,3,1004,'yesterday'),(4,4,1005,'today');
+select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid = 536870912 and
ds='today' order by a;
+select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid = 536936448 and
ds='today' order by a;
+
+--create table s1 as select key, value from src where value > 2 group by key,
value limit 10;
+--create table s2 as select key, '45' from src s2 where key > 1 group by key
limit 10;
+
+create table s1 (key int, value int) stored as ORC;
+create table s2 (key int, value int) stored as ORC;
+
+insert into s1 values(111, 33), (10, 45), (103, 44), (129, 34), (128, 11);
+insert into s2 values(10, 45), (100, 45), (103, 44), (110, 12), (128, 34),
(117, 71);
+insert into table acid_ptn_bucket1 partition(ds='today') select key,
count(value), key from (select * from s1 union all select * from s2) sub group
by key;
+select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid = 536870912 and
ds='today' order by a;
+select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid = 536936448 and
ds='today' order by a;
diff --git
a/ql/src/test/results/clientpositive/llap/murmur_hash_migration.q.out
b/ql/src/test/results/clientpositive/llap/murmur_hash_migration.q.out
index b2116947bc4..f915d5a9f9a 100644
--- a/ql/src/test/results/clientpositive/llap/murmur_hash_migration.q.out
+++ b/ql/src/test/results/clientpositive/llap/murmur_hash_migration.q.out
@@ -644,3 +644,335 @@ POSTHOOK: Input: default@tab_part_n11@ds=2008-04-08
417 val_417 417 val_417
417 val_417 417 val_417
446 val_446 446 val_446
+PREHOOK: query: create transactional table acid_ptn_bucket1 (a int, b int)
partitioned by(ds string)
+clustered by (a) into 2 buckets stored as ORC
+TBLPROPERTIES('bucketing_version'='1', 'transactional'='true',
'transactional_properties'='default')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@acid_ptn_bucket1
+POSTHOOK: query: create transactional table acid_ptn_bucket1 (a int, b int)
partitioned by(ds string)
+clustered by (a) into 2 buckets stored as ORC
+TBLPROPERTIES('bucketing_version'='1', 'transactional'='true',
'transactional_properties'='default')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@acid_ptn_bucket1
+PREHOOK: query: explain extended insert into acid_ptn_bucket1 partition (ds)
values(1,2,'today'),(1,3,'today'),(1,4,'yesterday'),(2,2,'yesterday'),(2,3,'today'),(2,4,'today')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acid_ptn_bucket1
+POSTHOOK: query: explain extended insert into acid_ptn_bucket1 partition (ds)
values(1,2,'today'),(1,3,'today'),(1,4,'yesterday'),(2,2,'yesterday'),(2,3,'today'),(2,4,'today')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: _dummy_table
+ Row Limit Per Split: 1
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE
Column stats: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions: array(const struct(1,2,'today'),const
struct(1,3,'today'),const struct(1,4,'yesterday'),const
struct(2,2,'yesterday'),const struct(2,3,'today'),const struct(2,4,'today'))
(type: array<struct<col1:int,col2:int,col3:string>>)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 88 Basic stats:
COMPLETE Column stats: COMPLETE
+ UDTF Operator
+ Statistics: Num rows: 1 Data size: 88 Basic stats:
COMPLETE Column stats: COMPLETE
+ function name: inline
+ Select Operator
+ expressions: col1 (type: int), col2 (type: int), col3
(type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 8 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 8 Basic stats:
COMPLETE Column stats: COMPLETE
+ tag: -1
+ value expressions: _col0 (type: int), _col1 (type:
int), _col2 (type: string)
+ auto parallelism: false
+ Execution mode: llap
+ LLAP IO: no inputs
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: dummy_path
+ input format:
org.apache.hadoop.hive.ql.io.NullRowsInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns
+ columns.comments
+ columns.types
+#### A masked pattern was here ####
+ name _dummy_database._dummy_table
+ serialization.ddl struct _dummy_table { }
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.NullStructSerDe
+ serde: org.apache.hadoop.hive.serde2.NullStructSerDe
+
+ input format:
org.apache.hadoop.hive.ql.io.NullRowsInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns
+ columns.comments
+ columns.types
+#### A masked pattern was here ####
+ name _dummy_database._dummy_table
+ serialization.ddl struct _dummy_table { }
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.NullStructSerDe
+ serde: org.apache.hadoop.hive.serde2.NullStructSerDe
+ name: _dummy_database._dummy_table
+ name: _dummy_database._dummy_table
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Reducer 2
+ Execution mode: vectorized, llap
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: int), VALUE._col1 (type: int),
VALUE._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: COMPLETE
+#### A masked pattern was here ####
+ table:
+ input format:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ bucket_count 2
+ bucket_field_name a
+ bucketing_version 1
+ column.name.delimiter ,
+ columns a,b
+ columns.comments
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.acid_ptn_bucket1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct acid_ptn_bucket1 { i32 a, i32
b}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ transactional true
+ transactional_properties default
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.acid_ptn_bucket1
+ TotalFiles: 1
+ Write Type: INSERT
+ GatherStats: true
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds
+ replace: false
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ bucket_count 2
+ bucket_field_name a
+ bucketing_version 1
+ column.name.delimiter ,
+ columns a,b
+ columns.comments
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.acid_ptn_bucket1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct acid_ptn_bucket1 { i32 a, i32 b}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ transactional true
+ transactional_properties default
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.acid_ptn_bucket1
+ Write Type: INSERT
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+#### A masked pattern was here ####
+
+PREHOOK: query: insert into acid_ptn_bucket1 partition (ds)
values(1,2,'today'),(1,3,'today'),(1,4,'yesterday'),(2,2,'yesterday'),(2,3,'today'),(2,4,'today')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acid_ptn_bucket1
+POSTHOOK: query: insert into acid_ptn_bucket1 partition (ds)
values(1,2,'today'),(1,3,'today'),(1,4,'yesterday'),(2,2,'yesterday'),(2,3,'today'),(2,4,'today')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@acid_ptn_bucket1@ds=today
+POSTHOOK: Output: default@acid_ptn_bucket1@ds=yesterday
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).a SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).b SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=yesterday).a SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=yesterday).b SCRIPT []
+PREHOOK: query: alter table acid_ptn_bucket1 add columns(c int)
+PREHOOK: type: ALTERTABLE_ADDCOLS
+PREHOOK: Input: default@acid_ptn_bucket1
+PREHOOK: Output: default@acid_ptn_bucket1
+POSTHOOK: query: alter table acid_ptn_bucket1 add columns(c int)
+POSTHOOK: type: ALTERTABLE_ADDCOLS
+POSTHOOK: Input: default@acid_ptn_bucket1
+POSTHOOK: Output: default@acid_ptn_bucket1
+PREHOOK: query: insert into acid_ptn_bucket1 partition (ds)
values(3,2,1000,'yesterday'),(3,3,1001,'today'),(3,4,1002,'yesterday'),(4,2,1003,'today'),
(4,3,1004,'yesterday'),(4,4,1005,'today')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acid_ptn_bucket1
+POSTHOOK: query: insert into acid_ptn_bucket1 partition (ds)
values(3,2,1000,'yesterday'),(3,3,1001,'today'),(3,4,1002,'yesterday'),(4,2,1003,'today'),
(4,3,1004,'yesterday'),(4,4,1005,'today')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@acid_ptn_bucket1@ds=today
+POSTHOOK: Output: default@acid_ptn_bucket1@ds=yesterday
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).a SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).b SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).c SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=yesterday).a SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=yesterday).b SCRIPT []
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=yesterday).c SCRIPT []
+PREHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid
= 536870912 and ds='today' order by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@acid_ptn_bucket1
+PREHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+POSTHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where
ROW__ID.bucketid = 536870912 and ds='today' order by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@acid_ptn_bucket1
+POSTHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":0} 2
4 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":1} 2
3 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":0} 4
4 1005 today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":1} 4
2 1003 today
+PREHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid
= 536936448 and ds='today' order by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@acid_ptn_bucket1
+PREHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+POSTHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where
ROW__ID.bucketid = 536936448 and ds='today' order by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@acid_ptn_bucket1
+POSTHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":0} 1
3 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":1} 1
2 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":0} 3
3 1001 today
+PREHOOK: query: create table s1 (key int, value int) stored as ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@s1
+POSTHOOK: query: create table s1 (key int, value int) stored as ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@s1
+PREHOOK: query: create table s2 (key int, value int) stored as ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@s2
+POSTHOOK: query: create table s2 (key int, value int) stored as ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@s2
+PREHOOK: query: insert into s1 values(111, 33), (10, 45), (103, 44), (129,
34), (128, 11)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@s1
+POSTHOOK: query: insert into s1 values(111, 33), (10, 45), (103, 44), (129,
34), (128, 11)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@s1
+POSTHOOK: Lineage: s1.key SCRIPT []
+POSTHOOK: Lineage: s1.value SCRIPT []
+PREHOOK: query: insert into s2 values(10, 45), (100, 45), (103, 44), (110,
12), (128, 34), (117, 71)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@s2
+POSTHOOK: query: insert into s2 values(10, 45), (100, 45), (103, 44), (110,
12), (128, 34), (117, 71)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@s2
+POSTHOOK: Lineage: s2.key SCRIPT []
+POSTHOOK: Lineage: s2.value SCRIPT []
+PREHOOK: query: insert into table acid_ptn_bucket1 partition(ds='today')
select key, count(value), key from (select * from s1 union all select * from
s2) sub group by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@s1
+PREHOOK: Input: default@s2
+PREHOOK: Output: default@acid_ptn_bucket1@ds=today
+POSTHOOK: query: insert into table acid_ptn_bucket1 partition(ds='today')
select key, count(value), key from (select * from s1 union all select * from
s2) sub group by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@s1
+POSTHOOK: Input: default@s2
+POSTHOOK: Output: default@acid_ptn_bucket1@ds=today
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).a EXPRESSION
[(s1)s1.FieldSchema(name:key, type:int, comment:null),
(s2)s2.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).b EXPRESSION
[(s1)s1.FieldSchema(name:value, type:int, comment:null),
(s2)s2.FieldSchema(name:value, type:int, comment:null), ]
+POSTHOOK: Lineage: acid_ptn_bucket1 PARTITION(ds=today).c EXPRESSION
[(s1)s1.FieldSchema(name:key, type:int, comment:null),
(s2)s2.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid
= 536870912 and ds='today' order by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@acid_ptn_bucket1
+PREHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+POSTHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where
ROW__ID.bucketid = 536870912 and ds='today' order by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@acid_ptn_bucket1
+POSTHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":0} 2
4 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":1} 2
3 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":0} 4
4 1005 today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":1} 4
2 1003 today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":0} 10
2 10 today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":1} 100
1 100 today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":2} 110
1 110 today
+{"writeid":### Masked writeid ###,"bucketid":536870912,"rowid":3} 128
2 128 today
+PREHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where ROW__ID.bucketid
= 536936448 and ds='today' order by a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@acid_ptn_bucket1
+PREHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+POSTHOOK: query: select ROW__ID, * from acid_ptn_bucket1 where
ROW__ID.bucketid = 536936448 and ds='today' order by a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@acid_ptn_bucket1
+POSTHOOK: Input: default@acid_ptn_bucket1@ds=today
+#### A masked pattern was here ####
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":0} 1
3 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":1} 1
2 NULL today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":0} 3
3 1001 today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":0} 103
2 103 today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":1} 111
1 111 today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":2} 117
1 117 today
+{"writeid":### Masked writeid ###,"bucketid":536936448,"rowid":3} 129
1 129 today
