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 Refined Soundex value. A refined soundex code is
39 * optimized for spell checking words. Soundex method originally developed by
40 * <CITE>Margaret Odell</CITE> and <CITE>Robert Russell</CITE>.
41 *
42 * @author Apache Software Foundation
43 * @version $Id: RefinedSoundex.java,v 1.1 2008-11-30 10:57:28 mchyzer Exp $
44 */
45 public class RefinedSoundex implements StringEncoder {
46
47 /**
48 * This static variable contains an instance of the RefinedSoundex using
49 * the US_ENGLISH mapping.
50 */
51 public static final RefinedSoundexgrouperClientExt/org/apache/commons/codec/language/RefinedSoundex.html#RefinedSoundex">RefinedSoundex US_ENGLISH = new RefinedSoundex();
52
53 /**
54 * RefinedSoundex is *refined* for a number of reasons one being that the
55 * mappings have been altered. This implementation contains default
56 * mappings for US English.
57 */
58 public static final char[] US_ENGLISH_MAPPING = "01360240043788015936020505".toCharArray();
59
60 /**
61 * Every letter of the alphabet is "mapped" to a numerical value. This char
62 * array holds the values to which each letter is mapped. This
63 * implementation contains a default map for US_ENGLISH
64 */
65 private char[] soundexMapping;
66
67 /**
68 * Creates an instance of the RefinedSoundex object using the default US
69 * English mapping.
70 */
71 public RefinedSoundex() {
72 this(US_ENGLISH_MAPPING);
73 }
74
75 /**
76 * Creates a refined soundex instance using a custom mapping. This
77 * constructor can be used to customize the mapping, and/or possibly
78 * provide an internationalized mapping for a non-Western character set.
79 *
80 * @param mapping
81 * Mapping array to use when finding the corresponding code for
82 * a given character
83 */
84 public RefinedSoundex(char[] mapping) {
85 this.soundexMapping = mapping;
86 }
87
88 /**
89 * Returns the number of characters in the two encoded Strings that are the
90 * same. This return value ranges from 0 to the length of the shortest
91 * encoded String: 0 indicates little or no similarity, and 4 out of 4 (for
92 * example) indicates strong similarity or identical values. For refined
93 * Soundex, the return value can be greater than 4.
94 *
95 * @param s1
96 * A String that will be encoded and compared.
97 * @param s2
98 * A String that will be encoded and compared.
99 * @return The number of characters in the two encoded Strings that are the
100 * same from 0 to to the length of the shortest encoded String.
101 *
102 * @see SoundexUtils#difference(StringEncoder,String,String)
103 * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
104 * MS T-SQL DIFFERENCE</a>
105 *
106 * @throws EncoderException
107 * if an error occurs encoding one of the strings
108 * @since 1.3
109 */
110 public int difference(String s1, String s2) throws EncoderException {
111 return SoundexUtils.difference(this, s1, s2);
112 }
113
114 /**
115 * Encodes an Object using the refined soundex algorithm. This method is
116 * provided in order to satisfy the requirements of the Encoder interface,
117 * and will throw an EncoderException if the supplied object is not of type
118 * java.lang.String.
119 *
120 * @param pObject
121 * Object to encode
122 * @return An object (or type java.lang.String) containing the refined
123 * soundex code which corresponds to the String supplied.
124 * @throws EncoderException
125 * if the parameter supplied is not of type java.lang.String
126 */
127 public Object encode(Object pObject) throws EncoderException {
128 if (!(pObject instanceof java.lang.String)) {
129 throw new EncoderException("Parameter supplied to RefinedSoundex encode is not of type java.lang.String");
130 }
131 return soundex((String) pObject);
132 }
133
134 /**
135 * Encodes a String using the refined soundex algorithm.
136 *
137 * @param pString
138 * A String object to encode
139 * @return A Soundex code corresponding to the String supplied
140 */
141 public String encode(String pString) {
142 return soundex(pString);
143 }
144
145 /**
146 * Returns the mapping code for a given character. The mapping codes are
147 * maintained in an internal char array named soundexMapping, and the
148 * default values of these mappings are US English.
149 *
150 * @param c
151 * char to get mapping for
152 * @return A character (really a numeral) to return for the given char
153 */
154 char getMappingCode(char c) {
155 if (!Character.isLetter(c)) {
156 return 0;
157 }
158 return this.soundexMapping[Character.toUpperCase(c) - 'A'];
159 }
160
161 /**
162 * Retreives the Refined Soundex code for a given String object.
163 *
164 * @param str
165 * String to encode using the Refined Soundex algorithm
166 * @return A soundex code for the String supplied
167 */
168 public String soundex(String str) {
169 if (str == null) {
170 return null;
171 }
172 str = SoundexUtils.clean(str);
173 if (str.length() == 0) {
174 return str;
175 }
176
177 StringBuffer sBuf = new StringBuffer();
178 sBuf.append(str.charAt(0));
179
180 char last, current;
181 last = '*';
182
183 for (int i = 0; i < str.length(); i++) {
184
185 current = getMappingCode(str.charAt(i));
186 if (current == last) {
187 continue;
188 } else if (current != 0) {
189 sBuf.append(current);
190 }
191
192 last = current;
193
194 }
195
196 return sBuf.toString();
197 }
198 }