1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * https://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.io;
18
19 import java.nio.charset.Charset;
20 import java.nio.charset.StandardCharsets;
21 import java.nio.charset.UnsupportedCharsetException;
22 import java.util.Collections;
23 import java.util.SortedMap;
24 import java.util.TreeMap;
25
26 /**
27 * Charsets required of every implementation of the Java platform.
28 *
29 * From the Java documentation <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">
30 * Standard charsets</a>:
31 * <p>
32 * <cite>Every implementation of the Java platform is required to support the following character encodings. Consult
33 * the release documentation for your implementation to see if any other encodings are supported. Consult the release
34 * documentation for your implementation to see if any other encodings are supported. </cite>
35 * </p>
36 *
37 * <ul>
38 * <li>{@code US-ASCII}<br>
39 * Seven-bit ASCII, a.k.a. ISO646-US, a.k.a. the Basic Latin block of the Unicode character set.</li>
40 * <li>{@code ISO-8859-1}<br>
41 * ISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.</li>
42 * <li>{@code UTF-8}<br>
43 * Eight-bit Unicode Transformation Format.</li>
44 * <li>{@code UTF-16BE}<br>
45 * Sixteen-bit Unicode Transformation Format, big-endian byte order.</li>
46 * <li>{@code UTF-16LE}<br>
47 * Sixteen-bit Unicode Transformation Format, little-endian byte order.</li>
48 * <li>{@code UTF-16}<br>
49 * Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial byte-order mark (either order
50 * accepted on input, big-endian used on output.)</li>
51 * </ul>
52 *
53 * @see <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
54 * @since 2.3
55 */
56 public class Charsets {
57
58 //
59 // This class should only contain Charset instances for required encodings. This guarantees that it will load
60 // correctly and without delay on all Java platforms.
61 //
62
63 private static final SortedMap<String, Charset> STANDARD_CHARSET_MAP;
64
65 static {
66 final SortedMap<String, Charset> standardCharsetMap = new TreeMap<>(String.CASE_INSENSITIVE_ORDER);
67 standardCharsetMap.put(StandardCharsets.ISO_8859_1.name(), StandardCharsets.ISO_8859_1);
68 standardCharsetMap.put(StandardCharsets.US_ASCII.name(), StandardCharsets.US_ASCII);
69 standardCharsetMap.put(StandardCharsets.UTF_16.name(), StandardCharsets.UTF_16);
70 standardCharsetMap.put(StandardCharsets.UTF_16BE.name(), StandardCharsets.UTF_16BE);
71 standardCharsetMap.put(StandardCharsets.UTF_16LE.name(), StandardCharsets.UTF_16LE);
72 standardCharsetMap.put(StandardCharsets.UTF_8.name(), StandardCharsets.UTF_8);
73 STANDARD_CHARSET_MAP = Collections.unmodifiableSortedMap(standardCharsetMap);
74 }
75
76 /**
77 * CharEncodingISO Latin Alphabet No. 1, a.k.a. ISO-LATIN-1.
78 * <p>
79 * Every implementation of the Java platform is required to support this character encoding.
80 * </p>
81 *
82 * @see <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
83 * @deprecated Use Java 7's {@link java.nio.charset.StandardCharsets}
84 */
85 @Deprecated
86 public static final Charset ISO_8859_1 = StandardCharsets.ISO_8859_1;
87
88 /**
89 * <p>
90 * Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block of the Unicode character set.
91 * </p>
92 * <p>
93 * Every implementation of the Java platform is required to support this character encoding.
94 * </p>
95 *
96 * @see <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
97 * @deprecated Use Java 7's {@link java.nio.charset.StandardCharsets}
98 */
99 @Deprecated
100 public static final Charset US_ASCII = StandardCharsets.US_ASCII;
101
102 /**
103 * <p>
104 * Sixteen-bit Unicode Transformation Format, The byte order specified by a mandatory initial byte-order mark
105 * (either order accepted on input, big-endian used on output)
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/8/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
112 * @deprecated Use Java 7's {@link java.nio.charset.StandardCharsets}
113 */
114 @Deprecated
115 public static final Charset UTF_16 = StandardCharsets.UTF_16;
116
117 /**
118 * <p>
119 * Sixteen-bit Unicode Transformation Format, big-endian byte order.
120 * </p>
121 * <p>
122 * Every implementation of the Java platform is required to support this character encoding.
123 * </p>
124 *
125 * @see <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
126 * @deprecated Use Java 7's {@link java.nio.charset.StandardCharsets}
127 */
128 @Deprecated
129 public static final Charset UTF_16BE = StandardCharsets.UTF_16BE;
130
131 /**
132 * <p>
133 * Sixteen-bit Unicode Transformation Format, little-endian byte order.
134 * </p>
135 * <p>
136 * Every implementation of the Java platform is required to support this character encoding.
137 * </p>
138 *
139 * @see <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
140 * @deprecated Use Java 7's {@link java.nio.charset.StandardCharsets}
141 */
142 @Deprecated
143 public static final Charset UTF_16LE = StandardCharsets.UTF_16LE;
144
145 /**
146 * <p>
147 * Eight-bit Unicode Transformation Format.
148 * </p>
149 * <p>
150 * Every implementation of the Java platform is required to support this character encoding.
151 * </p>
152 *
153 * @see <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">Standard charsets</a>
154 * @deprecated Use Java 7's {@link java.nio.charset.StandardCharsets}
155 */
156 @Deprecated
157 public static final Charset UTF_8 = StandardCharsets.UTF_8;
158
159 /**
160 * Tests whether the given non-null Charset has an alias of the given name.
161 *
162 * @param charset a non-null Charset.
163 * @param charsetName The name to test.
164 * @return whether the given non-null charset name is a UTF-8 alias.
165 * @since 2.20.0
166 */
167 public static boolean isAlias(final Charset charset, final String charsetName) {
168 return charsetName != null && (charset.name().equalsIgnoreCase(charsetName) || charset.aliases().stream().anyMatch(charsetName::equalsIgnoreCase));
169 }
170
171 /**
172 * Tests whether a given encoding is UTF-8. If the given charset is null, then check the platform's default encoding.
173 *
174 * @param charset If the given charset is null, then check the platform's default encoding.
175 * @return whether a given encoding is UTF-8.
176 * @since 2.20.0
177 */
178 public static boolean isUTF8(final Charset charset) {
179 return isUTF8Alias(toCharset(charset).name());
180 }
181
182 /**
183 * Tests whether the given non-null charset name is a UTF-8 alias.
184 *
185 * @param charsetName a non-null charset name.
186 * @return whether the given non-null charset name is a UTF-8 alias.
187 */
188 private static boolean isUTF8Alias(final String charsetName) {
189 return isAlias(StandardCharsets.UTF_8, charsetName);
190 }
191
192 /**
193 * Constructs a sorted map from canonical charset names to charset objects required of every implementation of the
194 * Java platform.
195 * <p>
196 * From the Java documentation <a href="https://docs.oracle.com/javase/8/docs/api/java/nio/charset/Charset.html">
197 * Standard charsets</a>:
198 * </p>
199 *
200 * @return An immutable, case-insensitive map from canonical charset names to charset objects.
201 * @see Charset#availableCharsets()
202 * @since 2.5
203 */
204 public static SortedMap<String, Charset> requiredCharsets() {
205 return STANDARD_CHARSET_MAP;
206 }
207
208 /**
209 * Returns the given Charset or the {@link Charset#defaultCharset() default Charset} if the given Charset is null.
210 *
211 * @param charset
212 * A charset or null.
213 * @return the given Charset or the default Charset if the given Charset is null
214 * @see Charset#defaultCharset()
215 */
216 public static Charset toCharset(final Charset charset) {
217 return charset == null ? Charset.defaultCharset() : charset;
218 }
219
220 /**
221 * Returns the given charset if non-null, otherwise return defaultCharset.
222 *
223 * @param charset The charset to test, may be null.
224 * @param defaultCharset The charset to return if charset is null, may be null.
225 * @return a Charset.
226 * @since 2.12.0
227 */
228 public static Charset toCharset(final Charset charset, final Charset defaultCharset) {
229 return charset == null ? defaultCharset : charset;
230 }
231
232 /**
233 * Returns a Charset for the named charset. If the name is null, return the {@link Charset#defaultCharset() default Charset}.
234 *
235 * @param charsetName The name of the requested charset, may be null.
236 * @return a Charset for the named charset.
237 * @throws UnsupportedCharsetException If the named charset is unavailable (unchecked exception).
238 * @see Charset#defaultCharset()
239 */
240 public static Charset toCharset(final String charsetName) throws UnsupportedCharsetException {
241 return toCharset(charsetName, Charset.defaultCharset());
242 }
243
244 /**
245 * Returns a Charset for the named charset. If the name is null, return the given default Charset.
246 *
247 * @param charsetName The name of the requested charset, may be null.
248 * @param defaultCharset The charset to return if charsetName is null, may be null.
249 * @return a Charset for the named charset.
250 * @throws UnsupportedCharsetException If the named charset is unavailable (unchecked exception).
251 * @since 2.12.0
252 */
253 public static Charset toCharset(final String charsetName, final Charset defaultCharset) throws UnsupportedCharsetException {
254 return charsetName == null ? defaultCharset : Charset.forName(charsetName);
255 }
256
257 /**
258 * Returns a Charset for the named charset or the {@code defaultCharset}.
259 * <p>
260 * If {@code charsetName} cannot load a charset, return {@code defaultCharset}. Therefore, this method should never fail and always return a Charset.
261 * </p>
262 *
263 * @param charsetName The name of the requested charset, may be null.
264 * @param defaultCharset The charset to return if charsetName is null or there is a problem, may be null which returns {@link Charset#defaultCharset()}.
265 * @return a Charset for the named charset or {@code defaultCharset} if any errors occur.
266 * @see Charset#defaultCharset()
267 * @since 2.20.0
268 */
269 public static Charset toCharsetDefault(final String charsetName, final Charset defaultCharset) {
270 try {
271 return toCharset(charsetName);
272 } catch (final RuntimeException ignored) {
273 return toCharset(defaultCharset);
274 }
275 }
276
277 /**
278 * Construct a new instance.
279 *
280 * @deprecated Will be private in 4.0
281 */
282 @Deprecated
283 public Charsets() {
284 // empty
285 }
286 }