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
020/**
021 * Encodes a string into a Caverphone 1.0 value.
022 *
023 * This is an algorithm created by the Caversham Project at the University of Otago. It implements the Caverphone 1.0
024 * algorithm:
025 *
026 * @version $Id: Caverphone.java 1075947 2011-03-01 17:56:14Z ggregory $
027 * @see <a href="http://en.wikipedia.org/wiki/Caverphone">Wikipedia - Caverphone</a>
028 * @see <a href="http://caversham.otago.ac.nz/files/working/ctp060902.pdf">Caverphone 1.0 specification</a>
029 * @since 1.5
030 *
031 * <p>This class is immutable and thread-safe.</p>
032 */
033public class Caverphone1 extends AbstractCaverphone {
034
035    private static final String SIX_1 = "111111";
036
037    /**
038     * Encodes the given String into a Caverphone value.
039     *
040     * @param source
041     *            String the source string
042     * @return A caverphone code for the given String
043     */
044    @Override
045    public String encode(final String source) {
046        String txt = source;
047        if (txt == null || txt.length() == 0) {
048            return SIX_1;
049        }
050
051        // 1. Convert to lowercase
052        txt = txt.toLowerCase(java.util.Locale.ENGLISH);
053
054        // 2. Remove anything not A-Z
055        txt = txt.replaceAll("[^a-z]", "");
056
057        // 3. Handle various start options
058        // 2 is a temporary placeholder to indicate a consonant which we are no longer interested in.
059        txt = txt.replaceAll("^cough", "cou2f");
060        txt = txt.replaceAll("^rough", "rou2f");
061        txt = txt.replaceAll("^tough", "tou2f");
062        txt = txt.replaceAll("^enough", "enou2f");
063        txt = txt.replaceAll("^gn", "2n");
064
065        // End
066        txt = txt.replaceAll("mb$", "m2");
067
068        // 4. Handle replacements
069        txt = txt.replaceAll("cq", "2q");
070        txt = txt.replaceAll("ci", "si");
071        txt = txt.replaceAll("ce", "se");
072        txt = txt.replaceAll("cy", "sy");
073        txt = txt.replaceAll("tch", "2ch");
074        txt = txt.replaceAll("c", "k");
075        txt = txt.replaceAll("q", "k");
076        txt = txt.replaceAll("x", "k");
077        txt = txt.replaceAll("v", "f");
078        txt = txt.replaceAll("dg", "2g");
079        txt = txt.replaceAll("tio", "sio");
080        txt = txt.replaceAll("tia", "sia");
081        txt = txt.replaceAll("d", "t");
082        txt = txt.replaceAll("ph", "fh");
083        txt = txt.replaceAll("b", "p");
084        txt = txt.replaceAll("sh", "s2");
085        txt = txt.replaceAll("z", "s");
086        txt = txt.replaceAll("^[aeiou]", "A");
087        // 3 is a temporary placeholder marking a vowel
088        txt = txt.replaceAll("[aeiou]", "3");
089        txt = txt.replaceAll("3gh3", "3kh3");
090        txt = txt.replaceAll("gh", "22");
091        txt = txt.replaceAll("g", "k");
092        txt = txt.replaceAll("s+", "S");
093        txt = txt.replaceAll("t+", "T");
094        txt = txt.replaceAll("p+", "P");
095        txt = txt.replaceAll("k+", "K");
096        txt = txt.replaceAll("f+", "F");
097        txt = txt.replaceAll("m+", "M");
098        txt = txt.replaceAll("n+", "N");
099        txt = txt.replaceAll("w3", "W3");
100        txt = txt.replaceAll("wy", "Wy"); // 1.0 only
101        txt = txt.replaceAll("wh3", "Wh3");
102        txt = txt.replaceAll("why", "Why"); // 1.0 only
103        txt = txt.replaceAll("w", "2");
104        txt = txt.replaceAll("^h", "A");
105        txt = txt.replaceAll("h", "2");
106        txt = txt.replaceAll("r3", "R3");
107        txt = txt.replaceAll("ry", "Ry"); // 1.0 only
108        txt = txt.replaceAll("r", "2");
109        txt = txt.replaceAll("l3", "L3");
110        txt = txt.replaceAll("ly", "Ly"); // 1.0 only
111        txt = txt.replaceAll("l", "2");
112        txt = txt.replaceAll("j", "y"); // 1.0 only
113        txt = txt.replaceAll("y3", "Y3"); // 1.0 only
114        txt = txt.replaceAll("y", "2"); // 1.0 only
115
116        // 5. Handle removals
117        txt = txt.replaceAll("2", "");
118        txt = txt.replaceAll("3", "");
119
120        // 6. put ten 1s on the end
121        txt = txt + SIX_1;
122
123        // 7. take the first six characters as the code
124        return txt.substring(0, SIX_1.length());
125    }
126
127}