mihailom-db commented on code in PR #48087:
URL: https://github.com/apache/spark/pull/48087#discussion_r1758249488
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala:
##########
@@ -1625,38 +1625,38 @@ class CollationSuite extends DatasourceV2SQLBase with
AdaptiveSparkPlanHelper {
}
}
- test("show collations") {
- assert(sql("SHOW COLLATIONS").collect().length >= 562)
+ test("TVF string_collations()") {
+ assert(sql("SELECT * FROM string_collations()").collect().length >= 562)
// verify that the output ordering is as expected (UTF8_BINARY,
UTF8_LCASE, etc.)
- val df = sql("SHOW COLLATIONS").limit(10)
+ val df = sql("SELECT * FROM string_collations() limit 10")
checkAnswer(df,
Seq(Row("SYSTEM", "BUILTIN", "UTF8_BINARY", null, null,
"ACCENT_SENSITIVE", "CASE_SENSITIVE", "NO_PAD", null),
- Row("SYSTEM", "BUILTIN", "UTF8_LCASE", null, null,
- "ACCENT_SENSITIVE", "CASE_INSENSITIVE", "NO_PAD", null),
- Row("SYSTEM", "BUILTIN", "UNICODE", "", "",
- "ACCENT_SENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
- Row("SYSTEM", "BUILTIN", "UNICODE_AI", "", "",
- "ACCENT_SENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0"),
- Row("SYSTEM", "BUILTIN", "UNICODE_CI", "", "",
- "ACCENT_INSENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
- Row("SYSTEM", "BUILTIN", "UNICODE_CI_AI", "", "",
- "ACCENT_INSENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0"),
- Row("SYSTEM", "BUILTIN", "af", "Afrikaans", "",
- "ACCENT_SENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
- Row("SYSTEM", "BUILTIN", "af_AI", "Afrikaans", "",
- "ACCENT_SENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0"),
- Row("SYSTEM", "BUILTIN", "af_CI", "Afrikaans", "",
- "ACCENT_INSENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
- Row("SYSTEM", "BUILTIN", "af_CI_AI", "Afrikaans", "",
- "ACCENT_INSENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0")))
-
- checkAnswer(sql("SHOW COLLATIONS LIKE '*UTF8_BINARY*'"),
+ Row("SYSTEM", "BUILTIN", "UTF8_LCASE", null, null,
+ "ACCENT_SENSITIVE", "CASE_INSENSITIVE", "NO_PAD", null),
+ Row("SYSTEM", "BUILTIN", "UNICODE", "", "",
+ "ACCENT_SENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
+ Row("SYSTEM", "BUILTIN", "UNICODE_AI", "", "",
+ "ACCENT_SENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0"),
+ Row("SYSTEM", "BUILTIN", "UNICODE_CI", "", "",
+ "ACCENT_INSENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
+ Row("SYSTEM", "BUILTIN", "UNICODE_CI_AI", "", "",
+ "ACCENT_INSENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0"),
+ Row("SYSTEM", "BUILTIN", "af", "Afrikaans", "",
+ "ACCENT_SENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
+ Row("SYSTEM", "BUILTIN", "af_AI", "Afrikaans", "",
+ "ACCENT_SENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0"),
+ Row("SYSTEM", "BUILTIN", "af_CI", "Afrikaans", "",
+ "ACCENT_INSENSITIVE", "CASE_SENSITIVE", "NO_PAD", "75.1.0.0"),
+ Row("SYSTEM", "BUILTIN", "af_CI_AI", "Afrikaans", "",
+ "ACCENT_INSENSITIVE", "CASE_INSENSITIVE", "NO_PAD", "75.1.0.0")))
+
+ checkAnswer(sql("SELECT * FROM string_collations() WHERE COLLATION_NAME
LIKE '%UTF8_BINARY%'"),
Row("SYSTEM", "BUILTIN", "UTF8_BINARY", null, null,
"ACCENT_SENSITIVE", "CASE_SENSITIVE", "NO_PAD", null))
- checkAnswer(sql("SHOW COLLATIONS '*zh_Hant_HKG*'"),
+ checkAnswer(sql("SELECT * FROM string_collations() WHERE COLLATION_NAME
LIKE '%zh_Hant_HKG%'"),
Review Comment:
Could you please do some test where we have for example `WHERE country
collate UTF8_LCASE like '%china%'` so that we know we can actually use search
on other fields, which is one of the main reasons we added this functionality
over SHOW COLLATIONS.
--
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]
