uros-db commented on code in PR #46720:
URL: https://github.com/apache/spark/pull/46720#discussion_r1612933590
##########
common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java:
##########
@@ -135,22 +135,90 @@ public static UTF8String lowercaseReplace(final
UTF8String src, final UTF8String
return buf.build();
}
+ /**
+ * Convert the input string to uppercase using the ICU root locale rules.
+ *
+ * @param target the input string
+ * @return the uppercase string
+ */
+ public static UTF8String toUpperCase(final UTF8String target) {
+ return UTF8String.fromString(toUpperCase(target.toString()));
+ }
+ public static String toUpperCase(final String target) {
+ return UCharacter.toUpperCase(target);
+ }
+
+ /**
+ * Convert the input string to uppercase using the specified ICU collation
rules.
+ *
+ * @param target the input string
+ * @return the uppercase string
+ */
+ public static UTF8String toUpperCase(final UTF8String target, final int
collationId) {
+ return UTF8String.fromString(toUpperCase(target.toString(), collationId));
+ }
public static String toUpperCase(final String target, final int collationId)
{
ULocale locale = CollationFactory.fetchCollation(collationId)
.collator.getLocale(ULocale.ACTUAL_LOCALE);
return UCharacter.toUpperCase(locale, target);
}
+ /**
+ * Convert the input string to lowercase using the ICU root locale rules.
+ *
+ * @param target the input string
+ * @return the lowercase string
+ */
+ public static UTF8String toLowerCase(final UTF8String target) {
+ return UTF8String.fromString(toLowerCase(target.toString()));
+ }
+ public static String toLowerCase(final String target) {
+ return UCharacter.toLowerCase(target);
+ }
+
+ /**
+ * Convert the input string to lowercase using the specified ICU collation
rules.
+ *
+ * @param target the input string
+ * @return the lowercase string
+ */
+ public static UTF8String toLowerCase(final UTF8String target, final int
collationId) {
+ return UTF8String.fromString(toLowerCase(target.toString(), collationId));
+ }
public static String toLowerCase(final String target, final int collationId)
{
ULocale locale = CollationFactory.fetchCollation(collationId)
.collator.getLocale(ULocale.ACTUAL_LOCALE);
return UCharacter.toLowerCase(locale, target);
}
+ /**
+ * Convert the input string to lowercase using the ICU root locale rules.
+ *
+ * @param target the input string
+ * @return the lowercase string
+ */
+ public static UTF8String toTitleCase(final UTF8String target) {
+ return UTF8String.fromString(toTitleCase(target.toString()));
+ }
+ public static String toTitleCase(final String target) {
+ BreakIterator wordIterator = BreakIterator.getWordInstance();
+ return UCharacter.toTitleCase(target, wordIterator);
+ }
Review Comment:
agreed, removing
--
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]
