kinow commented on a change in pull request #100: TEXT-104: Jaro Winkler
Distance refers to similarity
URL: https://github.com/apache/commons-text/pull/100#discussion_r257453672
##########
File path:
src/main/java/org/apache/commons/text/similarity/JaroWinklerDistance.java
##########
@@ -73,84 +57,13 @@
* @throws IllegalArgumentException if either CharSequence input is {@code
null}
*/
@Override
- public Double apply(final CharSequence left, final CharSequence right) {
- final double defaultScalingFactor = 0.1;
+ public Double apply(CharSequence left, CharSequence right) {
if (left == null || right == null) {
throw new IllegalArgumentException("CharSequences must not be
null");
}
- final int[] mtp = matches(left, right);
- final double m = mtp[0];
- if (m == 0) {
- return 0D;
- }
- final double j = ((m / left.length() + m / right.length() + (m -
(double) mtp[1] / 2) / m)) / 3;
- final double jw = j < 0.7D ? j : j + defaultScalingFactor * mtp[2] *
(1D - j);
- return jw;
- }
-
- /**
- * This method returns the Jaro-Winkler string matches, half
transpositions, prefix array.
- *
- * @param first the first string to be matched
- * @param second the second string to be matched
- * @return mtp array containing: matches, half transpositions, and prefix
- */
- protected static int[] matches(final CharSequence first, final
CharSequence second) {
- CharSequence max, min;
- if (first.length() > second.length()) {
- max = first;
- min = second;
- } else {
- max = second;
- min = first;
- }
- final int range = Math.max(max.length() / 2 - 1, 0);
- final int[] matchIndexes = new int[min.length()];
- Arrays.fill(matchIndexes, -1);
- final boolean[] matchFlags = new boolean[max.length()];
- int matches = 0;
- for (int mi = 0; mi < min.length(); mi++) {
- final char c1 = min.charAt(mi);
- for (int xi = Math.max(mi - range, 0), xn = Math.min(mi + range +
1, max.length()); xi < xn; xi++) {
- if (!matchFlags[xi] && c1 == max.charAt(xi)) {
- matchIndexes[mi] = xi;
- matchFlags[xi] = true;
- matches++;
- break;
- }
- }
- }
- final char[] ms1 = new char[matches];
- final char[] ms2 = new char[matches];
- for (int i = 0, si = 0; i < min.length(); i++) {
- if (matchIndexes[i] != -1) {
- ms1[si] = min.charAt(i);
- si++;
- }
- }
- for (int i = 0, si = 0; i < max.length(); i++) {
- if (matchFlags[i]) {
- ms2[si] = max.charAt(i);
- si++;
- }
- }
- int halfTranspositions = 0;
- for (int mi = 0; mi < ms1.length; mi++) {
- if (ms1[mi] != ms2[mi]) {
- halfTranspositions++;
- }
- }
- int prefix = 0;
- for (int mi = 0; mi < Math.min(4, min.length()); mi++) {
- if (first.charAt(mi) == second.charAt(mi)) {
- prefix++;
- } else {
- break;
- }
- }
- return new int[] {matches, halfTranspositions, prefix};
+ JaroWinklerSimilarity jwSim = new JaroWinklerSimilarity();
Review comment:
Maybe `similarity` or `jaroWinklerSimilarity`?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@commons.apache.org
For additional commands, e-mail: dev-h...@commons.apache.org
