miland-db commented on code in PR #45643: URL: https://github.com/apache/spark/pull/45643#discussion_r1549579283
########## common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java: ########## @@ -549,6 +549,45 @@ public int findInSet(UTF8String match) { return 0; } + public int findInSet(UTF8String match, int collationId) { + if (CollationFactory.fetchCollation(collationId).supportsBinaryEquality) { + return this.findInSet(match); + } + if (collationId == CollationFactory.UTF8_BINARY_LCASE_COLLATION_ID) { + return this.toLowerCase().findInSet(match.toLowerCase()); + } + return collationAwareFindInSet(match, collationId); +} + + private int collationAwareFindInSet(UTF8String match, int collationId) { + if (match.contains(COMMA_UTF8)) { + return 0; + } + + StringSearch stringSearch = CollationFactory.getStringSearch(this, match, collationId); + + String setString = this.toString(); + int wordStart = 0; + while ((wordStart = stringSearch.next()) != StringSearch.DONE) { + boolean isValidStart = wordStart == 0 || setString.charAt(wordStart - 1) == ','; + boolean isValidEnd = wordStart + stringSearch.getMatchLength() == setString.length() + || setString.charAt(wordStart + stringSearch.getMatchLength()) == ','; + + if (isValidStart && isValidEnd) { + int pos = 0; + for (int i = 0; i < setString.length() && i < wordStart; i++) { + if (setString.charAt(i) == ',') { + pos++; + } + } + + return pos + 1; Review Comment: I think it is specific for this case because we don't need methods like this in other places: `private int countBefore(UTF8String pattern, int collationId, int end)` `private int countAfter(UTF8String pattern, int collationId, int start)` Maybe if we encounter such a case, we can adapt code then. -- 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