1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * https://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17
18 package org.apache.commons.codec.language;
19
20 import java.util.Locale;
21
22 /**
23 * Encodes a string into a Caverphone 2.0 value.
24 *
25 * This is an algorithm created by the Caversham Project at the University of Otago. It implements the Caverphone 2.0
26 * algorithm:
27 *
28 * @see <a href="https://en.wikipedia.org/wiki/Caverphone">Wikipedia - Caverphone</a>
29 * @see <a href="https://caversham.otago.ac.nz/files/working/ctp150804.pdf">Caverphone 2.0 specification</a>
30 * @since 1.5
31 *
32 * <p>This class is immutable and thread-safe.</p>
33 */
34 public class Caverphone2 extends AbstractCaverphone {
35
36 private static final String TEN_1 = "1111111111";
37
38 /**
39 * Constructs a new instance.
40 */
41 public Caverphone2() {
42 // empty
43 }
44
45 /**
46 * Encodes the given String into a Caverphone 2.0 value.
47 *
48 * @param source
49 * String the source string.
50 * @return A Caverphone code for the given String.
51 */
52 @Override
53 public String encode(final String source) {
54 String txt = source;
55 if (SoundexUtils.isEmpty(txt)) {
56 return TEN_1;
57 }
58
59 // 1. Convert to lowercase
60 txt = txt.toLowerCase(Locale.ENGLISH);
61
62 // 2. Remove anything not A-Z
63 txt = txt.replaceAll("[^a-z]", "");
64
65 // 2.5. Remove final e
66 txt = txt.replaceAll("e$", ""); // 2.0 only
67
68 // 3. Handle various start options
69 txt = txt.replaceAll("^cough", "cou2f");
70 txt = txt.replaceAll("^rough", "rou2f");
71 txt = txt.replaceAll("^tough", "tou2f");
72 txt = txt.replaceAll("^enough", "enou2f"); // 2.0 only
73 txt = txt.replaceAll("^trough", "trou2f"); // 2.0 only
74 // note the spec says ^enough here again, c+p error I assume
75 txt = txt.replaceAll("^gn", "2n");
76
77 // End
78 txt = txt.replaceAll("mb$", "m2");
79
80 // 4. Handle replacements
81 txt = txt.replace("cq", "2q");
82 txt = txt.replace("ci", "si");
83 txt = txt.replace("ce", "se");
84 txt = txt.replace("cy", "sy");
85 txt = txt.replace("tch", "2ch");
86 txt = txt.replace("c", "k");
87 txt = txt.replace("q", "k");
88 txt = txt.replace("x", "k");
89 txt = txt.replace("v", "f");
90 txt = txt.replace("dg", "2g");
91 txt = txt.replace("tio", "sio");
92 txt = txt.replace("tia", "sia");
93 txt = txt.replace("d", "t");
94 txt = txt.replace("ph", "fh");
95 txt = txt.replace("b", "p");
96 txt = txt.replace("sh", "s2");
97 txt = txt.replace("z", "s");
98 txt = txt.replaceAll("^[aeiou]", "A");
99 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 }