Similarity Class Reference

A library implementing different string similarity and distance measures. More...

Static Public Member Functions
static double	Levenshtein (String s1, String s2)
static double	NormalizedLevenshtein (String s1, String s2)
static double	WeightedLevenshtein (String s1, String s2)
static double	Damerau (String s1, String s2)
static double	JaroWinkler (String s1, String s2)
static double	LongestCommonSubsequence (String s1, String s2)
static double	MetricLCS (String s1, String s2)
static double	twoGram (String s1, String s2)
static double	NGram (String s1, String s2)
static double	QGram (String s1, String s2)

Detailed Description

A library implementing different string similarity and distance measures.

A dozen of algorithms (including Levenshtein edit distance and sibblings, Jaro-Winkler, Longest Common Subsequence, cosine similarity etc.) are currently implemented. Check the summary table below for the complete list... https://github.com/tdebatty/java-string-similarity

Author

Copyright 2015 Thibault Debatty https://github.com/tdebatty/java-string-similarity/blob/master/LICENSE.md

Member Function Documentation

Damerau()

static double Damerau ( String  s1, String  s2  )

static

                                                           {
                Damerau d = new Damerau();
                return d.distance(s1, s2);
        }

JaroWinkler()

static double JaroWinkler ( String  s1, String  s2  )

static

                                                               {
                JaroWinkler jw = new JaroWinkler();
                return jw.similarity(s1, s2);
        }

Levenshtein()

static double Levenshtein ( String  s1, String  s2  )

static

                                                               {
                Levenshtein l = new Levenshtein();
                return l.distance(s1, s2);
        }

LongestCommonSubsequence()

static double LongestCommonSubsequence ( String  s1, String  s2  )

static

                                                                            {
                LongestCommonSubsequence lcs = new LongestCommonSubsequence();
                return lcs.distance(s1, s2);
        }

MetricLCS()

static double MetricLCS ( String  s1, String  s2  )

static

                                                             {
                MetricLCS lcs = new MetricLCS();
                return lcs.distance(s1, s2);
        }

NGram()

static double NGram ( String  s1, String  s2  )

static

                                                         {
                NGram ngram = new NGram(4);
                return ngram.distance(s1, s2);
        }

Referenced by Similarity.twoGram().

NormalizedLevenshtein()

static double NormalizedLevenshtein ( String  s1, String  s2  )

static

                                                                         {
                NormalizedLevenshtein nl = new NormalizedLevenshtein();
                return nl.distance(s1, s2);
        }

Referenced by SearchResource.getResultsLabelingSystem().

QGram()

static double QGram ( String  s1, String  s2  )

static

                                                         {
                QGram dig = new QGram(2);
                return dig.distance(s1, s2);
        }

twoGram()

static double twoGram ( String  s1, String  s2  )

static

                                                           {
                NGram twogram = new NGram(2);
                return twogram.distance(s1, s2);
        }

References Similarity.NGram().

WeightedLevenshtein()

static double WeightedLevenshtein ( String  s1, String  s2  )

static

                                                                       {
                WeightedLevenshtein wl = new WeightedLevenshtein(
                                new CharacterSubstitutionInterface() {
                        public double cost(char c1, char c2) {
                                // The cost for substituting 't' and 'r' is considered
                                // smaller as these 2 are located next to each other
                                // on a keyboard
                                if (c1 == 't' && c2 == 'r') {
                                        return 0.5;
                                }
                                // For most cases, the cost of substituting 2 characters
                                // is 1.0
                                return 1.0;
                        }
                });
                return wl.distance(s1, s2);
        }