blob: c07e7b806fa950419b13c986980bd0ce9bd697d3 [file] [log] [blame]
package org.apache.commons.compress.utils;
import java.nio.charset.Charset;
import java.nio.charset.UnsupportedCharsetException;
/**
* Charsets required of every implementation of the Java platform.
*
* From the Java documentation <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard
* charsets</a>:
* <p>
* <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the
* release documentation for your implementation to see if any other encodings are supported. Consult the release
* documentation for your implementation to see if any other encodings are supported. </cite>
* </p>
*
* <ul>
* <li><code>US-ASCII</code><br/>
* Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</li>
* <li><code>ISO-8859-1</code><br/>
* ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</li>
* <li><code>UTF-8</code><br/>
* Eight-bit Unicode Transformation Format.</li>
* <li><code>UTF-16BE</code><br/>
* Sixteen-bit Unicode Transformation Format, big-endian byte order.</li>
* <li><code>UTF-16LE</code><br/>
* Sixteen-bit Unicode Transformation Format, little-endian byte order.</li>
* <li><code>UTF-16</code><br/>
* Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
* accepted on input, big-endian used on output.)</li>
* </ul>
*
* This perhaps would best belong in the Commons Lang project. Even if a similar class is defined in Commons Lang, it is
* not foreseen that Commons Codec would be made to depend on Commons Lang.
*
* @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
* @author Apache Software Foundation
* @since 1.4
* @version $Id$
*/
public class Charsets {
//
// This class should only contain Charset instances for required encodings. This guarantees that it will load correctly and
// without delay on all Java platforms.
//
/**
* Returns the given Charset or the default Charset if the given Charset is null.
*
* @param charset
* A charset or null.
* @return the given Charset or the default Charset if the given Charset is null
*/
public static Charset toCharset(Charset charset) {
return charset == null ? Charset.defaultCharset() : charset;
}
/**
* Returns a Charset for the named charset. If the name is null, return the default Charset.
*
* @param charset
* The name of the requested charset, may be null.
* @return a Charset for the named charset
* @throws UnsupportedCharsetException
* If the named charset is unavailable
*/
public static Charset toCharset(String charset) {
return charset == null ? Charset.defaultCharset() : Charset.forName(charset);
}
/**
* CharsetNamesISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1. </p>
* <p>
* Every implementation of the Java platform is required to support this character encoding.
* </p>
*
* @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
*/
public static final Charset ISO_8859_1 = Charset.forName(CharsetNames.ISO_8859_1);
/**
* <p>
* Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
* </p>
* <p>
* Every implementation of the Java platform is required to support this character encoding.
* </p>
*
* @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
*/
public static final Charset US_ASCII = Charset.forName(CharsetNames.US_ASCII);
/**
* <p>
* Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
* (either order accepted on input, big-endian used on output)
* </p>
* <p>
* Every implementation of the Java platform is required to support this character encoding.
* </p>
*
* @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
*/
public static final Charset UTF_16 = Charset.forName(CharsetNames.UTF_16);
/**
* <p>
* Sixteen-bit Unicode Transformation Format, big-endian byte order.
* </p>
* <p>
* Every implementation of the Java platform is required to support this character encoding.
* </p>
*
* @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
*/
public static final Charset UTF_16BE = Charset.forName(CharsetNames.UTF_16BE);
/**
* <p>
* Sixteen-bit Unicode Transformation Format, little-endian byte order.
* </p>
* <p>
* Every implementation of the Java platform is required to support this character encoding.
* </p>
*
* @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
*/
public static final Charset UTF_16LE = Charset.forName(CharsetNames.UTF_16LE);
/**
* <p>
* Eight-bit Unicode Transformation Format.
* </p>
* <p>
* Every implementation of the Java platform is required to support this character encoding.
* </p>
*
* @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
*/
public static final Charset UTF_8 = Charset.forName(CharsetNames.UTF_8);
}