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
18 package org.apache.commons.codec.language;
19
20 import org.apache.commons.codec.EncoderException;
21 import org.apache.commons.codec.StringEncoder;
22
23 /**
24 * Encodes a string into a Refined Soundex value. A refined Soundex code is
25 * optimized for spell checking words. Soundex method originally developed by
26 * <CITE>Margaret Odell</CITE> and <CITE>Robert Russell</CITE>.
27 *
28 * <p>
29 * This class is immutable and thread-safe.
30 * </p>
31 */
32 public class RefinedSoundex implements StringEncoder {
33
34 /**
35 * Mapping:
36 * <pre>
37 * 0: A E I O U Y H W
38 * 1: B P
39 * 2: F V
40 * 3: C K S
41 * 4: G J
42 * 5: Q X Z
43 * 6: D T
44 * 7: L
45 * 8: M N
46 * 9: R
47 * </pre>
48 *
49 * @since 1.4
50 */
51 // ABCDEFGHIJKLMNOPQRSTUVWXYZ
52 public static final String US_ENGLISH_MAPPING_STRING = "01360240043788015936020505";
53
54 /**
55 * RefinedSoundex is *refined* for a number of reasons one being that the
56 * mappings have been altered. This implementation contains default
57 * mappings for US English.
58 */
59 private static final char[] US_ENGLISH_MAPPING = US_ENGLISH_MAPPING_STRING.toCharArray();
60
61 /**
62 * This static variable contains an instance of the RefinedSoundex using
63 * the US_ENGLISH mapping.
64 */
65 public static final RefinedSoundex US_ENGLISH = new RefinedSoundex();
66
67 /**
68 * Every letter of the alphabet is "mapped" to a numerical value. This char
69 * array holds the values to which each letter is mapped. This
70 * implementation contains a default map for US_ENGLISH.
71 */
72 private final char[] soundexMapping;
73
74 /**
75 * Creates an instance of the RefinedSoundex object using the default US
76 * English mapping.
77 */
78 public RefinedSoundex() {
79 this.soundexMapping = US_ENGLISH_MAPPING;
80 }
81
82 /**
83 * Creates a refined Soundex instance using a custom mapping. This
84 * constructor can be used to customize the mapping, and/or possibly
85 * provide an internationalized mapping for a non-Western character set.
86 *
87 * @param mapping
88 * Mapping array to use when finding the corresponding code for
89 * a given character.
90 */
91 public RefinedSoundex(final char[] mapping) {
92 this.soundexMapping = mapping.clone();
93 }
94
95 /**
96 * Creates a refined Soundex instance using a custom mapping. This constructor can be used to customize the mapping,
97 * and/or possibly provide an internationalized mapping for a non-Western character set.
98 *
99 * @param mapping
100 * Mapping string to use when finding the corresponding code for a given character.
101 * @since 1.4
102 */
103 public RefinedSoundex(final String mapping) {
104 this.soundexMapping = mapping.toCharArray();
105 }
106
107 /**
108 * Returns the number of characters in the two encoded Strings that are the
109 * same. This return value ranges from 0 to the length of the shortest
110 * encoded String: 0 indicates little or no similarity, and 4 out of 4 (for
111 * example) indicates strong similarity or identical values. For refined
112 * Soundex, the return value can be greater than 4.
113 *
114 * @param s1
115 * A String that will be encoded and compared.
116 * @param s2
117 * A String that will be encoded and compared.
118 * @return The number of characters in the two encoded Strings that are the
119 * same from 0 to the length of the shortest encoded String.
120 *
121 * @see SoundexUtils#difference(StringEncoder,String,String)
122 * @see <a href="https://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
123 * MS T-SQL DIFFERENCE</a>
124 *
125 * @throws EncoderException
126 * if an error occurs encoding one of the strings.
127 * @since 1.3
128 */
129 public int difference(final String s1, final String s2) throws EncoderException {
130 return SoundexUtils.difference(this, s1, s2);
131 }
132
133 /**
134 * Encodes an Object using the refined Soundex algorithm. This method is
135 * provided in order to satisfy the requirements of the Encoder interface,
136 * and will throw an EncoderException if the supplied object is not of type
137 * {@link String}.
138 *
139 * @param obj
140 * Object to encode.
141 * @return An object (or type {@link String}) containing the refined.
142 * Soundex code which corresponds to the String supplied.
143 * @throws EncoderException
144 * if the parameter supplied is not of type {@link String}.
145 */
146 @Override
147 public Object encode(final Object obj) throws EncoderException {
148 if (!(obj instanceof String)) {
149 throw new EncoderException("Parameter supplied to RefinedSoundex encode is not of type java.lang.String");
150 }
151 return soundex((String) obj);
152 }
153
154 /**
155 * Encodes a String using the refined Soundex algorithm.
156 *
157 * @param str
158 * A String object to encode.
159 * @return A Soundex code corresponding to the String supplied.
160 */
161 @Override
162 public String encode(final String str) {
163 return soundex(str);
164 }
165
166 /**
167 * Returns the mapping code for a given character. The mapping codes are
168 * maintained in an internal char array named soundexMapping, and the
169 * default values of these mappings are US English.
170 *
171 * @param c
172 * char to get mapping for.
173 * @return A character (really a numeral) to return for the given char.
174 */
175 char getMappingCode(final char c) {
176 if (!Character.isLetter(c)) {
177 return 0;
178 }
179 final int index = Character.toUpperCase(c) - 'A';
180 if (index < 0 || index >= this.soundexMapping.length) {
181 return 0;
182 }
183 return this.soundexMapping[index];
184 }
185
186 /**
187 * Retrieves the Refined Soundex code for a given String object.
188 *
189 * @param str
190 * String to encode using the Refined Soundex algorithm.
191 * @return A Soundex code for the String supplied.
192 */
193 public String soundex(String str) {
194 if (str == null) {
195 return null;
196 }
197 str = SoundexUtils.clean(str);
198 if (str.isEmpty()) {
199 return str;
200 }
201
202 final StringBuilder sBuf = new StringBuilder();
203 sBuf.append(str.charAt(0));
204
205 char last, current;
206 last = '*';
207
208 for (int i = 0; i < str.length(); i++) {
209
210 current = getMappingCode(str.charAt(i));
211 if (current == last) {
212 continue;
213 }
214 if (current != 0) {
215 sBuf.append(current);
216 }
217
218 last = current;
219
220 }
221
222 return sBuf.toString();
223 }
224 }