uros-db commented on code in PR #45643:
URL: https://github.com/apache/spark/pull/45643#discussion_r1565494137
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationStringExpressionsSuite.scala:
##########
@@ -96,6 +95,107 @@ class CollationStringExpressionsSuite
assert(collationMismatch.getErrorClass === "COLLATION_MISMATCH.EXPLICIT")
}
+ test("INSTR check result on explicitly collated strings") {
Review Comment:
Let's try to unify test naming
e.g. `test("Support StringInstr string expression with collation")`if the
test is in CollationStringExpressionsSuite.scala
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationStringExpressionsSuite.scala:
##########
@@ -96,6 +95,107 @@ class CollationStringExpressionsSuite
assert(collationMismatch.getErrorClass === "COLLATION_MISMATCH.EXPLICIT")
}
+ test("INSTR check result on explicitly collated strings") {
+ def testInStr(str: String, substr: String, collationId: Integer, expected:
Integer): Unit = {
+ val string = Literal.create(str, StringType(collationId))
+ val substring = Literal.create(substr, StringType(collationId))
+
+ checkEvaluation(StringInstr(string, substring), expected)
+ }
+
+ var collationId = CollationFactory.collationNameToId("UTF8_BINARY")
+ testInStr("aaads", "Aa", collationId, 0)
+ testInStr("aaaDs", "de", collationId, 0)
+ testInStr("aaads", "ds", collationId, 4)
+ testInStr("xxxx", "", collationId, 1)
+ testInStr("", "xxxx", collationId, 0)
+ // scalastyle:off
+ testInStr("test大千世界X大千世界", "大千", collationId, 5)
+ testInStr("test大千世界X大千世界", "界X", collationId, 8)
+ // scalastyle:on
+
+ collationId = CollationFactory.collationNameToId("UTF8_BINARY_LCASE")
+ testInStr("aaads", "Aa", collationId, 1)
+ testInStr("aaaDs", "de", collationId, 0)
+ testInStr("aaaDs", "ds", collationId, 4)
+ testInStr("xxxx", "", collationId, 1)
+ testInStr("", "xxxx", collationId, 0)
+ // scalastyle:off
+ testInStr("test大千世界X大千世界", "大千", collationId, 5)
+ testInStr("test大千世界X大千世界", "界x", collationId, 8)
+ // scalastyle:on
+
+ collationId = CollationFactory.collationNameToId("UNICODE")
+ testInStr("aaads", "Aa", collationId, 0)
+ testInStr("aaads", "aa", collationId, 1)
+ testInStr("aaads", "de", collationId, 0)
+ testInStr("xxxx", "", collationId, 1)
+ testInStr("", "xxxx", collationId, 0)
+ // scalastyle:off
+ testInStr("test大千世界X大千世界", "界x", collationId, 0)
+ testInStr("test大千世界X大千世界", "界X", collationId, 8)
+ // scalastyle:on
+
+ collationId = CollationFactory.collationNameToId("UNICODE_CI")
+ testInStr("aaads", "AD", collationId, 3)
+ testInStr("aaads", "dS", collationId, 4)
+ // scalastyle:off
+ testInStr("test大千世界X大千世界", "界x", collationId, 8)
+ // scalastyle:on
+ }
+
+ test("FIND_IN_SET check result on explicitly collated strings") {
Review Comment:
Let's try to unify test naming
e.g. `test("Support FindInSet string expression with collation")` if the
test is in CollationStringExpressionsSuite.scala
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
