1 /**
2 * Copyright 2014 Internet2
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 * http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16 /*
17 * Copyright 2001-2004 The Apache Software Foundation.
18 *
19 * Licensed under the Apache License, Version 2.0 (the "License");
20 * you may not use this file except in compliance with the License.
21 * You may obtain a copy of the License at
22 *
23 * http://www.apache.org/licenses/LICENSE-2.0
24 *
25 * Unless required by applicable law or agreed to in writing, software
26 * distributed under the License is distributed on an "AS IS" BASIS,
27 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
28 * See the License for the specific language governing permissions and
29 * limitations under the License.
30 */
31
32 package edu.internet2.middleware.grouperClientExt.org.apache.commons.codec.language;
33
34 import edu.internet2.middleware.grouperClientExt.org.apache.commons.codec.EncoderException;
35 import edu.internet2.middleware.grouperClientExt.org.apache.commons.codec.StringEncoder;
36
37 /**
38 * Encodes a string into a Soundex value. Soundex is an encoding used to relate similar names, but can also be used as a
39 * general purpose scheme to find word with similar phonemes.
40 *
41 * @author Apache Software Foundation
42 * @version $Id: Soundex.java,v 1.1 2008-11-30 10:57:28 mchyzer Exp $
43 */
44 public class Soundex implements StringEncoder {
45
46 /**
47 * An instance of Soundex using the US_ENGLISH_MAPPING mapping.
48 *
49 * @see #US_ENGLISH_MAPPING
50 */
51 public static final Soundexleware/grouperClientExt/org/apache/commons/codec/language/Soundex.html#Soundex">Soundex US_ENGLISH = new Soundex();
52
53 /**
54 * This is a default mapping of the 26 letters used in US English. A value of <code>0</code> for a letter position
55 * means do not encode.
56 * <p>
57 * (This constant is provided as both an implementation convenience and to allow Javadoc to pick
58 * up the value for the constant values page.)
59 * </p>
60 *
61 * @see #US_ENGLISH_MAPPING
62 */
63 public static final String US_ENGLISH_MAPPING_STRING = "01230120022455012623010202";
64
65 /**
66 * This is a default mapping of the 26 letters used in US English. A value of <code>0</code> for a letter position
67 * means do not encode.
68 *
69 * @see Soundex#Soundex(char[])
70 */
71 public static final char[] US_ENGLISH_MAPPING = US_ENGLISH_MAPPING_STRING.toCharArray();
72
73 /**
74 * Encodes the Strings and returns the number of characters in the two encoded Strings that are the same. This
75 * return value ranges from 0 through 4: 0 indicates little or no similarity, and 4 indicates strong similarity or
76 * identical values.
77 *
78 * @param s1
79 * A String that will be encoded and compared.
80 * @param s2
81 * A String that will be encoded and compared.
82 * @return The number of characters in the two encoded Strings that are the same from 0 to 4.
83 *
84 * @see SoundexUtils#difference(StringEncoder,String,String)
85 * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp"> MS
86 * T-SQL DIFFERENCE </a>
87 *
88 * @throws EncoderException
89 * if an error occurs encoding one of the strings
90 * @since 1.3
91 */
92 public int difference(String s1, String s2) throws EncoderException {
93 return SoundexUtils.difference(this, s1, s2);
94 }
95
96 /**
97 * The maximum length of a Soundex code - Soundex codes are only four characters by definition.
98 *
99 * @deprecated This feature is not needed since the encoding size must be constant. Will be removed in 2.0.
100 */
101 private int maxLength = 4;
102
103 /**
104 * Every letter of the alphabet is "mapped" to a numerical value. This char array holds the values to which each
105 * letter is mapped. This implementation contains a default map for US_ENGLISH
106 */
107 private char[] soundexMapping;
108
109 /**
110 * Creates an instance using US_ENGLISH_MAPPING
111 *
112 * @see Soundex#Soundex(char[])
113 * @see Soundex#US_ENGLISH_MAPPING
114 */
115 public Soundex() {
116 this(US_ENGLISH_MAPPING);
117 }
118
119 /**
120 * Creates a soundex instance using the given mapping. This constructor can be used to provide an internationalized
121 * mapping for a non-Western character set.
122 *
123 * Every letter of the alphabet is "mapped" to a numerical value. This char array holds the values to which each
124 * letter is mapped. This implementation contains a default map for US_ENGLISH
125 *
126 * @param mapping
127 * Mapping array to use when finding the corresponding code for a given character
128 */
129 public Soundex(char[] mapping) {
130 this.setSoundexMapping(mapping);
131 }
132
133 /**
134 * Encodes an Object using the soundex algorithm. This method is provided in order to satisfy the requirements of
135 * the Encoder interface, and will throw an EncoderException if the supplied object is not of type java.lang.String.
136 *
137 * @param pObject
138 * Object to encode
139 * @return An object (or type java.lang.String) containing the soundex code which corresponds to the String
140 * supplied.
141 * @throws EncoderException
142 * if the parameter supplied is not of type java.lang.String
143 * @throws IllegalArgumentException
144 * if a character is not mapped
145 */
146 public Object encode(Object pObject) throws EncoderException {
147 if (!(pObject instanceof String)) {
148 throw new EncoderException("Parameter supplied to Soundex encode is not of type java.lang.String");
149 }
150 return soundex((String) pObject);
151 }
152
153 /**
154 * Encodes a String using the soundex algorithm.
155 *
156 * @param pString
157 * A String object to encode
158 * @return A Soundex code corresponding to the String supplied
159 * @throws IllegalArgumentException
160 * if a character is not mapped
161 */
162 public String encode(String pString) {
163 return soundex(pString);
164 }
165
166 /**
167 * Used internally by the SoundEx algorithm.
168 *
169 * Consonants from the same code group separated by W or H are treated as one.
170 *
171 * @param str
172 * the cleaned working string to encode (in upper case).
173 * @param index
174 * the character position to encode
175 * @return Mapping code for a particular character
176 * @throws IllegalArgumentException
177 * if the character is not mapped
178 */
179 private char getMappingCode(String str, int index) {
180 char mappedChar = this.map(str.charAt(index));
181 // HW rule check
182 if (index > 1 && mappedChar != '0') {
183 char hwChar = str.charAt(index - 1);
184 if ('H' == hwChar || 'W' == hwChar) {
185 char preHWChar = str.charAt(index - 2);
186 char firstCode = this.map(preHWChar);
187 if (firstCode == mappedChar || 'H' == preHWChar || 'W' == preHWChar) {
188 return 0;
189 }
190 }
191 }
192 return mappedChar;
193 }
194
195 /**
196 * Returns the maxLength. Standard Soundex
197 *
198 * @deprecated This feature is not needed since the encoding size must be constant. Will be removed in 2.0.
199 * @return int
200 */
201 public int getMaxLength() {
202 return this.maxLength;
203 }
204
205 /**
206 * Returns the soundex mapping.
207 *
208 * @return soundexMapping.
209 */
210 private char[] getSoundexMapping() {
211 return this.soundexMapping;
212 }
213
214 /**
215 * Maps the given upper-case character to it's Soudex code.
216 *
217 * @param ch
218 * An upper-case character.
219 * @return A Soundex code.
220 * @throws IllegalArgumentException
221 * Thrown if <code>ch</code> is not mapped.
222 */
223 private char map(char ch) {
224 int index = ch - 'A';
225 if (index < 0 || index >= this.getSoundexMapping().length) {
226 throw new IllegalArgumentException("The character is not mapped: " + ch);
227 }
228 return this.getSoundexMapping()[index];
229 }
230
231 /**
232 * Sets the maxLength.
233 *
234 * @deprecated This feature is not needed since the encoding size must be constant. Will be removed in 2.0.
235 * @param maxLength
236 * The maxLength to set
237 */
238 public void setMaxLength(int maxLength) {
239 this.maxLength = maxLength;
240 }
241
242 /**
243 * Sets the soundexMapping.
244 *
245 * @param soundexMapping
246 * The soundexMapping to set.
247 */
248 private void setSoundexMapping(char[] soundexMapping) {
249 this.soundexMapping = soundexMapping;
250 }
251
252 /**
253 * Retreives the Soundex code for a given String object.
254 *
255 * @param str
256 * String to encode using the Soundex algorithm
257 * @return A soundex code for the String supplied
258 * @throws IllegalArgumentException
259 * if a character is not mapped
260 */
261 public String soundex(String str) {
262 if (str == null) {
263 return null;
264 }
265 str = SoundexUtils.clean(str);
266 if (str.length() == 0) {
267 return str;
268 }
269 char out[] = {'0', '0', '0', '0'};
270 char last, mapped;
271 int incount = 1, count = 1;
272 out[0] = str.charAt(0);
273 last = getMappingCode(str, 0);
274 while ((incount < str.length()) && (count < out.length)) {
275 mapped = getMappingCode(str, incount++);
276 if (mapped != 0) {
277 if ((mapped != '0') && (mapped != last)) {
278 out[count++] = mapped;
279 }
280 last = mapped;
281 }
282 }
283 return new String(out);
284 }
285
286 }