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  import java.nio.charset.StandardCharsets;
23  
24  /**
25   * Charsets required of every implementation of the Java platform.
26   *
27   * From the Java documentation <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard
28   * charsets</a>:
29   * <p>
30   * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the
31   * release documentation for your implementation to see if any other encodings are supported. Consult the release
32   * documentation for your implementation to see if any other encodings are supported. </cite>
33   * </p>
34   *
35   * <dl>
36   * <dt><code>US-ASCII</code></dt>
37   * <dd>Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</dd>
38   * <dt><code>ISO-8859-1</code></dt>
39   * <dd>ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</dd>
40   * <dt><code>UTF-8</code></dt>
41   * <dd>Eight-bit Unicode Transformation Format.</dd>
42   * <dt><code>UTF-16BE</code></dt>
43   * <dd>Sixteen-bit Unicode Transformation Format, big-endian byte order.</dd>
44   * <dt><code>UTF-16LE</code></dt>
45   * <dd>Sixteen-bit Unicode Transformation Format, little-endian byte order.</dd>
46   * <dt><code>UTF-16</code></dt>
47   * <dd>Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
48   * accepted on input, big-endian used on output.)</dd>
49   * </dl>
50   *
51   * <p>This class best belongs in the Commons Lang or IO project. Even if a similar class is defined in another Commons
52   * component, it is not foreseen that Commons Compress would be made to depend on another Commons component.</p>
53   *
54   * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
55   * @see StandardCharsets
56   * @since 1.4
57   */
58  public class Charsets {
59  
60      //
61      // This class should only contain Charset instances for required encodings. This guarantees that it will load correctly and
62      // without delay on all Java platforms.
63      //
64  
65      /**
66       * Returns the given Charset or the default Charset if the given Charset is null.
67       *
68       * @param charset
69       *            A charset or null.
70       * @return the given Charset or the default Charset if the given Charset is null
71       */
72      public static Charset toCharset(final Charset charset) {
73          return charset == null ? Charset.defaultCharset() : charset;
74      }
75  
76      /**
77       * Returns a Charset for the named charset. If the name is null, return the default Charset.
78       *
79       * @param charset
80       *            The name of the requested charset, may be null.
81       * @return a Charset for the named charset
82       * @throws java.nio.charset.UnsupportedCharsetException
83       *             If the named charset is unavailable
84       * @throws java.nio.charset.IllegalCharsetNameException
85       *             If the given charset name is illegal
86       */
87      public static Charset toCharset(final String charset) {
88          return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
89      }
90  
91      /**
92       * CharsetNamesISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.
93       * <p>
94       * Every implementation of the Java platform is required to support this character encoding.
95       * </p>
96       *
97       * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
98       * @deprecated replaced by {@link StandardCharsets} in Java 7
99       */
100     public static final Charset ISO_8859_1 = StandardCharsets.ISO_8859_1;
101 
102     /**
103      * <p>
104      * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
105      * </p>
106      * <p>
107      * Every implementation of the Java platform is required to support this character encoding.
108      * </p>
109      *
110      * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
111      * @deprecated replaced by {@link StandardCharsets} in Java 7
112      */
113     public static final Charset US_ASCII = StandardCharsets.US_ASCII;
114 
115     /**
116      * <p>
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      * <p>
121      * Every implementation of the Java platform is required to support this character encoding.
122      * </p>
123      *
124      * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
125      * @deprecated replaced by {@link StandardCharsets} in Java 7
126      */
127     public static final Charset UTF_16 = StandardCharsets.UTF_16;
128 
129     /**
130      * <p>
131      * Sixteen-bit Unicode Transformation Format, big-endian byte order.
132      * </p>
133      * <p>
134      * Every implementation of the Java platform is required to support this character encoding.
135      * </p>
136      *
137      * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
138      * @deprecated replaced by {@link StandardCharsets} in Java 7
139      */
140     public static final Charset UTF_16BE = StandardCharsets.UTF_16BE;
141 
142     /**
143      * <p>
144      * Sixteen-bit Unicode Transformation Format, little-endian byte order.
145      * </p>
146      * <p>
147      * Every implementation of the Java platform is required to support this character encoding.
148      * </p>
149      *
150      * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
151      * @deprecated replaced by {@link StandardCharsets} in Java 7
152      */
153     public static final Charset UTF_16LE = StandardCharsets.UTF_16LE;
154 
155     /**
156      * <p>
157      * Eight-bit Unicode Transformation Format.
158      * </p>
159      * <p>
160      * Every implementation of the Java platform is required to support this character encoding.
161      * </p>
162      *
163      * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
164      * @deprecated replaced by {@link StandardCharsets} in Java 7
165      */
166     public static final Charset UTF_8 = StandardCharsets.UTF_8;
167 }