Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/6804#discussion_r32376728 --- Diff: unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java --- @@ -131,24 +131,31 @@ public boolean contains(final UTF8String substring) { } for (int i = 0; i <= bytes.length - b.length; i++) { - // TODO: Avoid copying. - if (bytes[i] == b[0] && Arrays.equals(Arrays.copyOfRange(bytes, i, i + b.length), b)) { + if (bytes[i] == b[0] && startsWith(substring, i)) { return true; } } return false; } + private boolean startsWith(final UTF8String prefix, int offset) { --- End diff -- Nit: If we use `startsWith(final byte[] prefix, int offset)`, it will may save some calls of `s.getBytes()`. (not sure how is the difference).
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org