This is an automated email from the ASF dual-hosted git repository.
peter-toth pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new d2693b5baf5c [SPARK-52246][SQL][TEST] Add bucket transform regression
test for one-side shuffle with join key tail of partition keys
d2693b5baf5c is described below
commit d2693b5baf5cd7c449a521e93564fac4b296a167
Author: naveenp2708 <[email protected]>
AuthorDate: Sun Jul 26 10:16:06 2026 +0200
[SPARK-52246][SQL][TEST] Add bucket transform regression test for one-side
shuffle with join key tail of partition keys
### What changes were proposed in this pull request?
Add a regression test to `KeyGroupedPartitioningSuite` for the scenario
reported in [SPARK-52246](https://issues.apache.org/jira/browse/SPARK-52246)
(test adapted from the reproduction in the JIRA description): a
storage-partitioned join where one side is auto-shuffled, the partitioned side
uses a bucket transform, and the partition key is the tail of the join keys.
### Why are the changes needed?
SPARK-52246 reported silent incorrect results (empty join output) for this
scenario on 4.0.0/4.0.1. The defect was fixed by SPARK-54439, but the tests
added there cover identity and years transforms only, not bucket. This locks in
coverage for the bucket case.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
New test passes on master; verified it fails on v4.0.1 (pre-SPARK-54439),
reproducing the original wrong results.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #57442 from naveenp2708/repro-SPARK-52246.
Authored-by: naveenp2708 <[email protected]>
Signed-off-by: Peter Toth <[email protected]>
---
.../connector/KeyGroupedPartitioningSuite.scala | 26 ++++++++++++++++++++++
1 file changed, 26 insertions(+)
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/connector/KeyGroupedPartitioningSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/connector/KeyGroupedPartitioningSuite.scala
index e765b8630189..ceaac9729ddd 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/connector/KeyGroupedPartitioningSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/connector/KeyGroupedPartitioningSuite.scala
@@ -2724,6 +2724,32 @@ class KeyGroupedPartitioningSuite extends
DistributionAndOrderingSuiteBase with
}
}
+ test("SPARK-52246: one-side shuffle with join key tail part of the partition
keys") {
+ val items_partitions = Array(bucket(2, "id"))
+ createTable(items, itemsColumns, items_partitions)
+
+ sql(s"INSERT INTO testcat.ns.$items VALUES " +
+ "(1, 'aa', 40.0, cast('2020-01-01' as timestamp)), " +
+ "(1, 'aa', 30.0, cast('2020-01-02' as timestamp)), " +
+ "(3, 'bb', 10.0, cast('2020-01-01' as timestamp)), " +
+ "(4, 'cc', 15.5, cast('2020-02-01' as timestamp))")
+
+ createTable(purchases, purchasesColumns, Array.empty)
+ sql(s"INSERT INTO testcat.ns.$purchases VALUES " +
+ "(1, 42.0, cast('2020-01-01' as timestamp)), " +
+ "(1, 89.0, cast('2020-01-03' as timestamp)), " +
+ "(3, 19.5, cast('2020-02-01' as timestamp)), " +
+ "(5, 26.0, cast('2023-01-01' as timestamp)), " +
+ "(6, 50.0, cast('2023-02-01' as timestamp))")
+
+ withSQLConf(SQLConf.V2_BUCKETING_SHUFFLE_ENABLED.key -> "true") {
+ val df = createJoinTestDF(Seq("arrive_time" -> "time", "id" ->
"item_id"))
+ val shuffles = collectShuffles(df.queryExecution.executedPlan)
+ assert(shuffles.size == 1, "SPJ should be triggered")
+ checkAnswer(df, Seq(Row(1, "aa", 40.0, 42.0)))
+ }
+ }
+
test("SPARK-48949: test partition filters inner join") {
val items_partitions = Array(bucket(8, "id"), days("arrive_time"))
createTable(items, itemsColumns, items_partitions)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
