This is an automated email from the ASF dual-hosted git repository.
wenchen pushed a commit to branch branch-3.0
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.0 by this push:
new c157fa3 [SPARK-33372][SQL] Fix InSet bucket pruning
c157fa3 is described below
commit c157fa36e8e1aa18dcf87b6c774970b8122df0dc
Author: Yuming Wang <yumw...@ebay.com>
AuthorDate: Mon Nov 9 08:32:51 2020 +0000
[SPARK-33372][SQL] Fix InSet bucket pruning
### What changes were proposed in this pull request?
This pr fix `InSet` bucket pruning because of it's values should not be
`Literal`:
https://github.com/apache/spark/blob/cbd3fdea62dab73fc4a96702de8fd1f07722da66/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala#L253-L255
### Why are the changes needed?
Fix bug.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Unit test and manual test:
```scala
spark.sql("select id as a, id as b from range(10000)").write.bucketBy(100,
"a").saveAsTable("t")
spark.sql("select * from t where a in (1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
11)").show
```
Before this PR | After this PR
-- | --
|
Closes #30279 from wangyum/SPARK-33372.
Authored-by: Yuming Wang <yumw...@ebay.com>
Signed-off-by: Wenchen Fan <wenc...@databricks.com>
(cherry picked from commit 69799c514ff9874c57bf94d4de21ea4cd0cbbf8d)
Signed-off-by: Wenchen Fan <wenc...@databricks.com>
---
.../apache/spark/sql/execution/datasources/FileSourceStrategy.scala | 5 ++---
.../test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala | 2 +-
2 files changed, 3 insertions(+), 4 deletions(-)
diff --git
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
index b1e03fe..4b9e0c6 100644
---
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
+++
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
@@ -89,9 +89,8 @@ object FileSourceStrategy extends Strategy with Logging {
case expressions.In(a: Attribute, list)
if list.forall(_.isInstanceOf[Literal]) && a.name == bucketColumnName
=>
getBucketSetFromIterable(a, list.map(e => e.eval(EmptyRow)))
- case expressions.InSet(a: Attribute, hset)
- if hset.forall(_.isInstanceOf[Literal]) && a.name == bucketColumnName
=>
- getBucketSetFromIterable(a, hset.map(e =>
expressions.Literal(e).eval(EmptyRow)))
+ case expressions.InSet(a: Attribute, hset) if a.name == bucketColumnName
=>
+ getBucketSetFromIterable(a, hset)
case expressions.IsNull(a: Attribute) if a.name == bucketColumnName =>
getBucketSetFromValue(a, null)
case expressions.And(left, right) =>
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala
index 558bfd7..df8ca33 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala
@@ -188,7 +188,7 @@ abstract class BucketedReadSuite extends QueryTest with
SQLTestUtils {
// Case 4: InSet
val inSetExpr = expressions.InSet($"j".expr,
- Set(bucketValue, bucketValue + 1, bucketValue + 2, bucketValue +
3).map(lit(_).expr))
+ Set(bucketValue, bucketValue + 1, bucketValue + 2, bucketValue + 3))
checkPrunedAnswers(
bucketSpec,
bucketValues = Seq(bucketValue, bucketValue + 1, bucketValue + 2,
bucketValue + 3),
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
