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