1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * https://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.text.similarity;
18
19 import java.util.Locale;
20
21 /**
22 * A matching algorithm that is similar to the searching algorithms implemented in editors such
23 * as Sublime Text, TextMate, Atom and others.
24 *
25 * <p>
26 * One point is given for every matched character. Subsequent matches yield two bonus points. A higher score
27 * indicates a higher similarity.
28 * </p>
29 *
30 * <p>
31 * This code has been adapted from Apache Commons Lang 3.3.
32 * </p>
33 *
34 * @since 1.0
35 */
36 public class FuzzyScore {
37
38 /**
39 * Locale used to change the case of text.
40 */
41 private final Locale locale;
42
43 /**
44 * This returns a {@link Locale}-specific {@link FuzzyScore}.
45 *
46 * @param locale The string matching logic is case insensitive. A {@link Locale} is necessary to normalize both Strings to lower case.
47 * @throws IllegalArgumentException This is thrown if the {@link Locale} parameter is {@code null}.
48 */
49 public FuzzyScore(final Locale locale) {
50 if (locale == null) {
51 throw new IllegalArgumentException("Locale must not be null");
52 }
53 this.locale = locale;
54 }
55
56 /**
57 * Find the Fuzzy Score which indicates the similarity score between two Strings.
58 *
59 * <pre>
60 * score.fuzzyScore(null, null) = IllegalArgumentException
61 * score.fuzzyScore("not null", null) = IllegalArgumentException
62 * score.fuzzyScore(null, "not null") = IllegalArgumentException
63 * score.fuzzyScore("", "") = 0
64 * score.fuzzyScore("Workshop", "b") = 0
65 * score.fuzzyScore("Room", "o") = 1
66 * score.fuzzyScore("Workshop", "w") = 1
67 * score.fuzzyScore("Workshop", "ws") = 2
68 * score.fuzzyScore("Workshop", "wo") = 4
69 * score.fuzzyScore("Apache Software Foundation", "asf") = 3
70 * </pre>
71 *
72 * @param term a full term that should be matched against, must not be null.
73 * @param query the query that will be matched against a term, must not be null.
74 * @return result score.
75 * @throws IllegalArgumentException if the term or query is {@code null}.
76 */
77 public Integer fuzzyScore(final CharSequence term, final CharSequence query) {
78 if (term == null || query == null) {
79 throw new IllegalArgumentException("CharSequences must not be null");
80 }
81
82 // fuzzy logic is case insensitive. We normalize the Strings to lower
83 // case right from the start. Turning characters to lower case
84 // via Character.toLowerCase(char) is unfortunately insufficient
85 // as it does not accept a locale.
86 final String termLowerCase = term.toString().toLowerCase(locale);
87 final String queryLowerCase = query.toString().toLowerCase(locale);
88
89 // the resulting score
90 int score = 0;
91
92 // the position in the term which will be scanned next for potential
93 // query character matches
94 int termIndex = 0;
95
96 // index of the previously matched character in the term
97 int previousMatchingCharacterIndex = Integer.MIN_VALUE;
98
99 for (int queryIndex = 0; queryIndex < queryLowerCase.length(); queryIndex++) {
100 final char queryChar = queryLowerCase.charAt(queryIndex);
101
102 boolean termCharacterMatchFound = false;
103 for (; termIndex < termLowerCase.length()
104 && !termCharacterMatchFound; termIndex++) {
105 final char termChar = termLowerCase.charAt(termIndex);
106
107 if (queryChar == termChar) {
108 // simple character matches result in one point
109 score++;
110
111 // subsequent character matches further improve
112 // the score.
113 if (previousMatchingCharacterIndex + 1 == termIndex) {
114 score += 2;
115 }
116
117 previousMatchingCharacterIndex = termIndex;
118
119 // we can leave the nested loop. Every character in the
120 // query can match at most one character in the term.
121 termCharacterMatchFound = true;
122 }
123 }
124 }
125
126 return score;
127 }
128
129 /**
130 * Gets the locale.
131 *
132 * @return The locale
133 */
134 public Locale getLocale() {
135 return locale;
136 }
137
138 }