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 *      https://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     * Constructs a new instance for a {@link Locale}-specific {@link FuzzyScore}.
045     *
046     * @param locale The string matching logic is case insensitive. A {@link Locale} is necessary to normalize both Strings to lower case.
047     * @throws IllegalArgumentException This is thrown if the {@link Locale} parameter is {@code null}.
048     */
049    public FuzzyScore(final Locale locale) {
050        if (locale == null) {
051            throw new IllegalArgumentException("Locale must not be null");
052        }
053        this.locale = locale;
054    }
055
056    /**
057     * Computes the Fuzzy Score which indicates the similarity score between two Strings.
058     *
059     * <pre>
060     * score.fuzzyScore(null, null)                          = Throws {@link IllegalArgumentException}
061     * score.fuzzyScore("not null", null)                    = Throws {@link IllegalArgumentException}
062     * score.fuzzyScore(null, "not null")                    = Throws {@link IllegalArgumentException}
063     * score.fuzzyScore("", "")                              = 0
064     * score.fuzzyScore("Workshop", "b")                     = 0
065     * score.fuzzyScore("Room", "o")                         = 1
066     * score.fuzzyScore("Workshop", "w")                     = 1
067     * score.fuzzyScore("Workshop", "ws")                    = 2
068     * score.fuzzyScore("Workshop", "wo")                    = 4
069     * score.fuzzyScore("Apache Software Foundation", "asf") = 3
070     * </pre>
071     *
072     * @param term  a full term that should be matched against, must not be null.
073     * @param query the query that will be matched against a term, must not be null.
074     * @return result score.
075     * @throws IllegalArgumentException if the term or query is {@code null}.
076     */
077    public Integer fuzzyScore(final CharSequence term, final CharSequence query) {
078        if (term == null || query == null) {
079            throw new IllegalArgumentException("CharSequences must not be null");
080        }
081        // fuzzy logic is case insensitive. We normalize the Strings to lower
082        // case right from the start. Turning characters to lower case
083        // via Character.toLowerCase(char) is unfortunately insufficient
084        // as it does not accept a locale.
085        final String termLowerCase = term.toString().toLowerCase(locale);
086        final String queryLowerCase = query.toString().toLowerCase(locale);
087        // the resulting score
088        int score = 0;
089        // the position in the term which will be scanned next for potential
090        // query character matches
091        int termIndex = 0;
092        // index of the previously matched character in the term
093        int previousMatchingCharacterIndex = Integer.MIN_VALUE;
094        for (int queryIndex = 0; queryIndex < queryLowerCase.length(); queryIndex++) {
095            final char queryChar = queryLowerCase.charAt(queryIndex);
096            boolean termCharacterMatchFound = false;
097            for (; termIndex < termLowerCase.length() && !termCharacterMatchFound; termIndex++) {
098                final char termChar = termLowerCase.charAt(termIndex);
099                if (queryChar == termChar) {
100                    // simple character matches result in one point
101                    score++;
102                    // subsequent character matches further improve
103                    // the score.
104                    if (previousMatchingCharacterIndex + 1 == termIndex) {
105                        score += 2;
106                    }
107                    previousMatchingCharacterIndex = termIndex;
108                    // we can leave the nested loop. Every character in the
109                    // query can match at most one character in the term.
110                    termCharacterMatchFound = true;
111                }
112            }
113        }
114        return score;
115    }
116
117    /**
118     * Gets the locale.
119     *
120     * @return The locale
121     */
122    public Locale getLocale() {
123        return locale;
124    }
125
126}