dbatomic commented on code in PR #46722:
URL: https://github.com/apache/spark/pull/46722#discussion_r1620584813
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala:
##########
@@ -1046,6 +1046,211 @@ class CollationSuite extends DatasourceV2SQLBase with
AdaptiveSparkPlanHelper {
})
}
+ test("hash join should be used for arrays of collated strings") {
+ val t1 = "T_1"
+ val t2 = "T_2"
+
+ case class HashJoinTestCase[R](collation: String, result: R)
+ val testCases = Seq(
+ HashJoinTestCase("UTF8_BINARY",
+ Seq(Row(Seq("aa"), 1, Seq("aa"), 2))),
+ HashJoinTestCase("UTF8_BINARY_LCASE",
+ Seq(Row(Seq("aa"), 1, Seq("AA"), 2), Row(Seq("aa"), 1, Seq("aa"), 2))),
+ HashJoinTestCase("UNICODE",
+ Seq(Row(Seq("aa"), 1, Seq("aa"), 2))),
+ HashJoinTestCase("UNICODE_CI",
Review Comment:
Can we start adding at least one locale + case insensitive + accent
insensitive variation in tests? E.g. I would like to see if things work
correctly for SRB_CI_AI, SRB_CS_AS, SRB_CI_AS and SRB_CS_AI.
--
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]
