jovanpavl-db commented on code in PR #48222:
URL: https://github.com/apache/spark/pull/48222#discussion_r1773184318
##########
common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationFactory.java:
##########
@@ -661,58 +775,111 @@ private static int collationNameToId(
}
if (lastPos == -1) {
throw collationInvalidNameException(originalName);
- } else {
- String locale = collationName.substring(0, lastPos);
- int collationId =
ICULocaleToId.get(ICULocaleMapUppercase.get(locale));
-
- // Try all combinations of AS/AI and CS/CI.
- CaseSensitivity caseSensitivity;
- AccentSensitivity accentSensitivity;
- if (collationName.equals(locale) ||
- collationName.equals(locale + "_AS") ||
- collationName.equals(locale + "_CS") ||
- collationName.equals(locale + "_AS_CS") ||
- collationName.equals(locale + "_CS_AS")
- ) {
- caseSensitivity = CaseSensitivity.CS;
- accentSensitivity = AccentSensitivity.AS;
- } else if (collationName.equals(locale + "_CI") ||
- collationName.equals(locale + "_AS_CI") ||
- collationName.equals(locale + "_CI_AS")) {
- caseSensitivity = CaseSensitivity.CI;
- accentSensitivity = AccentSensitivity.AS;
- } else if (collationName.equals(locale + "_AI") ||
- collationName.equals(locale + "_CS_AI") ||
- collationName.equals(locale + "_AI_CS")) {
- caseSensitivity = CaseSensitivity.CS;
- accentSensitivity = AccentSensitivity.AI;
- } else if (collationName.equals(locale + "_AI_CI") ||
- collationName.equals(locale + "_CI_AI")) {
- caseSensitivity = CaseSensitivity.CI;
- accentSensitivity = AccentSensitivity.AI;
- } else {
- throw collationInvalidNameException(originalName);
- }
+ }
+ String locale = collationName.substring(0, lastPos);
+ int collationId = ICULocaleToId.get(ICULocaleMapUppercase.get(locale));
+ collationId = SpecifierUtils.setSpecValue(collationId,
+ IMPLEMENTATION_PROVIDER_OFFSET, ImplementationProvider.ICU);
- // Build collation ID from computed specifiers.
- collationId = SpecifierUtils.setSpecValue(collationId,
- IMPLEMENTATION_PROVIDER_OFFSET, ImplementationProvider.ICU);
- collationId = SpecifierUtils.setSpecValue(collationId,
- CASE_SENSITIVITY_OFFSET, caseSensitivity);
- collationId = SpecifierUtils.setSpecValue(collationId,
- ACCENT_SENSITIVITY_OFFSET, accentSensitivity);
+ // No other specifiers present.
+ if(collationName.equals(locale)){
return collationId;
}
+ if(collationName.charAt(locale.length()) != '_'){
+ throw collationInvalidNameException(originalName);
+ }
+ // Extract remaining specifiers and trim "_" separator.
+ String remainingSpecifiers = collationName.substring(lastPos + 1);
+
+ // Initialize default specifier flags.
+ boolean isCaseSpecifierSet = false;
+ boolean isAccentSpecifierSet = false;
+ boolean isSpaceTrimmingSpecifierSet = false;
+ CaseSensitivity caseSensitivity = CaseSensitivity.CS; //
Default: Case Sensitive
+ AccentSensitivity accentSensitivity = AccentSensitivity.AS; //
Default: Accent Sensitive
+ SpaceTrimming spaceTrimming = SpaceTrimming.NONE; // Default:
No Trim
+
+ String[] specifiers = remainingSpecifiers.split("_");
+
+ // Iterate through specifiers and set corresponding flags
+ for (String specifier : specifiers) {
+ switch (specifier) {
+ case "CI":
Review Comment:
Very nice catch, thanks!
--
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]