1 /*
2  * Copyright 2001-2004 The Apache Software Foundation.
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 package org.apache.commons.codec.language;
18 
19 import org.apache.commons.codec.EncoderException;
20 import org.apache.commons.codec.StringEncoder;
21 
22 /**
23  * Utility methods for {@link Soundex} and {@link RefinedSoundex} classes.
24  *
25  * @author Apache Software Foundation
26  * @version $Id: SoundexUtils.java,v 1.5 2004/03/17 18:31:35 ggregory Exp $
27  * @since 1.3
28  *
29  * @deprecated Please use {@link java.net.URL#openConnection} instead.
30  *     Please visit <a href="http://android-developers.blogspot.com/2011/09/androids-http-clients.html">this webpage</a>
31  *     for further details.
32  */
33 @Deprecated
34 final class SoundexUtils {
35 
36     /**
37      * Cleans up the input string before Soundex processing by only returning
38      * upper case letters.
39      *
40      * @param str
41      *                  The String to clean.
42      * @return A clean String.
43      */
clean(String str)44     static String clean(String str) {
45         if (str == null || str.length() == 0) {
46             return str;
47         }
48         int len = str.length();
49         char[] chars = new char[len];
50         int count = 0;
51         for (int i = 0; i < len; i++) {
52             if (Character.isLetter(str.charAt(i))) {
53                 chars[count++] = str.charAt(i);
54             }
55         }
56         if (count == len) {
57             return str.toUpperCase();
58         }
59         return new String(chars, 0, count).toUpperCase();
60     }
61 
62     /**
63      * Encodes the Strings and returns the number of characters in the two
64      * encoded Strings that are the same.
65      * <ul>
66      * <li>For Soundex, this return value ranges from 0 through 4: 0 indicates
67      * little or no similarity, and 4 indicates strong similarity or identical
68      * values.</li>
69      * <li>For refined Soundex, the return value can be greater than 4.</li>
70      * </ul>
71      *
72      * @param encoder
73      *                  The encoder to use to encode the Strings.
74      * @param s1
75      *                  A String that will be encoded and compared.
76      * @param s2
77      *                  A String that will be encoded and compared.
78      * @return The number of characters in the two Soundex encoded Strings that
79      *             are the same.
80      *
81      * @see #differenceEncoded(String,String)
82      * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
83      *          MS T-SQL DIFFERENCE</a>
84      *
85      * @throws EncoderException
86      *                  if an error occurs encoding one of the strings
87      */
difference(StringEncoder encoder, String s1, String s2)88     static int difference(StringEncoder encoder, String s1, String s2) throws EncoderException {
89         return differenceEncoded(encoder.encode(s1), encoder.encode(s2));
90     }
91 
92     /**
93      * Returns the number of characters in the two Soundex encoded Strings that
94      * are the same.
95      * <ul>
96      * <li>For Soundex, this return value ranges from 0 through 4: 0 indicates
97      * little or no similarity, and 4 indicates strong similarity or identical
98      * values.</li>
99      * <li>For refined Soundex, the return value can be greater than 4.</li>
100      * </ul>
101      *
102      * @param es1
103      *                  An encoded String.
104      * @param es2
105      *                  An encoded String.
106      * @return The number of characters in the two Soundex encoded Strings that
107      *             are the same.
108      *
109      * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
110      *          MS T-SQL DIFFERENCE</a>
111      */
differenceEncoded(String es1, String es2)112     static int differenceEncoded(String es1, String es2) {
113 
114         if (es1 == null || es2 == null) {
115             return 0;
116         }
117         int lengthToMatch = Math.min(es1.length(), es2.length());
118         int diff = 0;
119         for (int i = 0; i < lengthToMatch; i++) {
120             if (es1.charAt(i) == es2.charAt(i)) {
121                 diff++;
122             }
123         }
124         return diff;
125     }
126 
127 }
128