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