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 */
017
018package org.apache.commons.compress.utils;
019
020import java.nio.charset.Charset;
021import java.nio.charset.StandardCharsets;
022
023/**
024 * Charsets required of every implementation of the Java platform.
025 *
026 * From the Java documentation <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard
027 * charsets</a>:
028 * <p>
029 * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the
030 * release documentation for your implementation to see if any other encodings are supported. Consult the release
031 * documentation for your implementation to see if any other encodings are supported. </cite>
032 * </p>
033 *
034 * <dl>
035 * <dt>{@code US-ASCII}</dt>
036 * <dd>Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</dd>
037 * <dt>{@code ISO-8859-1}</dt>
038 * <dd>ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</dd>
039 * <dt>{@code UTF-8}</dt>
040 * <dd>Eight-bit Unicode Transformation Format.</dd>
041 * <dt>{@code UTF-16BE}</dt>
042 * <dd>Sixteen-bit Unicode Transformation Format, big-endian byte order.</dd>
043 * <dt>{@code UTF-16LE}</dt>
044 * <dd>Sixteen-bit Unicode Transformation Format, little-endian byte order.</dd>
045 * <dt>{@code UTF-16}</dt>
046 * <dd>Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
047 * accepted on input, big-endian used on output.)</dd>
048 * </dl>
049 *
050 * <p>This class best belongs in the Commons Lang or IO project. Even if a similar class is defined in another Commons
051 * component, it is not foreseen that Commons Compress would be made to depend on another Commons component.</p>
052 *
053 * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
054 * @see StandardCharsets
055 * @since 1.4
056 */
057public class Charsets {
058
059    //
060    // This class should only contain Charset instances for required encodings. This guarantees that it will load correctly and
061    // without delay on all Java platforms.
062    //
063
064    /**
065     * CharsetNamesISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.
066     * <p>
067     * Every implementation of the Java platform is required to support this character encoding.
068     * </p>
069     *
070     * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
071     * @deprecated replaced by {@link StandardCharsets} in Java 7
072     */
073    @Deprecated
074    public static final Charset ISO_8859_1 = StandardCharsets.ISO_8859_1;
075
076    /**
077     * <p>
078     * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
079     * </p>
080     * <p>
081     * Every implementation of the Java platform is required to support this character encoding.
082     * </p>
083     *
084     * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
085     * @deprecated replaced by {@link StandardCharsets} in Java 7
086     */
087    @Deprecated
088    public static final Charset US_ASCII = StandardCharsets.US_ASCII;
089
090    /**
091     * <p>
092     * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
093     * (either order accepted on input, big-endian used on output)
094     * </p>
095     * <p>
096     * Every implementation of the Java platform is required to support this character encoding.
097     * </p>
098     *
099     * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
100     * @deprecated replaced by {@link StandardCharsets} in Java 7
101     */
102    @Deprecated
103    public static final Charset UTF_16 = StandardCharsets.UTF_16;
104
105    /**
106     * <p>
107     * Sixteen-bit Unicode Transformation Format, big-endian byte order.
108     * </p>
109     * <p>
110     * Every implementation of the Java platform is required to support this character encoding.
111     * </p>
112     *
113     * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
114     * @deprecated replaced by {@link StandardCharsets} in Java 7
115     */
116    @Deprecated
117    public static final Charset UTF_16BE = StandardCharsets.UTF_16BE;
118
119    /**
120     * <p>
121     * Sixteen-bit Unicode Transformation Format, little-endian byte order.
122     * </p>
123     * <p>
124     * Every implementation of the Java platform is required to support this character encoding.
125     * </p>
126     *
127     * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
128     * @deprecated replaced by {@link StandardCharsets} in Java 7
129     */
130    @Deprecated
131    public static final Charset UTF_16LE = StandardCharsets.UTF_16LE;
132
133    /**
134     * <p>
135     * Eight-bit Unicode Transformation Format.
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="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
142     * @deprecated replaced by {@link StandardCharsets} in Java 7
143     */
144    @Deprecated
145    public static final Charset UTF_8 = StandardCharsets.UTF_8;
146
147    /**
148     * Returns the given Charset or the default Charset if the given Charset is null.
149     *
150     * @param charset
151     *            A charset or null.
152     * @return the given Charset or the default Charset if the given Charset is null
153     */
154    public static Charset toCharset(final Charset charset) {
155        return charset == null ? Charset.defaultCharset() : charset;
156    }
157
158    /**
159     * Returns a Charset for the named charset. If the name is null, return the default Charset.
160     *
161     * @param charset
162     *            The name of the requested charset, may be null.
163     * @return a Charset for the named charset
164     * @throws java.nio.charset.UnsupportedCharsetException
165     *             If the named charset is unavailable
166     * @throws java.nio.charset.IllegalCharsetNameException
167     *             If the given charset name is illegal
168     */
169    public static Charset toCharset(final String charset) {
170        return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
171    }
172}