Apache
/
commons-lang
mirror of https://github.com/apache/commons-lang.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Tiddy up JavaDoc for Jaro Winkler Distance calculation 

git-svn-id: https://svn.apache.org/repos/asf/commons/proper/lang/trunk@1560740 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Benedikt Ritter 2014-01-23 16:48:17 +00:00
parent 7460a856f2
commit 8d815d8f8d
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/main/java/org/apache/commons/lang3/StringUtils.java
View File

@ -6980,10 +6980,10 @@ distance is O(nm), but a bound of k allows us to reduce it to O(km) time by only
* <p>Find the Jaro Winkler Distance which indicates the similarity score between two Strings.</p>
*
* <p>The Jaro measure is the weighted sum of percentage of matched characters from each file and transposed characters.
* Winkler increased this measure for matching initial characters</p>
* Winkler increased this measure for matching initial characters.</p>
*
* <p>This implementation is based on the Jaro Winkler similarity algorithm
* from <a href="http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance">http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance</a></p>
* from <a href="http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance">http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance</a>.</p>
*
* <pre>
* StringUtils.getJaroWinklerDistance(null, null) = IllegalArgumentException
@ -7002,8 +7002,8 @@ distance is O(nm), but a bound of k allows us to reduce it to O(km) time by only
* StringUtils.getJaroWinklerDistance("PENNSYLVANIA", "PENNCISYLVNIA") = 0.9
* </pre>
*
* @param s the first String, must not be null
* @param t the second String, must not be null
* @param first the first String, must not be null
* @param second the second String, must not be null
* @return result distance
* @throws IllegalArgumentException if either String input {@code null}
*/
@ -7029,8 +7029,9 @@ public static double getJaroWinklerDistance(CharSequence first, CharSequence sec
}
/**
* This method returns the jarowinkler score for string matching.
* @param strings to be matched
* This method returns the Jaro-Winkler score for string matching.
* @param first the first string to be matched
* @param second the second string to be machted
* @return matching score without scaling factor impact
*/
private static double score(CharSequence first, CharSequence second) {
@ -7082,13 +7083,14 @@ private static double score(CharSequence first, CharSequence second) {
/**
* Gets a set of matching characters between two strings.
*
*
* <p><Two characters from the first string and the second string are considered matching if the character's
* respective positions are no farther than the limit value.</p>
*
* @param first The first string.
* @param second The second string.
* @param limit The maximum distance to consider.
* @return A string contain the set of common characters.
* @remarks Two characters from the first string and the second string are considered matching if the character's
* respective positions are no farther than the limit value.
*/
private static String getSetOfMatchingCharacterWithin(CharSequence first, CharSequence second, int limit)
{