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 *      https://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 java.util.Locale;
021
022/**
023 * Encodes a string into a Caverphone 2.0 value.
024 *
025 * This is an algorithm created by the Caversham Project at the University of Otago. It implements the Caverphone 2.0
026 * algorithm:
027 *
028 * @see <a href="https://en.wikipedia.org/wiki/Caverphone">Wikipedia - Caverphone</a>
029 * @see <a href="https://caversham.otago.ac.nz/files/working/ctp150804.pdf">Caverphone 2.0 specification</a>
030 * @since 1.5
031 *
032 * <p>
033 * This class is immutable and thread-safe.
034 * </p>
035 */
036public class Caverphone2 extends AbstractCaverphone {
037
038    private static final String TEN_1 = "1111111111";
039
040    /**
041     * Constructs a new instance.
042     */
043    public Caverphone2() {
044        // empty
045    }
046
047    /**
048     * Encodes the given String into a Caverphone 2.0 value.
049     *
050     * @param source
051     *            String the source string.
052     * @return A Caverphone code for the given String.
053     */
054    @Override
055    public String encode(final String source) {
056        String txt = source;
057        if (SoundexUtils.isEmpty(txt)) {
058            return TEN_1;
059        }
060
061        // 1. Convert to lowercase
062        txt = txt.toLowerCase(Locale.ENGLISH);
063
064        // 2. Remove anything not A-Z
065        txt = txt.replaceAll("[^a-z]", "");
066
067        // 2.5. Remove final e
068        txt = txt.replaceAll("e$", ""); // 2.0 only
069
070        // 3. Handle various start options
071        txt = txt.replaceAll("^cough", "cou2f");
072        txt = txt.replaceAll("^rough", "rou2f");
073        txt = txt.replaceAll("^tough", "tou2f");
074        txt = txt.replaceAll("^enough", "enou2f"); // 2.0 only
075        txt = txt.replaceAll("^trough", "trou2f"); // 2.0 only
076                                                   // note the spec says ^enough here again, c+p error I assume
077        txt = txt.replaceAll("^gn", "2n");
078
079        // End
080        txt = txt.replaceAll("mb$", "m2");
081
082        // 4. Handle replacements
083        txt = txt.replace("cq", "2q");
084        txt = txt.replace("ci", "si");
085        txt = txt.replace("ce", "se");
086        txt = txt.replace("cy", "sy");
087        txt = txt.replace("tch", "2ch");
088        txt = txt.replace("c", "k");
089        txt = txt.replace("q", "k");
090        txt = txt.replace("x", "k");
091        txt = txt.replace("v", "f");
092        txt = txt.replace("dg", "2g");
093        txt = txt.replace("tio", "sio");
094        txt = txt.replace("tia", "sia");
095        txt = txt.replace("d", "t");
096        txt = txt.replace("ph", "fh");
097        txt = txt.replace("b", "p");
098        txt = txt.replace("sh", "s2");
099        txt = txt.replace("z", "s");
100        txt = txt.replaceAll("^[aeiou]", "A");
101        txt = txt.replaceAll("[aeiou]", "3");
102        txt = txt.replace("j", "y"); // 2.0 only
103        txt = txt.replaceAll("^y3", "Y3"); // 2.0 only
104        txt = txt.replaceAll("^y", "A"); // 2.0 only
105        txt = txt.replace("y", "3"); // 2.0 only
106        txt = txt.replace("3gh3", "3kh3");
107        txt = txt.replace("gh", "22");
108        txt = txt.replace("g", "k");
109        txt = txt.replaceAll("s+", "S");
110        txt = txt.replaceAll("t+", "T");
111        txt = txt.replaceAll("p+", "P");
112        txt = txt.replaceAll("k+", "K");
113        txt = txt.replaceAll("f+", "F");
114        txt = txt.replaceAll("m+", "M");
115        txt = txt.replaceAll("n+", "N");
116        txt = txt.replace("w3", "W3");
117        txt = txt.replace("wh3", "Wh3");
118        txt = txt.replaceAll("w$", "3"); // 2.0 only
119        txt = txt.replace("w", "2");
120        txt = txt.replaceAll("^h", "A");
121        txt = txt.replace("h", "2");
122        txt = txt.replace("r3", "R3");
123        txt = txt.replaceAll("r$", "3"); // 2.0 only
124        txt = txt.replace("r", "2");
125        txt = txt.replace("l3", "L3");
126        txt = txt.replaceAll("l$", "3"); // 2.0 only
127        txt = txt.replace("l", "2");
128
129        // 5. Handle removals
130        txt = txt.replace("2", "");
131        txt = txt.replaceAll("3$", "A"); // 2.0 only
132        txt = txt.replace("3", "");
133
134        // 6. put ten 1s on the end
135        txt += TEN_1;
136
137        // 7. take the first ten characters as the code
138        return txt.substring(0, TEN_1.length());
139    }
140
141}