mihailom-db commented on code in PR #45819:
URL: https://github.com/apache/spark/pull/45819#discussion_r1555542892
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala:
##########
@@ -645,6 +646,34 @@ class CollationSuite extends DatasourceV2SQLBase with
AdaptiveSparkPlanHelper {
},
errorClass = "COLLATION_MISMATCH.IMPLICIT"
)
+
+ // check if substring passes through implicit collation
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(s"SELECT substr('a' COLLATE UNICODE, 0, 1) == substr('b' COLLATE
UNICODE_CI, 0, 1)")
+ },
+ errorClass = "COLLATION_MISMATCH.IMPLICIT"
+ )
+
+ checkAnswer(spark.sql("SELECT collation(:var1 || :var2)",
+ Map(
+ "var1" -> Literal.create("a", StringType(1)),
+ "var2" -> Literal.create("b", StringType(2))
+ )
+ ),
+ Seq(Row("UTF8_BINARY"))
+ )
+
+ withSQLConf(SqlApiConf.DEFAULT_COLLATION -> "UNICODE") {
+ checkAnswer(spark.sql("SELECT collation(:var1 || :var2)",
+ Map(
+ "var1" -> Literal.create("a", StringType(1)),
+ "var2" -> Literal.create("b", StringType(2))
+ )
+ ),
+ Seq(Row("UNICODE"))
+ )
+ }
Review Comment:
@srielau Is this the expected behaviour? Apparently we can pass different
collations to parameters. I understood that the behaviour should be if
StringType has priority of default then it has to have session level default
collation, as otherwise we might have different collations with same default
priority, which is not covered by design.
--
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]
