viirya commented on code in PR #53142:
URL: https://github.com/apache/spark/pull/53142#discussion_r2547578772
##########
sql/core/src/test/scala/org/apache/spark/sql/connector/KeyGroupedPartitioningSuite.scala:
##########
@@ -2771,4 +2771,34 @@ class KeyGroupedPartitioningSuite extends
DistributionAndOrderingSuiteBase {
}
}
}
+
+ test("SPARK-54439: KeyGroupedPartitioning and join key size mismatch") {
+ val items_partitions = Array(identity("id"))
+ createTable(items, itemsColumns, items_partitions)
+
+ sql(s"INSERT INTO testcat.ns.$items VALUES " +
+ "(1, 'aa', 40.0, cast('2020-01-01' as timestamp)), " +
+ "(3, 'bb', 10.0, cast('2020-01-01' as timestamp)), " +
+ "(4, 'cc', 15.5, cast('2020-02-01' as timestamp))")
+
+ createTable(purchases, purchasesColumns, Array.empty)
+ sql(s"INSERT INTO testcat.ns.$purchases VALUES " +
+ "(1, 42.0, cast('2020-01-01' as timestamp)), " +
+ "(3, 19.5, cast('2020-02-01' as timestamp))")
+
+ Seq(true, false).foreach { shuffle =>
+ withSQLConf(SQLConf.V2_BUCKETING_SHUFFLE_ENABLED.key ->
shuffle.toString) {
+ val df = createJoinTestDF(Seq("arrive_time" -> "time", "id" ->
"item_id"))
+ val shuffles = collectShuffles(df.queryExecution.executedPlan)
+ if (shuffle) {
+ assert(shuffles.size == 1, "only shuffle one side not report
partitioning")
+ } else {
+ assert(shuffles.size == 2, "should add two side shuffle when
bucketing shuffle one side" +
+ " is not enabled")
+ }
+
+ checkAnswer(df, Seq(Row(1, "aa", 40.0, 42.0)))
Review Comment:
Hmm, this looks like a correctness bug.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
