001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017
018package org.apache.commons.codec.language;
019
020import org.apache.commons.codec.EncoderException;
021import org.apache.commons.codec.StringEncoder;
022
023/**
024 * Encodes a string into a Refined Soundex value. A refined soundex code is
025 * optimized for spell checking words. Soundex method originally developed by
026 * <CITE>Margaret Odell</CITE> and <CITE>Robert Russell</CITE>.
027 *
028 * <p>This class is immutable and thread-safe.</p>
029 *
030 * @version $Id: RefinedSoundex.html 928559 2014-11-10 02:53:54Z ggregory $
031 */
032public class RefinedSoundex implements StringEncoder {
033
034    /**
035     * @since 1.4
036     */
037    public static final String US_ENGLISH_MAPPING_STRING = "01360240043788015936020505";
038
039   /**
040     * RefinedSoundex is *refined* for a number of reasons one being that the
041     * mappings have been altered. This implementation contains default
042     * mappings for US English.
043     */
044    private static final char[] US_ENGLISH_MAPPING = US_ENGLISH_MAPPING_STRING.toCharArray();
045
046    /**
047     * Every letter of the alphabet is "mapped" to a numerical value. This char
048     * array holds the values to which each letter is mapped. This
049     * implementation contains a default map for US_ENGLISH
050     */
051    private final char[] soundexMapping;
052
053    /**
054     * This static variable contains an instance of the RefinedSoundex using
055     * the US_ENGLISH mapping.
056     */
057    public static final RefinedSoundex US_ENGLISH = new RefinedSoundex();
058
059     /**
060     * Creates an instance of the RefinedSoundex object using the default US
061     * English mapping.
062     */
063    public RefinedSoundex() {
064        this.soundexMapping = US_ENGLISH_MAPPING;
065    }
066
067    /**
068     * Creates a refined soundex instance using a custom mapping. This
069     * constructor can be used to customize the mapping, and/or possibly
070     * provide an internationalized mapping for a non-Western character set.
071     *
072     * @param mapping
073     *                  Mapping array to use when finding the corresponding code for
074     *                  a given character
075     */
076    public RefinedSoundex(final char[] mapping) {
077        this.soundexMapping = new char[mapping.length];
078        System.arraycopy(mapping, 0, this.soundexMapping, 0, mapping.length);
079    }
080
081    /**
082     * Creates a refined Soundex instance using a custom mapping. This constructor can be used to customize the mapping,
083     * and/or possibly provide an internationalized mapping for a non-Western character set.
084     *
085     * @param mapping
086     *            Mapping string to use when finding the corresponding code for a given character
087     * @since 1.4
088     */
089    public RefinedSoundex(final String mapping) {
090        this.soundexMapping = mapping.toCharArray();
091    }
092
093    /**
094     * Returns the number of characters in the two encoded Strings that are the
095     * same. This return value ranges from 0 to the length of the shortest
096     * encoded String: 0 indicates little or no similarity, and 4 out of 4 (for
097     * example) indicates strong similarity or identical values. For refined
098     * Soundex, the return value can be greater than 4.
099     *
100     * @param s1
101     *                  A String that will be encoded and compared.
102     * @param s2
103     *                  A String that will be encoded and compared.
104     * @return The number of characters in the two encoded Strings that are the
105     *             same from 0 to to the length of the shortest encoded String.
106     *
107     * @see SoundexUtils#difference(StringEncoder,String,String)
108     * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
109     *          MS T-SQL DIFFERENCE</a>
110     *
111     * @throws EncoderException
112     *                  if an error occurs encoding one of the strings
113     * @since 1.3
114     */
115    public int difference(final String s1, final String s2) throws EncoderException {
116        return SoundexUtils.difference(this, s1, s2);
117    }
118
119    /**
120     * Encodes an Object using the refined soundex algorithm. This method is
121     * provided in order to satisfy the requirements of the Encoder interface,
122     * and will throw an EncoderException if the supplied object is not of type
123     * java.lang.String.
124     *
125     * @param obj
126     *                  Object to encode
127     * @return An object (or type java.lang.String) containing the refined
128     *             soundex code which corresponds to the String supplied.
129     * @throws EncoderException
130     *                  if the parameter supplied is not of type java.lang.String
131     */
132    @Override
133    public Object encode(final Object obj) throws EncoderException {
134        if (!(obj instanceof String)) {
135            throw new EncoderException("Parameter supplied to RefinedSoundex encode is not of type java.lang.String");
136        }
137        return soundex((String) obj);
138    }
139
140    /**
141     * Encodes a String using the refined soundex algorithm.
142     *
143     * @param str
144     *                  A String object to encode
145     * @return A Soundex code corresponding to the String supplied
146     */
147    @Override
148    public String encode(final String str) {
149        return soundex(str);
150    }
151
152    /**
153     * Returns the mapping code for a given character. The mapping codes are
154     * maintained in an internal char array named soundexMapping, and the
155     * default values of these mappings are US English.
156     *
157     * @param c
158     *                  char to get mapping for
159     * @return A character (really a numeral) to return for the given char
160     */
161    char getMappingCode(final char c) {
162        if (!Character.isLetter(c)) {
163            return 0;
164        }
165        return this.soundexMapping[Character.toUpperCase(c) - 'A'];
166    }
167
168    /**
169     * Retrieves the Refined Soundex code for a given String object.
170     *
171     * @param str
172     *                  String to encode using the Refined Soundex algorithm
173     * @return A soundex code for the String supplied
174     */
175    public String soundex(String str) {
176        if (str == null) {
177            return null;
178        }
179        str = SoundexUtils.clean(str);
180        if (str.length() == 0) {
181            return str;
182        }
183
184        final StringBuilder sBuf = new StringBuilder();
185        sBuf.append(str.charAt(0));
186
187        char last, current;
188        last = '*';
189
190        for (int i = 0; i < str.length(); i++) {
191
192            current = getMappingCode(str.charAt(i));
193            if (current == last) {
194                continue;
195            } else if (current != 0) {
196                sBuf.append(current);
197            }
198
199            last = current;
200
201        }
202
203        return sBuf.toString();
204    }
205}