uros-db commented on code in PR #45421: URL: https://github.com/apache/spark/pull/45421#discussion_r1516381847
########## common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java: ########## @@ -384,27 +387,47 @@ public boolean startsWith(final UTF8String prefix) { } public boolean startsWith(final UTF8String prefix, int collationId) { - if (CollationFactory.fetchCollation(collationId).isBinaryCollation) { + if (collationId == CollationFactory.DEFAULT_COLLATION_ID) { return this.startsWith(prefix); } if (collationId == CollationFactory.LOWERCASE_COLLATION_ID) { return this.toLowerCase().startsWith(prefix.toLowerCase()); } - return matchAt(prefix, 0, collationId); + if (prefix.numBytes == 0 || this.numBytes == 0) return prefix.numBytes==0; + + String prefixString = StandardCharsets.UTF_8.decode(prefix.getByteBuffer()).toString(), + patternString = StandardCharsets.UTF_8.decode(this.getByteBuffer()).toString(); + + StringSearch search = new StringSearch(prefixString, + new StringCharacterIterator(patternString), + (RuleBasedCollator) CollationFactory.fetchCollation(collationId).collator + ); + + return search.first()==0; } public boolean endsWith(final UTF8String suffix) { return matchAt(suffix, numBytes - suffix.numBytes); } public boolean endsWith(final UTF8String suffix, int collationId) { - if (CollationFactory.fetchCollation(collationId).isBinaryCollation) { + if (collationId == CollationFactory.DEFAULT_COLLATION_ID) { Review Comment: (see comment above) -- 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