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 * http://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 package org.apache.commons.codec;
18
19 import java.nio.charset.Charset;
20
21 /**
22 * Charsets required of every implementation of the Java platform.
23 *
24 * From the Java documentation <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard
25 * charsets</a>:
26 * <p>
27 * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the
28 * release documentation for your implementation to see if any other encodings are supported. Consult the release
29 * documentation for your implementation to see if any other encodings are supported. </cite>
30 * </p>
31 *
32 * <ul>
33 * <li><code>US-ASCII</code><br/>
34 * Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</li>
35 * <li><code>ISO-8859-1</code><br/>
36 * ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</li>
37 * <li><code>UTF-8</code><br/>
38 * Eight-bit Unicode Transformation Format.</li>
39 * <li><code>UTF-16BE</code><br/>
40 * Sixteen-bit Unicode Transformation Format, big-endian byte order.</li>
41 * <li><code>UTF-16LE</code><br/>
42 * Sixteen-bit Unicode Transformation Format, little-endian byte order.</li>
43 * <li><code>UTF-16</code><br/>
44 * Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
45 * accepted on input, big-endian used on output.)</li>
46 * </ul>
47 *
48 * This perhaps would best belong in the Commons Lang project. Even if a similar class is defined in Commons Lang, it is
49 * not foreseen that Commons Codec would be made to depend on Commons Lang.
50 *
51 * <p>
52 * This class is immutable and thread-safe.
53 * </p>
54 *
55 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
56 * @since 1.7
57 * @version $Id: Charsets.html 889935 2013-12-11 05:05:13Z ggregory $
58 */
59 public class Charsets {
60
61 //
62 // This class should only contain Charset instances for required encodings. This guarantees that it will load
63 // correctly and without delay on all Java platforms.
64 //
65
66 /**
67 * Returns the given Charset or the default Charset if the given Charset is null.
68 *
69 * @param charset
70 * A charset or null.
71 * @return the given Charset or the default Charset if the given Charset is null
72 */
73 public static Charset toCharset(Charset charset) {
74 return charset == null ? Charset.defaultCharset() : charset;
75 }
76
77 /**
78 * Returns a Charset for the named charset. If the name is null, return the default Charset.
79 *
80 * @param charset
81 * The name of the requested charset, may be null.
82 * @return a Charset for the named charset
83 * @throws java.nio.charset.UnsupportedCharsetException
84 * If the named charset is unavailable
85 */
86 public static Charset toCharset(String charset) {
87 return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
88 }
89
90 /**
91 * CharEncodingISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.
92 * <p>
93 * Every implementation of the Java platform is required to support this character encoding.
94 *
95 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
96 */
97 public static final Charset ISO_8859_1 = Charset.forName(CharEncoding.ISO_8859_1);
98
99 /**
100 * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
101 * <p>
102 * Every implementation of the Java platform is required to support this character encoding.
103 *
104 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
105 */
106 public static final Charset US_ASCII = Charset.forName(CharEncoding.US_ASCII);
107
108 /**
109 * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
110 * (either order accepted on input, big-endian used on output)
111 * <p>
112 * Every implementation of the Java platform is required to support this character encoding.
113 *
114 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
115 */
116 public static final Charset UTF_16 = Charset.forName(CharEncoding.UTF_16);
117
118 /**
119 * Sixteen-bit Unicode Transformation Format, big-endian byte order.
120 * <p>
121 * Every implementation of the Java platform is required to support this character encoding.
122 *
123 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
124 */
125 public static final Charset UTF_16BE = Charset.forName(CharEncoding.UTF_16BE);
126
127 /**
128 * Sixteen-bit Unicode Transformation Format, little-endian byte order.
129 * <p>
130 * Every implementation of the Java platform is required to support this character encoding.
131 *
132 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
133 */
134 public static final Charset UTF_16LE = Charset.forName(CharEncoding.UTF_16LE);
135
136 /**
137 * Eight-bit Unicode Transformation Format.
138 * <p>
139 * Every implementation of the Java platform is required to support this character encoding.
140 *
141 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
142 */
143 public static final Charset UTF_8 = Charset.forName(CharEncoding.UTF_8);
144 }