info.debatty.java.stringsimilarity.MetricLCS Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of java-string-similarity Show documentation
Show all versions of java-string-similarity Show documentation
Implementation of various string similarity and distance algorithms: Levenshtein, Jaro-winkler, n-Gram, Q-Gram, Jaccard index, Longest Common Subsequence edit distance, cosine similarity...
/*
* The MIT License
*
* Copyright 2015 Thibault Debatty.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
package info.debatty.java.stringsimilarity;
import info.debatty.java.stringsimilarity.interfaces.MetricStringDistance;
import info.debatty.java.stringsimilarity.interfaces.NormalizedStringDistance;
/**
* Distance metric based on Longest Common Subsequence, from the notes "An
* LCS-based string metric" by Daniel Bakkelund.
* @author Thibault Debatty
*/
public class MetricLCS implements MetricStringDistance, NormalizedStringDistance {
private final LongestCommonSubsequence lcs = new LongestCommonSubsequence();
/**
* Distance metric based on Longest Common Subsequence, computed as
* 1 - |LCS(s1, s2)| / max(|s1|, |s2|)
* @param s1
* @param s2
* @return
*/
public double distance(String s1, String s2) {
return 1.0 - ((double) lcs.length(s1, s2)) / Math.max(s1.length(), s2.length());
}
}