001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.text.similarity;
018
019import java.util.Locale;
020
021/**
022 * A matching algorithm that is similar to the searching algorithms implemented in editors such
023 * as Sublime Text, TextMate, Atom and others.
024 *
025 * <p>
026 * One point is given for every matched character. Subsequent matches yield two bonus points. A higher score
027 * indicates a higher similarity.
028 * </p>
029 *
030 * <p>
031 * This code has been adapted from Apache Commons Lang 3.3.
032 * </p>
033 *
034 * @since 1.0
035 */
036public class FuzzyScore {
037
038    /**
039     * Locale used to change the case of text.
040     */
041    private final Locale locale;
042
043    /**
044     * This returns a {@link Locale}-specific {@link FuzzyScore}.
045     *
046     * @param locale The string matching logic is case insensitive.
047                     A {@link Locale} is necessary to normalize both Strings to lower case.
048     * @throws IllegalArgumentException
049     *         This is thrown if the {@link Locale} parameter is {@code null}.
050     */
051    public FuzzyScore(final Locale locale) {
052        if (locale == null) {
053            throw new IllegalArgumentException("Locale must not be null");
054        }
055        this.locale = locale;
056    }
057
058    /**
059     * Find the Fuzzy Score which indicates the similarity score between two
060     * Strings.
061     *
062     * <pre>
063     * score.fuzzyScore(null, null)                          = IllegalArgumentException
064     * score.fuzzyScore("not null", null)                    = IllegalArgumentException
065     * score.fuzzyScore(null, "not null")                    = IllegalArgumentException
066     * score.fuzzyScore("", "")                              = 0
067     * score.fuzzyScore("Workshop", "b")                     = 0
068     * score.fuzzyScore("Room", "o")                         = 1
069     * score.fuzzyScore("Workshop", "w")                     = 1
070     * score.fuzzyScore("Workshop", "ws")                    = 2
071     * score.fuzzyScore("Workshop", "wo")                    = 4
072     * score.fuzzyScore("Apache Software Foundation", "asf") = 3
073     * </pre>
074     *
075     * @param term a full term that should be matched against, must not be null
076     * @param query the query that will be matched against a term, must not be
077     *            null
078     * @return result score
079     * @throws IllegalArgumentException if the term or query is {@code null}
080     */
081    public Integer fuzzyScore(final CharSequence term, final CharSequence query) {
082        if (term == null || query == null) {
083            throw new IllegalArgumentException("CharSequences must not be null");
084        }
085
086        // fuzzy logic is case insensitive. We normalize the Strings to lower
087        // case right from the start. Turning characters to lower case
088        // via Character.toLowerCase(char) is unfortunately insufficient
089        // as it does not accept a locale.
090        final String termLowerCase = term.toString().toLowerCase(locale);
091        final String queryLowerCase = query.toString().toLowerCase(locale);
092
093        // the resulting score
094        int score = 0;
095
096        // the position in the term which will be scanned next for potential
097        // query character matches
098        int termIndex = 0;
099
100        // index of the previously matched character in the term
101        int previousMatchingCharacterIndex = Integer.MIN_VALUE;
102
103        for (int queryIndex = 0; queryIndex < queryLowerCase.length(); queryIndex++) {
104            final char queryChar = queryLowerCase.charAt(queryIndex);
105
106            boolean termCharacterMatchFound = false;
107            for (; termIndex < termLowerCase.length()
108                    && !termCharacterMatchFound; termIndex++) {
109                final char termChar = termLowerCase.charAt(termIndex);
110
111                if (queryChar == termChar) {
112                    // simple character matches result in one point
113                    score++;
114
115                    // subsequent character matches further improve
116                    // the score.
117                    if (previousMatchingCharacterIndex + 1 == termIndex) {
118                        score += 2;
119                    }
120
121                    previousMatchingCharacterIndex = termIndex;
122
123                    // we can leave the nested loop. Every character in the
124                    // query can match at most one character in the term.
125                    termCharacterMatchFound = true;
126                }
127            }
128        }
129
130        return score;
131    }
132
133    /**
134     * Gets the locale.
135     *
136     * @return The locale
137     */
138    public Locale getLocale() {
139        return locale;
140    }
141
142}