001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.codec;
018
019import java.nio.charset.Charset;
020
021/**
022 * Charsets required of every implementation of the Java platform.
023 *
024 * From the Java documentation <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard
025 * charsets</a>:
026 * <p>
027 * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the
028 * release documentation for your implementation to see if any other encodings are supported. Consult the release
029 * documentation for your implementation to see if any other encodings are supported. </cite>
030 * </p>
031 *
032 * <ul>
033 * <li><code>US-ASCII</code><p>
034 * Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</p></li>
035 * <li><code>ISO-8859-1</code><p>
036 * ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</p></li>
037 * <li><code>UTF-8</code><p>
038 * Eight-bit Unicode Transformation Format.</p></li>
039 * <li><code>UTF-16BE</code><p>
040 * Sixteen-bit Unicode Transformation Format, big-endian byte order.</p></li>
041 * <li><code>UTF-16LE</code><p>
042 * Sixteen-bit Unicode Transformation Format, little-endian byte order.</p></li>
043 * <li><code>UTF-16</code><p>
044 * Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
045 * accepted on input, big-endian used on output.)</p></li>
046 * </ul>
047 *
048 * This perhaps would best belong in the Commons Lang project. Even if a similar class is defined in Commons Lang, it is
049 * not foreseen that Commons Codec would be made to depend on Commons Lang.
050 *
051 * <p>
052 * This class is immutable and thread-safe.
053 * </p>
054 *
055 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
056 * @since 1.7
057 */
058public class Charsets {
059
060    //
061    // This class should only contain Charset instances for required encodings. This guarantees that it will load
062    // correctly and without delay on all Java platforms.
063    //
064
065    /**
066     * Returns the given Charset or the default Charset if the given Charset is null.
067     *
068     * @param charset
069     *            A charset or null.
070     * @return the given Charset or the default Charset if the given Charset is null
071     */
072    public static Charset toCharset(final Charset charset) {
073        return charset == null ? Charset.defaultCharset() : charset;
074    }
075
076    /**
077     * Returns a Charset for the named charset. If the name is null, return the default Charset.
078     *
079     * @param charset
080     *            The name of the requested charset, may be null.
081     * @return a Charset for the named charset
082     * @throws java.nio.charset.UnsupportedCharsetException
083     *             If the named charset is unavailable
084     */
085    public static Charset toCharset(final String charset) {
086        return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
087    }
088
089    /**
090     * CharEncodingISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.
091     * <p>
092     * Every implementation of the Java platform is required to support this character encoding.
093     * </p>
094     * <p>
095     * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
096     * </p>
097     *
098     * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
099     */
100    public static final Charset ISO_8859_1 = Charset.forName(CharEncoding.ISO_8859_1);
101
102    /**
103     * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
104     * <p>
105     * Every implementation of the Java platform is required to support this character encoding.
106     * </p>
107     * <p>
108     * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
109     * </p>
110     *
111     * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
112     */
113    public static final Charset US_ASCII = Charset.forName(CharEncoding.US_ASCII);
114
115    /**
116     * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
117     * (either order accepted on input, big-endian used on output)
118     * <p>
119     * Every implementation of the Java platform is required to support this character encoding.
120     * </p>
121     * <p>
122     * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
123     * </p>
124     *
125     * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
126     */
127    public static final Charset UTF_16 = Charset.forName(CharEncoding.UTF_16);
128
129    /**
130     * Sixteen-bit Unicode Transformation Format, big-endian byte order.
131     * <p>
132     * Every implementation of the Java platform is required to support this character encoding.
133     * </p>
134     * <p>
135     * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
136     * </p>
137     *
138     * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
139     */
140    public static final Charset UTF_16BE = Charset.forName(CharEncoding.UTF_16BE);
141
142    /**
143     * Sixteen-bit Unicode Transformation Format, little-endian byte order.
144     * <p>
145     * Every implementation of the Java platform is required to support this character encoding.
146     * </p>
147     * <p>
148     * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
149     * </p>
150     *
151     * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
152     */
153    public static final Charset UTF_16LE = Charset.forName(CharEncoding.UTF_16LE);
154
155    /**
156     * Eight-bit Unicode Transformation Format.
157     * <p>
158     * Every implementation of the Java platform is required to support this character encoding.
159     * </p>
160     * <p>
161     * On Java 7 or later, use {@link java.nio.charset.StandardCharsets#ISO_8859_1} instead.
162     * </p>
163     *
164     * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
165     */
166    public static final Charset UTF_8 = Charset.forName(CharEncoding.UTF_8);
167}