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  package org.apache.commons.io;
18  
19  import java.nio.charset.Charset;
20  import java.nio.charset.UnsupportedCharsetException;
21  import java.util.Collections;
22  import java.util.SortedMap;
23  import java.util.TreeMap;
24  
25  /**
26   * Charsets required of every implementation of the Java platform.
27   * 
28   * From the Java documentation <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">
29   * Standard charsets</a>:
30   * <p>
31   * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult
32   * the release documentation for your implementation to see if any other encodings are supported. Consult the release
33   * documentation for your implementation to see if any other encodings are supported. </cite>
34   * </p>
35   * 
36   * <ul>
37   * <li><code>US-ASCII</code><br/>
38   * Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</li>
39   * <li><code>ISO-8859-1</code><br/>
40   * ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</li>
41   * <li><code>UTF-8</code><br/>
42   * Eight-bit Unicode Transformation Format.</li>
43   * <li><code>UTF-16BE</code><br/>
44   * Sixteen-bit Unicode Transformation Format, big-endian byte order.</li>
45   * <li><code>UTF-16LE</code><br/>
46   * Sixteen-bit Unicode Transformation Format, little-endian byte order.</li>
47   * <li><code>UTF-16</code><br/>
48   * Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
49   * accepted on input, big-endian used on output.)</li>
50   * </ul>
51   * 
52   * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
53   * @since 2.3
54   * @version $Id: Charsets.java 1415850 2012-11-30 20:51:39Z ggregory $
55   */
56  public class Charsets {
57      //
58      // This class should only contain Charset instances for required encodings. This guarantees that it will load
59      // correctly and without delay on all Java platforms.
60      //
61  
62      /**
63       * Constructs a sorted map from canonical charset names to charset objects required of every implementation of the
64       * Java platform.
65       * <p>
66       * From the Java documentation <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">
67       * Standard charsets</a>:
68       * </p>
69       * 
70       * @return An immutable, case-insensitive map from canonical charset names to charset objects.
71       * @see Charset#availableCharsets()
72       * @since 2.5
73       */
74      public static SortedMap<String, Charset> requiredCharsets() {
75          // maybe cache?
76          final TreeMap<String, Charset> m = new TreeMap<String, Charset>(String.CASE_INSENSITIVE_ORDER);
77          m.put(ISO_8859_1.name(), ISO_8859_1);
78          m.put(US_ASCII.name(), US_ASCII);
79          m.put(UTF_16.name(), UTF_16);
80          m.put(UTF_16BE.name(), UTF_16BE);
81          m.put(UTF_16LE.name(), UTF_16LE);
82          m.put(UTF_8.name(), UTF_8);
83          return Collections.unmodifiableSortedMap(m);
84      }
85  
86      /**
87       * Returns the given Charset or the default Charset if the given Charset is null.
88       * 
89       * @param charset
90       *            A charset or null.
91       * @return the given Charset or the default Charset if the given Charset is null
92       */
93      public static Charset toCharset(final Charset charset) {
94          return charset == null ? Charset.defaultCharset() : charset;
95      }
96  
97      /**
98       * Returns a Charset for the named charset. If the name is null, return the default Charset.
99       * 
100      * @param charset
101      *            The name of the requested charset, may be null.
102      * @return a Charset for the named charset
103      * @throws UnsupportedCharsetException
104      *             If the named charset is unavailable
105      */
106     public static Charset toCharset(final String charset) {
107         return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
108     }
109 
110     /**
111      * CharEncodingISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1. </p>
112      * <p>
113      * Every implementation of the Java platform is required to support this character encoding.
114      * </p>
115      * 
116      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
117      */
118     public static final Charset ISO_8859_1 = Charset.forName("ISO-8859-1");
119 
120     /**
121      * <p>
122      * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
123      * </p>
124      * <p>
125      * Every implementation of the Java platform is required to support this character encoding.
126      * </p>
127      * 
128      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
129      */
130     public static final Charset US_ASCII = Charset.forName("US-ASCII");
131 
132     /**
133      * <p>
134      * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
135      * (either order accepted on input, big-endian used on output)
136      * </p>
137      * <p>
138      * Every implementation of the Java platform is required to support this character encoding.
139      * </p>
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_16 = Charset.forName("UTF-16");
144 
145     /**
146      * <p>
147      * Sixteen-bit Unicode Transformation Format, big-endian byte order.
148      * </p>
149      * <p>
150      * Every implementation of the Java platform is required to support this character encoding.
151      * </p>
152      * 
153      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
154      */
155     public static final Charset UTF_16BE = Charset.forName("UTF-16BE");
156 
157     /**
158      * <p>
159      * Sixteen-bit Unicode Transformation Format, little-endian byte order.
160      * </p>
161      * <p>
162      * Every implementation of the Java platform is required to support this character encoding.
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_16LE = Charset.forName("UTF-16LE");
168 
169     /**
170      * <p>
171      * Eight-bit Unicode Transformation Format.
172      * </p>
173      * <p>
174      * Every implementation of the Java platform is required to support this character encoding.
175      * </p>
176      * 
177      * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
178      */
179     public static final Charset UTF_8 = Charset.forName("UTF-8");
180 }