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
020/**
021 * Encodes a string into a Caverphone 2.0 value.
022 *
023 * This is an algorithm created by the Caversham Project at the University of Otago. It implements the Caverphone 2.0
024 * algorithm:
025 *
026 * @see <a href="https://en.wikipedia.org/wiki/Caverphone">Wikipedia - Caverphone</a>
027 * @see <a href="https://caversham.otago.ac.nz/files/working/ctp150804.pdf">Caverphone 2.0 specification</a>
028 * @since 1.5
029 *
030 * <p>This class is immutable and thread-safe.</p>
031 */
032public class Caverphone2 extends AbstractCaverphone {
033
034    private static final String TEN_1 = "1111111111";
035
036    /**
037     * Constructs a new instance.
038     */
039    public Caverphone2() {
040        // empty
041    }
042
043    /**
044     * Encodes the given String into a Caverphone 2.0 value.
045     *
046     * @param source
047     *            String the source string
048     * @return A Caverphone code for the given String
049     */
050    @Override
051    public String encode(final String source) {
052        String txt = source;
053        if (SoundexUtils.isEmpty(txt)) {
054            return TEN_1;
055        }
056
057        // 1. Convert to lowercase
058        txt = txt.toLowerCase(java.util.Locale.ENGLISH);
059
060        // 2. Remove anything not A-Z
061        txt = txt.replaceAll("[^a-z]", "");
062
063        // 2.5. Remove final e
064        txt = txt.replaceAll("e$", ""); // 2.0 only
065
066        // 3. Handle various start options
067        txt = txt.replaceAll("^cough", "cou2f");
068        txt = txt.replaceAll("^rough", "rou2f");
069        txt = txt.replaceAll("^tough", "tou2f");
070        txt = txt.replaceAll("^enough", "enou2f"); // 2.0 only
071        txt = txt.replaceAll("^trough", "trou2f"); // 2.0 only
072                                                   // note the spec says ^enough here again, c+p error I assume
073        txt = txt.replaceAll("^gn", "2n");
074
075        // End
076        txt = txt.replaceAll("mb$", "m2");
077
078        // 4. Handle replacements
079        txt = txt.replace("cq", "2q");
080        txt = txt.replace("ci", "si");
081        txt = txt.replace("ce", "se");
082        txt = txt.replace("cy", "sy");
083        txt = txt.replace("tch", "2ch");
084        txt = txt.replace("c", "k");
085        txt = txt.replace("q", "k");
086        txt = txt.replace("x", "k");
087        txt = txt.replace("v", "f");
088        txt = txt.replace("dg", "2g");
089        txt = txt.replace("tio", "sio");
090        txt = txt.replace("tia", "sia");
091        txt = txt.replace("d", "t");
092        txt = txt.replace("ph", "fh");
093        txt = txt.replace("b", "p");
094        txt = txt.replace("sh", "s2");
095        txt = txt.replace("z", "s");
096        txt = txt.replaceAll("^[aeiou]", "A");
097        txt = txt.replaceAll("[aeiou]", "3");
098        txt = txt.replace("j", "y"); // 2.0 only
099        txt = txt.replaceAll("^y3", "Y3"); // 2.0 only
100        txt = txt.replaceAll("^y", "A"); // 2.0 only
101        txt = txt.replace("y", "3"); // 2.0 only
102        txt = txt.replace("3gh3", "3kh3");
103        txt = txt.replace("gh", "22");
104        txt = txt.replace("g", "k");
105        txt = txt.replaceAll("s+", "S");
106        txt = txt.replaceAll("t+", "T");
107        txt = txt.replaceAll("p+", "P");
108        txt = txt.replaceAll("k+", "K");
109        txt = txt.replaceAll("f+", "F");
110        txt = txt.replaceAll("m+", "M");
111        txt = txt.replaceAll("n+", "N");
112        txt = txt.replace("w3", "W3");
113        txt = txt.replace("wh3", "Wh3");
114        txt = txt.replaceAll("w$", "3"); // 2.0 only
115        txt = txt.replace("w", "2");
116        txt = txt.replaceAll("^h", "A");
117        txt = txt.replace("h", "2");
118        txt = txt.replace("r3", "R3");
119        txt = txt.replaceAll("r$", "3"); // 2.0 only
120        txt = txt.replace("r", "2");
121        txt = txt.replace("l3", "L3");
122        txt = txt.replaceAll("l$", "3"); // 2.0 only
123        txt = txt.replace("l", "2");
124
125        // 5. Handle removals
126        txt = txt.replace("2", "");
127        txt = txt.replaceAll("3$", "A"); // 2.0 only
128        txt = txt.replace("3", "");
129
130        // 6. put ten 1s on the end
131        txt += TEN_1;
132
133        // 7. take the first ten characters as the code
134        return txt.substring(0, TEN_1.length());
135    }
136
137}