1 /* ====================================================================
2 * Copyright (c) 2006 J.T. Beetstra
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining
5 * a copy of this software and associated documentation files (the
6 * "Software"), to deal in the Software without restriction, including
7 * without limitation the rights to use, copy, modify, merge, publish,
8 * distribute, sublicense, and/or sell copies of the Software, and to
9 * permit persons to whom the Software is furnished to do so, subject to
10 * the following conditions:
11 *
12 * The above copyright notice and this permission notice shall be
13 * included in all copies or substantial portions of the Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
18 * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
19 * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
20 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
21 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
22 * ====================================================================
23 */
24 package com.beetstra.jutf7;
25
26 import java.nio.charset.Charset;
27 import java.nio.charset.CharsetDecoder;
28 import java.nio.charset.CharsetEncoder;
29 import java.util.Arrays;
30 import java.util.List;
31
32 /**
33 * <p>Abstract base class for UTF-7 style encoding and decoding.</p>
34 *
35 * @author Jaap Beetstra
36 */
37 abstract class UTF7StyleCharset extends Charset {
38 private static final List CONTAINED = Arrays.asList(new String[] { "US-ASCII", "ISO-8859-1",
39 "UTF-8", "UTF-16", "UTF-16LE", "UTF-16BE" });
40 final boolean strict;
41 Base64Util base64;
42
43 /**
44 * <p>Besides the name and aliases, two additional parameters are required. First the
45 * base 64 alphabet used; in modified UTF-7 a slightly different alphabet is used.
46 * Additionally, it should be specified if encoders and decoders should be strict
47 * about the interpretation of malformed encoded sequences. This is used since
48 * modified UTF-7 specifically disallows some constructs which are allowed (or not
49 * specifically disallowed) in UTF-7 (RFC 2152).</p>
50 *
51 * @param canonicalName The name as defined in java.nio.charset.Charset
52 * @param aliases The aliases as defined in java.nio.charset.Charset
53 * @param alphabet The base 64 alphabet used
54 * @param strict True if strict handling of sequences is requested
55 */
56 protected UTF7StyleCharset(String canonicalName, String[] aliases, String alphabet,
57 boolean strict) {
58 super(canonicalName, aliases);
59 this.base64 = new Base64Util(alphabet);
60 this.strict = strict;
61 }
62
63 /* (non-Javadoc)
64 * @see java.nio.charset.Charset#contains(java.nio.charset.Charset)
65 */
66 public boolean contains(final Charset cs) {
67 return CONTAINED.contains(cs.name());
68 }
69
70 /* (non-Javadoc)
71 * @see java.nio.charset.Charset#newDecoder()
72 */
73 public CharsetDecoder newDecoder() {
74 return new UTF7StyleCharsetDecoder(this, base64, strict);
75 }
76
77 /* (non-Javadoc)
78 * @see java.nio.charset.Charset#newEncoder()
79 */
80 public CharsetEncoder newEncoder() {
81 return new UTF7StyleCharsetEncoder(this, base64, strict);
82 }
83
84 /**
85 * Tells if a character can be encoded using simple (US-ASCII) encoding or
86 * requires base 64 encoding.
87 *
88 * @param ch The character
89 * @return True if the character can be encoded directly, false otherwise
90 */
91 abstract boolean canEncodeDirectly(char ch);
92
93 /**
94 * Returns character used to switch to base 64 encoding.
95 * @return The shift character
96 */
97 abstract byte shift();
98
99 /**
100 * Returns character used to switch from base 64 encoding to simple encoding.
101 * @return The unshift character
102 */
103 abstract byte unshift();
104 }