Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/7236#discussion_r34223281 --- Diff: unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java --- @@ -254,6 +254,67 @@ public boolean equals(final Object other) { } } + /** + * Levenshtein distance is a metric for measuring the distance of two strings. The distance is + * defined by the minimum number of single-character edits (i.e. insertions, deletions or + * substitutions) that are required to change one of the strings into the other. + */ + public int levenshteinDistance(UTF8String other) { + // Implementation adopted from org.apache.common.lang3.StringUtils.getLevenshteinDistance + + int n = numChars(); + int m = other.numChars(); + + if (n == 0) { + return m; + } else if (m == 0) { + return n; + } + + UTF8String s, t; + + if (n <= m) { + s = this; + t = other; + } else { + s = other; + t = this; + n = s.numChars(); + m = t.numChars(); + } + + int p[] = new int[n + 1]; + int d[] = new int[n + 1]; + int swap[]; + + int i, i_bytes, j, j_bytes, num_bytes_j, cost; + + for (i = 0; i <= n; i++) { + p[i] = i; + } + + for (j = 0, j_bytes = 0; j < m; j_bytes += numBytesForFirstByte(t.getByte(j_bytes)), j++) { + num_bytes_j = numBytesForFirstByte(t.getByte(j_bytes)); + d[0] = j + 1; + + for (i = 0, i_bytes = 0; i < n; i_bytes += numBytesForFirstByte(s.getByte(i_bytes)), i++) { + if (num_bytes_j != numBytesForFirstByte(s.getByte(i_bytes))) { + cost = 1; + } else { + cost = (ByteArrayMethods.arrayEquals(t.base, t.offset + j_bytes, s.base, --- End diff -- num_bytes_j will be <= 4
--- 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