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 */ 018 019package org.apache.commons.compress.utils; 020 021import java.nio.charset.Charset; 022import java.nio.charset.StandardCharsets; 023 024/** 025 * Charsets required of every implementation of the Java platform. 026 * 027 * From the Java documentation <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard 028 * charsets</a>: 029 * <p> 030 * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult the 031 * release documentation for your implementation to see if any other encodings are supported. Consult the release 032 * documentation for your implementation to see if any other encodings are supported. </cite> 033 * </p> 034 * 035 * <dl> 036 * <dt><code>US-ASCII</code></dt> 037 * <dd>Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</dd> 038 * <dt><code>ISO-8859-1</code></dt> 039 * <dd>ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</dd> 040 * <dt><code>UTF-8</code></dt> 041 * <dd>Eight-bit Unicode Transformation Format.</dd> 042 * <dt><code>UTF-16BE</code></dt> 043 * <dd>Sixteen-bit Unicode Transformation Format, big-endian byte order.</dd> 044 * <dt><code>UTF-16LE</code></dt> 045 * <dd>Sixteen-bit Unicode Transformation Format, little-endian byte order.</dd> 046 * <dt><code>UTF-16</code></dt> 047 * <dd>Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order 048 * accepted on input, big-endian used on output.)</dd> 049 * </dl> 050 * 051 * <p>This class best belongs in the Commons Lang or IO project. Even if a similar class is defined in another Commons 052 * component, it is not foreseen that Commons Compress would be made to depend on another Commons component.</p> 053 * 054 * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 055 * @see StandardCharsets 056 * @since 1.4 057 */ 058public class Charsets { 059 060 // 061 // This class should only contain Charset instances for required encodings. This guarantees that it will load correctly and 062 // 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 * @throws java.nio.charset.IllegalCharsetNameException 085 * If the given charset name is illegal 086 */ 087 public static Charset toCharset(final String charset) { 088 return charset == null ? Charset.defaultCharset() : Charset.forName(charset); 089 } 090 091 /** 092 * CharsetNamesISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1. 093 * <p> 094 * Every implementation of the Java platform is required to support this character encoding. 095 * </p> 096 * 097 * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 098 * @deprecated replaced by {@link StandardCharsets} in Java 7 099 */ 100 @Deprecated 101 public static final Charset ISO_8859_1 = StandardCharsets.ISO_8859_1; 102 103 /** 104 * <p> 105 * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set. 106 * </p> 107 * <p> 108 * Every implementation of the Java platform is required to support this character encoding. 109 * </p> 110 * 111 * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 112 * @deprecated replaced by {@link StandardCharsets} in Java 7 113 */ 114 @Deprecated 115 public static final Charset US_ASCII = StandardCharsets.US_ASCII; 116 117 /** 118 * <p> 119 * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark 120 * (either order accepted on input, big-endian used on output) 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="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 127 * @deprecated replaced by {@link StandardCharsets} in Java 7 128 */ 129 @Deprecated 130 public static final Charset UTF_16 = StandardCharsets.UTF_16; 131 132 /** 133 * <p> 134 * Sixteen-bit Unicode Transformation Format, big-endian byte order. 135 * </p> 136 * <p> 137 * Every implementation of the Java platform is required to support this character encoding. 138 * </p> 139 * 140 * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 141 * @deprecated replaced by {@link StandardCharsets} in Java 7 142 */ 143 @Deprecated 144 public static final Charset UTF_16BE = StandardCharsets.UTF_16BE; 145 146 /** 147 * <p> 148 * Sixteen-bit Unicode Transformation Format, little-endian byte order. 149 * </p> 150 * <p> 151 * Every implementation of the Java platform is required to support this character encoding. 152 * </p> 153 * 154 * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 155 * @deprecated replaced by {@link StandardCharsets} in Java 7 156 */ 157 @Deprecated 158 public static final Charset UTF_16LE = StandardCharsets.UTF_16LE; 159 160 /** 161 * <p> 162 * Eight-bit Unicode Transformation Format. 163 * </p> 164 * <p> 165 * Every implementation of the Java platform is required to support this character encoding. 166 * </p> 167 * 168 * @see <a href="https://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> 169 * @deprecated replaced by {@link StandardCharsets} in Java 7 170 */ 171 @Deprecated 172 public static final Charset UTF_8 = StandardCharsets.UTF_8; 173}