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 * Encodes a string into a Refined Soundex value. A refined soundex code is 24 * optimized for spell checking words. Soundex method originally developed by 25 * <CITE>Margaret Odell</CITE> and <CITE>Robert Russell</CITE>. 26 * 27 * @author Apache Software Foundation 28 * @version $Id: RefinedSoundex.java,v 1.21 2004/06/05 18:32:04 ggregory Exp $ 29 */ 30 public class RefinedSoundex implements StringEncoder { 31 32 /** 33 * This static variable contains an instance of the RefinedSoundex using 34 * the US_ENGLISH mapping. 35 */ 36 public static final RefinedSoundex US_ENGLISH = new RefinedSoundex(); 37 38 /** 39 * RefinedSoundex is *refined* for a number of reasons one being that the 40 * mappings have been altered. This implementation contains default 41 * mappings for US English. 42 */ 43 public static final char[] US_ENGLISH_MAPPING = "01360240043788015936020505".toCharArray(); 44 45 /** 46 * Every letter of the alphabet is "mapped" to a numerical value. This char 47 * array holds the values to which each letter is mapped. This 48 * implementation contains a default map for US_ENGLISH 49 */ 50 private char[] soundexMapping; 51 52 /** 53 * Creates an instance of the RefinedSoundex object using the default US 54 * English mapping. 55 */ 56 public RefinedSoundex() { 57 this(US_ENGLISH_MAPPING); 58 } 59 60 /** 61 * Creates a refined soundex instance using a custom mapping. This 62 * constructor can be used to customize the mapping, and/or possibly 63 * provide an internationalized mapping for a non-Western character set. 64 * 65 * @param mapping 66 * Mapping array to use when finding the corresponding code for 67 * a given character 68 */ 69 public RefinedSoundex(char[] mapping) { 70 this.soundexMapping = mapping; 71 } 72 73 // BEGIN android-note 74 // Removed @see reference to SoundexUtils below, since the class isn't 75 // public. 76 // END android-note 77 /** 78 * Returns the number of characters in the two encoded Strings that are the 79 * same. This return value ranges from 0 to the length of the shortest 80 * encoded String: 0 indicates little or no similarity, and 4 out of 4 (for 81 * example) indicates strong similarity or identical values. For refined 82 * Soundex, the return value can be greater than 4. 83 * 84 * @param s1 85 * A String that will be encoded and compared. 86 * @param s2 87 * A String that will be encoded and compared. 88 * @return The number of characters in the two encoded Strings that are the 89 * same from 0 to to the length of the shortest encoded String. 90 * 91 * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp"> 92 * MS T-SQL DIFFERENCE</a> 93 * 94 * @throws EncoderException 95 * if an error occurs encoding one of the strings 96 * @since 1.3 97 */ 98 public int difference(String s1, String s2) throws EncoderException { 99 return SoundexUtils.difference(this, s1, s2); 100 } 101 102 /** 103 * Encodes an Object using the refined soundex algorithm. This method is 104 * provided in order to satisfy the requirements of the Encoder interface, 105 * and will throw an EncoderException if the supplied object is not of type 106 * java.lang.String. 107 * 108 * @param pObject 109 * Object to encode 110 * @return An object (or type java.lang.String) containing the refined 111 * soundex code which corresponds to the String supplied. 112 * @throws EncoderException 113 * if the parameter supplied is not of type java.lang.String 114 */ 115 public Object encode(Object pObject) throws EncoderException { 116 if (!(pObject instanceof java.lang.String)) { 117 throw new EncoderException("Parameter supplied to RefinedSoundex encode is not of type java.lang.String"); 118 } 119 return soundex((String) pObject); 120 } 121 122 /** 123 * Encodes a String using the refined soundex algorithm. 124 * 125 * @param pString 126 * A String object to encode 127 * @return A Soundex code corresponding to the String supplied 128 */ 129 public String encode(String pString) { 130 return soundex(pString); 131 } 132 133 /** 134 * Returns the mapping code for a given character. The mapping codes are 135 * maintained in an internal char array named soundexMapping, and the 136 * default values of these mappings are US English. 137 * 138 * @param c 139 * char to get mapping for 140 * @return A character (really a numeral) to return for the given char 141 */ 142 char getMappingCode(char c) { 143 if (!Character.isLetter(c)) { 144 return 0; 145 } 146 return this.soundexMapping[Character.toUpperCase(c) - 'A']; 147 } 148 149 /** 150 * Retreives the Refined Soundex code for a given String object. 151 * 152 * @param str 153 * String to encode using the Refined Soundex algorithm 154 * @return A soundex code for the String supplied 155 */ 156 public String soundex(String str) { 157 if (str == null) { 158 return null; 159 } 160 str = SoundexUtils.clean(str); 161 if (str.length() == 0) { 162 return str; 163 } 164 165 StringBuffer sBuf = new StringBuffer(); 166 sBuf.append(str.charAt(0)); 167 168 char last, current; 169 last = '*'; 170 171 for (int i = 0; i < str.length(); i++) { 172 173 current = getMappingCode(str.charAt(i)); 174 if (current == last) { 175 continue; 176 } else if (current != 0) { 177 sBuf.append(current); 178 } 179 180 last = current; 181 182 } 183 184 return sBuf.toString(); 185 } 186 } 187
