View Javadoc
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   */
18  
19  package org.apache.commons.compress.utils;
20  
21  import java.nio.charset.Charset;
22  
23  /**
24   * Charsets required of every implementation of the Java platform.
25   *
26   * From the Java documentation <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard
27   * charsets</a>:
28   * <p>
29   * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the
30   * release documentation for your implementation to see if any other encodings are supported. Consult the release
31   * documentation for your implementation to see if any other encodings are supported. </cite>
32   * </p>
33   *
34   * <dl>
35   * <dt><code>US-ASCII</code></dt>
36   * <dd>Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</dd>
37   * <dt><code>ISO-8859-1</code></dt>
38   * <dd>ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</dd>
39   * <dt><code>UTF-8</code></dt>
40   * <dd>Eight-bit Unicode Transformation Format.</dd>
41   * <dt><code>UTF-16BE</code></dt>
42   * <dd>Sixteen-bit Unicode Transformation Format, big-endian byte order.</dd>
43   * <dt><code>UTF-16LE</code></dt>
44   * <dd>Sixteen-bit Unicode Transformation Format, little-endian byte order.</dd>
45   * <dt><code>UTF-16</code></dt>
46   * <dd>Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
47   * accepted on input, big-endian used on output.)</dd>
48   * </dl>
49   *
50   * <p>This class best belongs in the Commons Lang or IO project. Even if a similar class is defined in another Commons
51   * component, it is not foreseen that Commons Compress would be made to depend on another Commons component.</p>
52   *
53   * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
54   * @since 1.4
55   * @version $Id: Charsets.java 1552970 2013-12-22 07:03:43Z bodewig $
56   */
57  public class Charsets {
58  
59      //
60      // This class should only contain Charset instances for required encodings. This guarantees that it will load correctly and
61      // without delay on all Java platforms.
62      //
63  
64      /**
65       * Returns the given Charset or the default Charset if the given Charset is null.
66       *
67       * @param charset
68       *            A charset or null.
69       * @return the given Charset or the default Charset if the given Charset is null
70       */
71      public static Charset toCharset(Charset charset) {
72          return charset == null ? Charset.defaultCharset() : charset;
73      }
74  
75      /**
76       * Returns a Charset for the named charset. If the name is null, return the default Charset.
77       *
78       * @param charset
79       *            The name of the requested charset, may be null.
80       * @return a Charset for the named charset
81       * @throws java.nio.charset.UnsupportedCharsetException
82       *             If the named charset is unavailable
83       * @throws java.nio.charset.IllegalCharsetNameException
84       *             If the given charset name is illegal
85       */
86      public static Charset toCharset(String charset) {
87          return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
88      }
89  
90      /**
91       * CharsetNamesISO 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       *
96       * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
97       */
98      public static final Charset ISO_8859_1 = Charset.forName(CharsetNames.ISO_8859_1);
99  
100     /**
101      * <p>
102      * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
103      * </p>
104      * <p>
105      * Every implementation of the Java platform is required to support this character encoding.
106      * </p>
107      *
108      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
109      */
110     public static final Charset US_ASCII = Charset.forName(CharsetNames.US_ASCII);
111 
112     /**
113      * <p>
114      * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
115      * (either order accepted on input, big-endian used on output)
116      * </p>
117      * <p>
118      * Every implementation of the Java platform is required to support this character encoding.
119      * </p>
120      *
121      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
122      */
123     public static final Charset UTF_16 = Charset.forName(CharsetNames.UTF_16);
124 
125     /**
126      * <p>
127      * Sixteen-bit Unicode Transformation Format, big-endian byte order.
128      * </p>
129      * <p>
130      * Every implementation of the Java platform is required to support this character encoding.
131      * </p>
132      *
133      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
134      */
135     public static final Charset UTF_16BE = Charset.forName(CharsetNames.UTF_16BE);
136 
137     /**
138      * <p>
139      * Sixteen-bit Unicode Transformation Format, little-endian byte order.
140      * </p>
141      * <p>
142      * Every implementation of the Java platform is required to support this character encoding.
143      * </p>
144      *
145      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
146      */
147     public static final Charset UTF_16LE = Charset.forName(CharsetNames.UTF_16LE);
148 
149     /**
150      * <p>
151      * Eight-bit Unicode Transformation Format.
152      * </p>
153      * <p>
154      * Every implementation of the Java platform is required to support this character encoding.
155      * </p>
156      *
157      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
158      */
159     public static final Charset UTF_8 = Charset.forName(CharsetNames.UTF_8);
160 }