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 package org.apache.commons.io; 018 019 import java.nio.charset.Charset; 020 import java.nio.charset.UnsupportedCharsetException; 021 022 /** 023 * Charsets required of every implementation of the Java platform. 024 * 025 * From the Java documentation <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html"> 026 * Standard charsets</a>: 027 * <p> 028 * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the 029 * release documentation for your implementation to see if any other encodings are supported. Consult the release 030 * documentation for your implementation to see if any other encodings are supported. </cite> 031 * </p> 032 * 033 * <ul> 034 * <li><code>US-ASCII</code><br/> 035 * Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</li> 036 * <li><code>ISO-8859-1</code><br/> 037 * ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</li> 038 * <li><code>UTF-8</code><br/> 039 * Eight-bit Unicode Transformation Format.</li> 040 * <li><code>UTF-16BE</code><br/> 041 * Sixteen-bit Unicode Transformation Format, big-endian byte order.</li> 042 * <li><code>UTF-16LE</code><br/> 043 * Sixteen-bit Unicode Transformation Format, little-endian byte order.</li> 044 * <li><code>UTF-16</code><br/> 045 * Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order 046 * accepted on input, big-endian used on output.)</li> 047 * </ul> 048 * 049 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 050 * @since 2.3 051 * @version $Id: Charsets.java 1311751 2012-04-10 14:26:21Z ggregory $ 052 */ 053 public class Charsets { 054 // 055 // This class should only contain Charset instances for required encodings. This guarantees that it will load 056 // correctly and without delay on all Java platforms. 057 // 058 059 /** 060 * Returns the given Charset or the default Charset if the given Charset is null. 061 * 062 * @param charset 063 * A charset or null. 064 * @return the given Charset or the default Charset if the given Charset is null 065 */ 066 public static Charset toCharset(Charset charset) { 067 return charset == null ? Charset.defaultCharset() : charset; 068 } 069 070 /** 071 * Returns a Charset for the named charset. If the name is null, return the default Charset. 072 * 073 * @param charset 074 * The name of the requested charset, may be null. 075 * @return a Charset for the named charset 076 * @throws UnsupportedCharsetException 077 * If the named charset is unavailable 078 */ 079 public static Charset toCharset(String charset) { 080 return charset == null ? Charset.defaultCharset() : Charset.forName(charset); 081 } 082 083 /** 084 * CharEncodingISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1. </p> 085 * <p> 086 * Every implementation of the Java platform is required to support this character encoding. 087 * </p> 088 * 089 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 090 */ 091 public static final Charset ISO_8859_1 = Charset.forName("ISO-8859-1"); 092 093 /** 094 * <p> 095 * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set. 096 * </p> 097 * <p> 098 * Every implementation of the Java platform is required to support this character encoding. 099 * </p> 100 * 101 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 102 */ 103 public static final Charset US_ASCII = Charset.forName("US-ASCII"); 104 105 /** 106 * <p> 107 * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark 108 * (either order accepted on input, big-endian used on output) 109 * </p> 110 * <p> 111 * Every implementation of the Java platform is required to support this character encoding. 112 * </p> 113 * 114 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 115 */ 116 public static final Charset UTF_16 = Charset.forName("UTF-16"); 117 118 /** 119 * <p> 120 * Sixteen-bit Unicode Transformation Format, big-endian byte order. 121 * </p> 122 * <p> 123 * Every implementation of the Java platform is required to support this character encoding. 124 * </p> 125 * 126 * @see <a href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 127 */ 128 public static final Charset UTF_16BE = Charset.forName("UTF-16BE"); 129 130 /** 131 * <p> 132 * Sixteen-bit Unicode Transformation Format, little-endian byte order. 133 * </p> 134 * <p> 135 * Every implementation of the Java platform is required to support this character encoding. 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_16LE = Charset.forName("UTF-16LE"); 141 142 /** 143 * <p> 144 * Eight-bit Unicode Transformation Format. 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="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 151 */ 152 public static final Charset UTF_8 = Charset.forName("UTF-8"); 153 }