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: CharEncoding.java 1173287 2011-09-20 18:16:19Z 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(final 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(final 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 * </p>
95 * <p>
96 * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
97 * </p>
98 *
99 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
100 */
101 public static final Charset ISO_8859_1 = Charset.forName(CharEncoding.ISO_8859_1);
102
103 /**
104 * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
105 * <p>
106 * Every implementation of the Java platform is required to support this character encoding.
107 * </p>
108 * <p>
109 * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
110 * </p>
111 *
112 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
113 */
114 public static final Charset US_ASCII = Charset.forName(CharEncoding.US_ASCII);
115
116 /**
117 * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
118 * (either order accepted on input, big-endian used on output)
119 * <p>
120 * Every implementation of the Java platform is required to support this character encoding.
121 * </p>
122 * <p>
123 * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
124 * </p>
125 *
126 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
127 */
128 public static final Charset UTF_16 = Charset.forName(CharEncoding.UTF_16);
129
130 /**
131 * Sixteen-bit Unicode Transformation Format, big-endian byte order.
132 * <p>
133 * Every implementation of the Java platform is required to support this character encoding.
134 * </p>
135 * <p>
136 * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
137 * </p>
138 *
139 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
140 */
141 public static final Charset UTF_16BE = Charset.forName(CharEncoding.UTF_16BE);
142
143 /**
144 * Sixteen-bit Unicode Transformation Format, little-endian byte order.
145 * <p>
146 * Every implementation of the Java platform is required to support this character encoding.
147 * </p>
148 * <p>
149 * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
150 * </p>
151 *
152 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
153 */
154 public static final Charset UTF_16LE = Charset.forName(CharEncoding.UTF_16LE);
155
156 /**
157 * Eight-bit Unicode Transformation Format.
158 * <p>
159 * Every implementation of the Java platform is required to support this character encoding.
160 * </p>
161 * <p>
162 * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
163 * </p>
164 *
165 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
166 */
167 public static final Charset UTF_8 = Charset.forName(CharEncoding.UTF_8);
168 }