MaxGekk commented on code in PR #45436:
URL: https://github.com/apache/spark/pull/45436#discussion_r1518208382
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala:
##########
@@ -438,6 +438,39 @@ class CollationSuite extends DatasourceV2SQLBase with
AdaptiveSparkPlanHelper {
}
}
+ test("test concurrently running aggregates") {
+ // generating ICU sort keys is not thread-safe by default so this should
fail
+ // if we don't handle the concurrency properly on Collator level
+
+ for (_ <- 1 to 100) {
+ Seq(
+ ("ucs_basic", Seq("AAA", "aaa"), Seq(Row(1, "AAA"), Row(1, "aaa"))),
+ ("ucs_basic", Seq("aaa", "aaa"), Seq(Row(2, "aaa"))),
+ ("ucs_basic", Seq("aaa", "bbb"), Seq(Row(1, "aaa"), Row(1, "bbb"))),
+ ("ucs_basic_lcase", Seq("aaa", "aaa"), Seq(Row(2, "aaa"))),
+ ("ucs_basic_lcase", Seq("AAA", "aaa"), Seq(Row(2, "AAA"))),
+ ("ucs_basic_lcase", Seq("aaa", "bbb"), Seq(Row(1, "aaa"), Row(1,
"bbb"))),
+ ("unicode", Seq("AAA", "aaa"), Seq(Row(1, "AAA"), Row(1, "aaa"))),
+ ("unicode", Seq("aaa", "aaa"), Seq(Row(2, "aaa"))),
+ ("unicode", Seq("aaa", "bbb"), Seq(Row(1, "aaa"), Row(1, "bbb"))),
+ ("unicode_CI", Seq("aaa", "aaa"), Seq(Row(2, "aaa"))),
+ ("unicode_CI", Seq("AAA", "aaa"), Seq(Row(2, "AAA"))),
+ ("unicode_CI", Seq("aaa", "bbb"), Seq(Row(1, "aaa"), Row(1, "bbb")))
+ ).foreach {
Review Comment:
How this sequential execution proofs the fix? Maybe use a parallel
collection?
--
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]
