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.java 1811347 2017-10-06 15:21:18Z ggregory $
031 */
032public class RefinedSoundex implements StringEncoder {
033
034    /**
035     * Mapping:
036     * <pre>
037     * 0: A E I O U Y H W
038     * 1: B P
039     * 2: F V
040     * 3: C K S
041     * 4: G J
042     * 5: Q X Z
043     * 6: D T
044     * 7: L
045     * 8: M N
046     * 9: R
047     * </pre>
048     * @since 1.4
049     */
050    //                                                      ABCDEFGHIJKLMNOPQRSTUVWXYZ
051    public static final String US_ENGLISH_MAPPING_STRING = "01360240043788015936020505";
052
053   /**
054     * RefinedSoundex is *refined* for a number of reasons one being that the
055     * mappings have been altered. This implementation contains default
056     * mappings for US English.
057     */
058    private static final char[] US_ENGLISH_MAPPING = US_ENGLISH_MAPPING_STRING.toCharArray();
059
060    /**
061     * Every letter of the alphabet is "mapped" to a numerical value. This char
062     * array holds the values to which each letter is mapped. This
063     * implementation contains a default map for US_ENGLISH
064     */
065    private final char[] soundexMapping;
066
067    /**
068     * This static variable contains an instance of the RefinedSoundex using
069     * the US_ENGLISH mapping.
070     */
071    public static final RefinedSoundex US_ENGLISH = new RefinedSoundex();
072
073     /**
074     * Creates an instance of the RefinedSoundex object using the default US
075     * English mapping.
076     */
077    public RefinedSoundex() {
078        this.soundexMapping = US_ENGLISH_MAPPING;
079    }
080
081    /**
082     * Creates a refined soundex instance using a custom mapping. This
083     * constructor can be used to customize the mapping, and/or possibly
084     * provide an internationalized mapping for a non-Western character set.
085     *
086     * @param mapping
087     *                  Mapping array to use when finding the corresponding code for
088     *                  a given character
089     */
090    public RefinedSoundex(final char[] mapping) {
091        this.soundexMapping = new char[mapping.length];
092        System.arraycopy(mapping, 0, this.soundexMapping, 0, mapping.length);
093    }
094
095    /**
096     * Creates a refined Soundex instance using a custom mapping. This constructor can be used to customize the mapping,
097     * and/or possibly provide an internationalized mapping for a non-Western character set.
098     *
099     * @param mapping
100     *            Mapping string to use when finding the corresponding code for a given character
101     * @since 1.4
102     */
103    public RefinedSoundex(final String mapping) {
104        this.soundexMapping = mapping.toCharArray();
105    }
106
107    /**
108     * Returns the number of characters in the two encoded Strings that are the
109     * same. This return value ranges from 0 to the length of the shortest
110     * encoded String: 0 indicates little or no similarity, and 4 out of 4 (for
111     * example) indicates strong similarity or identical values. For refined
112     * Soundex, the return value can be greater than 4.
113     *
114     * @param s1
115     *                  A String that will be encoded and compared.
116     * @param s2
117     *                  A String that will be encoded and compared.
118     * @return The number of characters in the two encoded Strings that are the
119     *             same from 0 to to the length of the shortest encoded String.
120     *
121     * @see SoundexUtils#difference(StringEncoder,String,String)
122     * @see <a href="http://msdn.microsoft.com/library/default.asp?url=/library/en-us/tsqlref/ts_de-dz_8co5.asp">
123     *          MS T-SQL DIFFERENCE</a>
124     *
125     * @throws EncoderException
126     *                  if an error occurs encoding one of the strings
127     * @since 1.3
128     */
129    public int difference(final String s1, final String s2) throws EncoderException {
130        return SoundexUtils.difference(this, s1, s2);
131    }
132
133    /**
134     * Encodes an Object using the refined soundex algorithm. This method is
135     * provided in order to satisfy the requirements of the Encoder interface,
136     * and will throw an EncoderException if the supplied object is not of type
137     * java.lang.String.
138     *
139     * @param obj
140     *                  Object to encode
141     * @return An object (or type java.lang.String) containing the refined
142     *             soundex code which corresponds to the String supplied.
143     * @throws EncoderException
144     *                  if the parameter supplied is not of type java.lang.String
145     */
146    @Override
147    public Object encode(final Object obj) throws EncoderException {
148        if (!(obj instanceof String)) {
149            throw new EncoderException("Parameter supplied to RefinedSoundex encode is not of type java.lang.String");
150        }
151        return soundex((String) obj);
152    }
153
154    /**
155     * Encodes a String using the refined soundex algorithm.
156     *
157     * @param str
158     *                  A String object to encode
159     * @return A Soundex code corresponding to the String supplied
160     */
161    @Override
162    public String encode(final String str) {
163        return soundex(str);
164    }
165
166    /**
167     * Returns the mapping code for a given character. The mapping codes are
168     * maintained in an internal char array named soundexMapping, and the
169     * default values of these mappings are US English.
170     *
171     * @param c
172     *                  char to get mapping for
173     * @return A character (really a numeral) to return for the given char
174     */
175    char getMappingCode(final char c) {
176        if (!Character.isLetter(c)) {
177            return 0;
178        }
179        return this.soundexMapping[Character.toUpperCase(c) - 'A'];
180    }
181
182    /**
183     * Retrieves the Refined Soundex code for a given String object.
184     *
185     * @param str
186     *                  String to encode using the Refined Soundex algorithm
187     * @return A soundex code for the String supplied
188     */
189    public String soundex(String str) {
190        if (str == null) {
191            return null;
192        }
193        str = SoundexUtils.clean(str);
194        if (str.length() == 0) {
195            return str;
196        }
197
198        final StringBuilder sBuf = new StringBuilder();
199        sBuf.append(str.charAt(0));
200
201        char last, current;
202        last = '*';
203
204        for (int i = 0; i < str.length(); i++) {
205
206            current = getMappingCode(str.charAt(i));
207            if (current == last) {
208                continue;
209            } else if (current != 0) {
210                sBuf.append(current);
211            }
212
213            last = current;
214
215        }
216
217        return sBuf.toString();
218    }
219}