uros-db commented on code in PR #47040:
URL: https://github.com/apache/spark/pull/47040#discussion_r1651019921
##########
common/unsafe/src/test/scala/org/apache/spark/unsafe/types/CollationFactorySuite.scala:
##########
@@ -91,37 +91,35 @@ class CollationFactorySuite extends AnyFunSuite with
Matchers { // scalastyle:ig
test("fetch invalid UTF8_BINARY and ICU root locale collation names") {
Seq(
- "UTF8_BINARY_CS",
- "UTF8_BINARY_AS",
- "UTF8_BINARY_CS_AS",
- "UTF8_BINARY_AS_CS",
- "UTF8_BINARY_CI",
- "UTF8_BINARY_AI",
- "UTF8_BINARY_CI_AI",
- "UTF8_BINARY_AI_CI",
- "UTF8_BS",
- "BINARY_UTF8",
- "UTF8_BINARY_A",
- "UNICODE_X",
- "UNICODE_CI_X",
- "UNICODE_LCASE_X",
- "UTF8_UNICODE",
- "UTF8_BINARY_UNICODE",
- "CI_UNICODE",
- "LCASE_UNICODE",
- "UNICODE_UNSPECIFIED",
- "UNICODE_CI_UNSPECIFIED",
- "UNICODE_UNSPECIFIED_CI_UNSPECIFIED",
- "UNICODE_INDETERMINATE",
- "UNICODE_CI_INDETERMINATE"
- ).foreach(collationName => {
- val error = intercept[SparkException] {
- fetchCollation(collationName)
- }
-
+ ("UTF8_BINARY_CS", "UTF8_BINARY"),
+ ("UTF8_BINARY_AS", "UTF8_BINARY"), // this should be UNICODE_AS
+ ("UTF8_BINARY_CS_AS","UTF8_BINARY"), // this should be UNICODE_CS_AS
+ ("UTF8_BINARY_AS_CS","UTF8_BINARY"),
+ ("UTF8_BINARY_CI","UTF8_BINARY"),
+ ("UTF8_BINARY_AI","UTF8_BINARY"),
+ ("UTF8_BINARY_CI_AI","UTF8_BINARY"),
+ ("UTF8_BINARY_AI_CI","UTF8_BINARY"),
+ ("UTF8_BS","UTF8_LCASE"),
+ ("BINARY_UTF8","ar_SAU"),
+ ("UTF8_BINARY_A","UTF8_BINARY"),
+ ("UNICODE_X","UNICODE"),
+ ("UNICODE_CI_X","UNICODE"),
+ ("UNICODE_LCASE_X","UNICODE"),
+ ("UTF8_UNICODE","UTF8_LCASE"),
+ ("UTF8_BINARY_UNICODE","UTF8_BINARY"),
+ ("CI_UNICODE", "UNICODE"),
Review Comment:
for possible future improvement: could we maybe modify the proposal choice
so that we get "UNICODE_CI" here?
for example, by adding some sort of second criteria (apart from Levenshtein)
--
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]