1 // Mozilla has modified this file - see https://hg.mozilla.org/ for details. 2 /* 3 * Licensed to the Apache Software Foundation (ASF) under one or more 4 * contributor license agreements. See the NOTICE file distributed with 5 * this work for additional information regarding copyright ownership. 6 * The ASF licenses this file to You under the Apache License, Version 2.0 7 * (the "License"); you may not use this file except in compliance with 8 * the License. You may obtain a copy of the License at 9 * 10 * http://www.apache.org/licenses/LICENSE-2.0 11 * 12 * Unless required by applicable law or agreed to in writing, software 13 * distributed under the License is distributed on an "AS IS" BASIS, 14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 15 * See the License for the specific language governing permissions and 16 * limitations under the License. 17 */ 18 19 package org.mozilla.apache.commons.codec.language; 20 21 /** 22 * Encodes a string into a Caverphone 2.0 value. 23 * 24 * This is an algorithm created by the Caversham Project at the University of Otago. It implements the Caverphone 2.0 25 * algorithm: 26 * 27 * @author Apache Software Foundation 28 * @version $Id: Caverphone.java 1075947 2011-03-01 17:56:14Z ggregory $ 29 * @see <a href="http://en.wikipedia.org/wiki/Caverphone">Wikipedia - Caverphone</a> 30 * @see <a href="http://caversham.otago.ac.nz/files/working/ctp150804.pdf">Caverphone 2.0 specification</a> 31 * @since 1.5 32 */ 33 public class Caverphone2 extends AbstractCaverphone { 34 35 private static final String TEN_1 = "1111111111"; 36 37 /** 38 * Encodes the given String into a Caverphone 2.0 value. 39 * 40 * @param source 41 * String the source string 42 * @return A caverphone code for the given String 43 */ encode(String source)44 public String encode(String source) { 45 String txt = source; 46 if (txt == null || txt.length() == 0) { 47 return TEN_1; 48 } 49 50 // 1. Convert to lowercase 51 txt = txt.toLowerCase(java.util.Locale.ENGLISH); 52 53 // 2. Remove anything not A-Z 54 txt = txt.replaceAll("[^a-z]", ""); 55 56 // 2.5. Remove final e 57 txt = txt.replaceAll("e$", ""); // 2.0 only 58 59 // 3. Handle various start options 60 txt = txt.replaceAll("^cough", "cou2f"); 61 txt = txt.replaceAll("^rough", "rou2f"); 62 txt = txt.replaceAll("^tough", "tou2f"); 63 txt = txt.replaceAll("^enough", "enou2f"); // 2.0 only 64 txt = txt.replaceAll("^trough", "trou2f"); // 2.0 only - note the spec says ^enough here again, c+p error I assume 65 txt = txt.replaceAll("^gn", "2n"); 66 67 // End 68 txt = txt.replaceAll("mb$", "m2"); 69 70 // 4. Handle replacements 71 txt = txt.replaceAll("cq", "2q"); 72 txt = txt.replaceAll("ci", "si"); 73 txt = txt.replaceAll("ce", "se"); 74 txt = txt.replaceAll("cy", "sy"); 75 txt = txt.replaceAll("tch", "2ch"); 76 txt = txt.replaceAll("c", "k"); 77 txt = txt.replaceAll("q", "k"); 78 txt = txt.replaceAll("x", "k"); 79 txt = txt.replaceAll("v", "f"); 80 txt = txt.replaceAll("dg", "2g"); 81 txt = txt.replaceAll("tio", "sio"); 82 txt = txt.replaceAll("tia", "sia"); 83 txt = txt.replaceAll("d", "t"); 84 txt = txt.replaceAll("ph", "fh"); 85 txt = txt.replaceAll("b", "p"); 86 txt = txt.replaceAll("sh", "s2"); 87 txt = txt.replaceAll("z", "s"); 88 txt = txt.replaceAll("^[aeiou]", "A"); 89 txt = txt.replaceAll("[aeiou]", "3"); 90 txt = txt.replaceAll("j", "y"); // 2.0 only 91 txt = txt.replaceAll("^y3", "Y3"); // 2.0 only 92 txt = txt.replaceAll("^y", "A"); // 2.0 only 93 txt = txt.replaceAll("y", "3"); // 2.0 only 94 txt = txt.replaceAll("3gh3", "3kh3"); 95 txt = txt.replaceAll("gh", "22"); 96 txt = txt.replaceAll("g", "k"); 97 txt = txt.replaceAll("s+", "S"); 98 txt = txt.replaceAll("t+", "T"); 99 txt = txt.replaceAll("p+", "P"); 100 txt = txt.replaceAll("k+", "K"); 101 txt = txt.replaceAll("f+", "F"); 102 txt = txt.replaceAll("m+", "M"); 103 txt = txt.replaceAll("n+", "N"); 104 txt = txt.replaceAll("w3", "W3"); 105 txt = txt.replaceAll("wh3", "Wh3"); 106 txt = txt.replaceAll("w$", "3"); // 2.0 only 107 txt = txt.replaceAll("w", "2"); 108 txt = txt.replaceAll("^h", "A"); 109 txt = txt.replaceAll("h", "2"); 110 txt = txt.replaceAll("r3", "R3"); 111 txt = txt.replaceAll("r$", "3"); // 2.0 only 112 txt = txt.replaceAll("r", "2"); 113 txt = txt.replaceAll("l3", "L3"); 114 txt = txt.replaceAll("l$", "3"); // 2.0 only 115 txt = txt.replaceAll("l", "2"); 116 117 // 5. Handle removals 118 txt = txt.replaceAll("2", ""); 119 txt = txt.replaceAll("3$", "A"); // 2.0 only 120 txt = txt.replaceAll("3", ""); 121 122 // 6. put ten 1s on the end 123 txt = txt + TEN_1; 124 125 // 7. take the first ten characters as the code 126 return txt.substring(0, TEN_1.length()); 127 } 128 129 } 130