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
018 package 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 * @author Apache Software Foundation
027 * @version $Id: Caverphone.java 1075947 2011-03-01 17:56:14Z ggregory $
028 * @see <a href="http://en.wikipedia.org/wiki/Caverphone">Wikipedia - Caverphone</a>
029 * @see <a href="http://caversham.otago.ac.nz/files/working/ctp150804.pdf">Caverphone 2.0 specification</a>
030 * @since 1.5
031 */
032 public class Caverphone2 extends AbstractCaverphone {
033
034 private static final String TEN_1 = "1111111111";
035
036 /**
037 * Encodes the given String into a Caverphone 2.0 value.
038 *
039 * @param source
040 * String the source string
041 * @return A caverphone code for the given String
042 */
043 public String encode(String source) {
044 String txt = source;
045 if (txt == null || txt.length() == 0) {
046 return TEN_1;
047 }
048
049 // 1. Convert to lowercase
050 txt = txt.toLowerCase(java.util.Locale.ENGLISH);
051
052 // 2. Remove anything not A-Z
053 txt = txt.replaceAll("[^a-z]", "");
054
055 // 2.5. Remove final e
056 txt = txt.replaceAll("e$", ""); // 2.0 only
057
058 // 3. Handle various start options
059 txt = txt.replaceAll("^cough", "cou2f");
060 txt = txt.replaceAll("^rough", "rou2f");
061 txt = txt.replaceAll("^tough", "tou2f");
062 txt = txt.replaceAll("^enough", "enou2f"); // 2.0 only
063 txt = txt.replaceAll("^trough", "trou2f"); // 2.0 only - note the spec says ^enough here again, c+p error I assume
064 txt = txt.replaceAll("^gn", "2n");
065
066 // End
067 txt = txt.replaceAll("mb$", "m2");
068
069 // 4. Handle replacements
070 txt = txt.replaceAll("cq", "2q");
071 txt = txt.replaceAll("ci", "si");
072 txt = txt.replaceAll("ce", "se");
073 txt = txt.replaceAll("cy", "sy");
074 txt = txt.replaceAll("tch", "2ch");
075 txt = txt.replaceAll("c", "k");
076 txt = txt.replaceAll("q", "k");
077 txt = txt.replaceAll("x", "k");
078 txt = txt.replaceAll("v", "f");
079 txt = txt.replaceAll("dg", "2g");
080 txt = txt.replaceAll("tio", "sio");
081 txt = txt.replaceAll("tia", "sia");
082 txt = txt.replaceAll("d", "t");
083 txt = txt.replaceAll("ph", "fh");
084 txt = txt.replaceAll("b", "p");
085 txt = txt.replaceAll("sh", "s2");
086 txt = txt.replaceAll("z", "s");
087 txt = txt.replaceAll("^[aeiou]", "A");
088 txt = txt.replaceAll("[aeiou]", "3");
089 txt = txt.replaceAll("j", "y"); // 2.0 only
090 txt = txt.replaceAll("^y3", "Y3"); // 2.0 only
091 txt = txt.replaceAll("^y", "A"); // 2.0 only
092 txt = txt.replaceAll("y", "3"); // 2.0 only
093 txt = txt.replaceAll("3gh3", "3kh3");
094 txt = txt.replaceAll("gh", "22");
095 txt = txt.replaceAll("g", "k");
096 txt = txt.replaceAll("s+", "S");
097 txt = txt.replaceAll("t+", "T");
098 txt = txt.replaceAll("p+", "P");
099 txt = txt.replaceAll("k+", "K");
100 txt = txt.replaceAll("f+", "F");
101 txt = txt.replaceAll("m+", "M");
102 txt = txt.replaceAll("n+", "N");
103 txt = txt.replaceAll("w3", "W3");
104 txt = txt.replaceAll("wh3", "Wh3");
105 txt = txt.replaceAll("w$", "3"); // 2.0 only
106 txt = txt.replaceAll("w", "2");
107 txt = txt.replaceAll("^h", "A");
108 txt = txt.replaceAll("h", "2");
109 txt = txt.replaceAll("r3", "R3");
110 txt = txt.replaceAll("r$", "3"); // 2.0 only
111 txt = txt.replaceAll("r", "2");
112 txt = txt.replaceAll("l3", "L3");
113 txt = txt.replaceAll("l$", "3"); // 2.0 only
114 txt = txt.replaceAll("l", "2");
115
116 // 5. Handle removals
117 txt = txt.replaceAll("2", "");
118 txt = txt.replaceAll("3$", "A"); // 2.0 only
119 txt = txt.replaceAll("3", "");
120
121 // 6. put ten 1s on the end
122 txt = txt + TEN_1;
123
124 // 7. take the first ten characters as the code
125 return txt.substring(0, TEN_1.length());
126 }
127
128 }