This is an automated email from the ASF dual-hosted git repository.
rameshkumar 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 9fff198b021 HIVE-28313: Support ambiguous column references when CBO
fallback is disabled (Soumyakanti Das reviewed by Ramesh Kumar)
9fff198b021 is described below
commit 9fff198b0213ae85f2a5b32a895336ad45f027fd
Author: Soumyakanti Das <[email protected]>
AuthorDate: Thu Aug 15 10:41:39 2024 -0700
HIVE-28313: Support ambiguous column references when CBO fallback is
disabled (Soumyakanti Das reviewed by Ramesh Kumar)
---
.../hadoop/hive/ql/parse/SemanticAnalyzer.java | 2 +-
ql/src/test/queries/clientpositive/ambiguous_col.q | 5 ++
.../clientpositive/llap/ambiguous_col.q.out | 80 ++++++++++++++++++++--
3 files changed, 82 insertions(+), 5 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 49bba7256b6..a44def6927c 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
@@ -4078,7 +4078,7 @@ public class SemanticAnalyzer extends
BaseSemanticAnalyzer {
}
assert nonNull(tmp);
if (ensureUniqueCols) {
- if (!output.putWithCheck(tmp[0], tmp[1], null, oColInfo)) {
+ if (!output.putWithCheck(tmp[0], tmp[1], oColInfo.getInternalName(),
oColInfo)) {
throw new CalciteSemanticException("Cannot add column to RR: " +
tmp[0] + "." + tmp[1]
+ " => " + oColInfo + " due to duplication, see previous
warnings",
UnsupportedFeature.Duplicates_in_RR);
diff --git a/ql/src/test/queries/clientpositive/ambiguous_col.q
b/ql/src/test/queries/clientpositive/ambiguous_col.q
index f645ff15197..4f8bc853c46 100644
--- a/ql/src/test/queries/clientpositive/ambiguous_col.q
+++ b/ql/src/test/queries/clientpositive/ambiguous_col.q
@@ -1,15 +1,20 @@
--! qt:dataset:src1
--! qt:dataset:src
set hive.support.quoted.identifiers=none;
+set hive.cbo.fallback.strategy=NEVER;
-- TOK_ALLCOLREF
+explain cbo select * from (select a.key, a.* from (select * from src) a join
(select * from src1) b on (a.key = b.key)) t;
explain select * from (select a.key, a.* from (select * from src) a join
(select * from src1) b on (a.key = b.key)) t;
select * from (select a.key, a.* from (select * from src) a join (select *
from src1) b on (a.key = b.key)) t;
-- DOT
+explain cbo select * from (select a.key, a.`[k].*` from (select * from src) a
join (select * from src1) b on (a.key = b.key)) t;
explain select * from (select a.key, a.`[k].*` from (select * from src) a join
(select * from src1) b on (a.key = b.key)) t;
select * from (select a.key, a.`[k].*` from (select * from src) a join (select
* from src1) b on (a.key = b.key)) t;
-- EXPRESSION
+explain cbo select * from (select a.key, a.key from (select * from src) a join
(select * from src1) b on (a.key = b.key)) t;
explain select * from (select a.key, a.key from (select * from src) a join
(select * from src1) b on (a.key = b.key)) t;
select * from (select a.key, a.key from (select * from src) a join (select *
from src1) b on (a.key = b.key)) t;
+explain cbo select count(*) from (select key, key from src) subq;
explain select count(*) from (select key, key from src) subq;
select count(*) from (select key, key from src) subq;
diff --git a/ql/src/test/results/clientpositive/llap/ambiguous_col.q.out
b/ql/src/test/results/clientpositive/llap/ambiguous_col.q.out
index 2d160858b46..f43bc3bd0d1 100644
--- a/ql/src/test/results/clientpositive/llap/ambiguous_col.q.out
+++ b/ql/src/test/results/clientpositive/llap/ambiguous_col.q.out
@@ -1,3 +1,23 @@
+PREHOOK: query: explain cbo select * from (select a.key, a.* from (select *
from src) a join (select * from src1) b on (a.key = b.key)) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo select * from (select a.key, a.* from (select *
from src) a join (select * from src1) b on (a.key = b.key)) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+CBO PLAN:
+HiveProject(key=[$0], _o__col1=[$0], value=[$1])
+ HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none],
cost=[not available])
+ HiveProject(key=[$0], value=[$1])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, src]], table:alias=[src])
+ HiveProject(key=[$0])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, src1]], table:alias=[src1])
+
PREHOOK: query: explain select * from (select a.key, a.* from (select * from
src) a join (select * from src1) b on (a.key = b.key)) t
PREHOOK: type: QUERY
PREHOOK: Input: default@src
@@ -77,10 +97,10 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col0 (type: string),
_col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 39 Data size: 6942 Basic stats:
COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 10335 Basic stats:
COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 39 Data size: 6942 Basic stats:
COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 10335 Basic stats:
COMPLETE Column stats: COMPLETE
table:
input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -139,6 +159,26 @@ POSTHOOK: Input: default@src1
66 66 val_66
98 98 val_98
98 98 val_98
+PREHOOK: query: explain cbo select * from (select a.key, a.`[k].*` from
(select * from src) a join (select * from src1) b on (a.key = b.key)) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo select * from (select a.key, a.`[k].*` from
(select * from src) a join (select * from src1) b on (a.key = b.key)) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+CBO PLAN:
+HiveProject(key=[$0], _o__col1=[$0])
+ HiveJoin(condition=[=($0, $1)], joinType=[inner], algorithm=[none],
cost=[not available])
+ HiveProject(key=[$0])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, src]], table:alias=[src])
+ HiveProject(key=[$0])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, src1]], table:alias=[src1])
+
PREHOOK: query: explain select * from (select a.key, a.`[k].*` from (select *
from src) a join (select * from src1) b on (a.key = b.key)) t
PREHOOK: type: QUERY
PREHOOK: Input: default@src
@@ -217,10 +257,10 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 39 Data size: 3393 Basic stats:
COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 6786 Basic stats:
COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 39 Data size: 3393 Basic stats:
COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 6786 Basic stats:
COMPLETE Column stats: COMPLETE
table:
input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -279,6 +319,26 @@ POSTHOOK: Input: default@src1
66 66
98 98
98 98
+PREHOOK: query: explain cbo select * from (select a.key, a.key from (select *
from src) a join (select * from src1) b on (a.key = b.key)) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo select * from (select a.key, a.key from (select *
from src) a join (select * from src1) b on (a.key = b.key)) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+CBO PLAN:
+HiveProject(key=[$0], _o__col1=[$0])
+ HiveJoin(condition=[=($0, $1)], joinType=[inner], algorithm=[none],
cost=[not available])
+ HiveProject(key=[$0])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, src]], table:alias=[src])
+ HiveProject(key=[$0])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, src1]], table:alias=[src1])
+
PREHOOK: query: explain select * from (select a.key, a.key from (select * from
src) a join (select * from src1) b on (a.key = b.key)) t
PREHOOK: type: QUERY
PREHOOK: Input: default@src
@@ -419,6 +479,18 @@ POSTHOOK: Input: default@src1
66 66
98 98
98 98
+PREHOOK: query: explain cbo select count(*) from (select key, key from src)
subq
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo select count(*) from (select key, key from src)
subq
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+CBO PLAN:
+HiveAggregate(group=[{}], agg#0=[count()])
+ HiveTableScan(table=[[default, src]], table:alias=[src])
+
PREHOOK: query: explain select count(*) from (select key, key from src) subq
PREHOOK: type: QUERY
PREHOOK: Input: default@src