1 /*
2 * Copyright (c) 2000, 2017, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.nio.charset;
27
28 import jdk.internal.misc.VM;
29 import sun.nio.cs.StandardCharsets;
30 import sun.nio.cs.ThreadLocalCoders;
31 import sun.security.action.GetPropertyAction;
32
33 import java.nio.ByteBuffer;
34 import java.nio.CharBuffer;
35 import java.nio.charset.spi.CharsetProvider;
36 import java.security.AccessController;
37 import java.security.PrivilegedAction;
38 import java.util.Arrays;
39 import java.util.Collections;
40 import java.util.HashSet;
41 import java.util.Iterator;
42 import java.util.Locale;
43 import java.util.Map;
44 import java.util.NoSuchElementException;
45 import java.util.Objects;
46 import java.util.ServiceConfigurationError;
47 import java.util.ServiceLoader;
48 import java.util.Set;
49 import java.util.SortedMap;
50 import java.util.TreeMap;
51
52
53 /**
54 * A named mapping between sequences of sixteen-bit Unicode <a
55 * href="../../lang/Character.html#unicode">code units</a> and sequences of
56 * bytes. This class defines methods for creating decoders and encoders and
57 * for retrieving the various names associated with a charset. Instances of
58 * this class are immutable.
59 *
60 * <p> This class also defines static methods for testing whether a particular
61 * charset is supported, for locating charset instances by name, and for
62 * constructing a map that contains every charset for which support is
63 * available in the current Java virtual machine. Support for new charsets can
64 * be added via the service-provider interface defined in the {@link
65 * java.nio.charset.spi.CharsetProvider} class.
66 *
67 * <p> All of the methods defined in this class are safe for use by multiple
68 * concurrent threads.
69 *
70 *
71 * <a id="names"></a><a id="charenc"></a>
72 * <h2>Charset names</h2>
73 *
74 * <p> Charsets are named by strings composed of the following characters:
75 *
76 * <ul>
77 *
78 * <li> The uppercase letters {@code 'A'} through {@code 'Z'}
79 * (<code>'\u0041'</code> through <code>'\u005a'</code>),
80 *
81 * <li> The lowercase letters {@code 'a'} through {@code 'z'}
82 * (<code>'\u0061'</code> through <code>'\u007a'</code>),
83 *
84 * <li> The digits {@code '0'} through {@code '9'}
85 * (<code>'\u0030'</code> through <code>'\u0039'</code>),
86 *
87 * <li> The dash character {@code '-'}
88 * (<code>'\u002d'</code>, <small>HYPHEN-MINUS</small>),
89 *
90 * <li> The plus character {@code '+'}
91 * (<code>'\u002b'</code>, <small>PLUS SIGN</small>),
92 *
93 * <li> The period character {@code '.'}
94 * (<code>'\u002e'</code>, <small>FULL STOP</small>),
95 *
96 * <li> The colon character {@code ':'}
97 * (<code>'\u003a'</code>, <small>COLON</small>), and
98 *
99 * <li> The underscore character {@code '_'}
100 * (<code>'\u005f'</code>, <small>LOW LINE</small>).
101 *
102 * </ul>
103 *
104 * A charset name must begin with either a letter or a digit. The empty string
105 * is not a legal charset name. Charset names are not case-sensitive; that is,
106 * case is always ignored when comparing charset names. Charset names
107 * generally follow the conventions documented in <a
108 * href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC 2278: IANA Charset
109 * Registration Procedures</i></a>.
110 *
111 * <p> Every charset has a <i>canonical name</i> and may also have one or more
112 * <i>aliases</i>. The canonical name is returned by the {@link #name() name} method
113 * of this class. Canonical names are, by convention, usually in upper case.
114 * The aliases of a charset are returned by the {@link #aliases() aliases}
115 * method.
116 *
117 * <p><a id="hn">Some charsets have an <i>historical name</i> that is defined for
118 * compatibility with previous versions of the Java platform.</a> A charset's
119 * historical name is either its canonical name or one of its aliases. The
120 * historical name is returned by the {@code getEncoding()} methods of the
121 * {@link java.io.InputStreamReader#getEncoding InputStreamReader} and {@link
122 * java.io.OutputStreamWriter#getEncoding OutputStreamWriter} classes.
123 *
124 * <p><a id="iana"> </a>If a charset listed in the <a
125 * href="http://www.iana.org/assignments/character-sets"><i>IANA Charset
126 * Registry</i></a> is supported by an implementation of the Java platform then
127 * its canonical name must be the name listed in the registry. Many charsets
128 * are given more than one name in the registry, in which case the registry
129 * identifies one of the names as <i>MIME-preferred</i>. If a charset has more
130 * than one registry name then its canonical name must be the MIME-preferred
131 * name and the other names in the registry must be valid aliases. If a
132 * supported charset is not listed in the IANA registry then its canonical name
133 * must begin with one of the strings {@code "X-"} or {@code "x-"}.
134 *
135 * <p> The IANA charset registry does change over time, and so the canonical
136 * name and the aliases of a particular charset may also change over time. To
137 * ensure compatibility it is recommended that no alias ever be removed from a
138 * charset, and that if the canonical name of a charset is changed then its
139 * previous canonical name be made into an alias.
140 *
141 *
142 * <h2>Standard charsets</h2>
143 *
144 *
145 *
146 * <p><a id="standard">Every implementation of the Java platform is required to support the
147 * following standard charsets.</a> Consult the release documentation for your
148 * implementation to see if any other charsets are supported. The behavior
149 * of such optional charsets may differ between implementations.
150 *
151 * <blockquote><table class="striped" style="width:80%">
152 * <caption style="display:none">Description of standard charsets</caption>
153 * <thead>
154 * <tr><th scope="col" style="text-align:left">Charset</th><th scope="col" style="text-align:left">Description</th></tr>
155 * </thead>
156 * <tbody>
157 * <tr><th scope="row" style="vertical-align:top">{@code US-ASCII}</th>
158 * <td>Seven-bit ASCII, a.k.a. {@code ISO646-US},
159 * a.k.a. the Basic Latin block of the Unicode character set</td></tr>
160 * <tr><th scope="row" style="vertical-align:top"><code>ISO-8859-1 </code></th>
161 * <td>ISO Latin Alphabet No. 1, a.k.a. {@code ISO-LATIN-1}</td></tr>
162 * <tr><th scope="row" style="vertical-align:top">{@code UTF-8}</th>
163 * <td>Eight-bit UCS Transformation Format</td></tr>
164 * <tr><th scope="row" style="vertical-align:top">{@code UTF-16BE}</th>
165 * <td>Sixteen-bit UCS Transformation Format,
166 * big-endian byte order</td></tr>
167 * <tr><th scope="row" style="vertical-align:top">{@code UTF-16LE}</th>
168 * <td>Sixteen-bit UCS Transformation Format,
169 * little-endian byte order</td></tr>
170 * <tr><th scope="row" style="vertical-align:top">{@code UTF-16}</th>
171 * <td>Sixteen-bit UCS Transformation Format,
172 * byte order identified by an optional byte-order mark</td></tr>
173 * </tbody>
174 * </table></blockquote>
175 *
176 * <p> The {@code UTF-8} charset is specified by <a
177 * href="http://www.ietf.org/rfc/rfc2279.txt"><i>RFC 2279</i></a>; the
178 * transformation format upon which it is based is specified in
179 * Amendment 2 of ISO 10646-1 and is also described in the <a
180 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode
181 * Standard</i></a>.
182 *
183 * <p> The {@code UTF-16} charsets are specified by <a
184 * href="http://www.ietf.org/rfc/rfc2781.txt"><i>RFC 2781</i></a>; the
185 * transformation formats upon which they are based are specified in
186 * Amendment 1 of ISO 10646-1 and are also described in the <a
187 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode
188 * Standard</i></a>.
189 *
190 * <p> The {@code UTF-16} charsets use sixteen-bit quantities and are
191 * therefore sensitive to byte order. In these encodings the byte order of a
192 * stream may be indicated by an initial <i>byte-order mark</i> represented by
193 * the Unicode character <code>'\uFEFF'</code>. Byte-order marks are handled
194 * as follows:
195 *
196 * <ul>
197 *
198 * <li><p> When decoding, the {@code UTF-16BE} and {@code UTF-16LE}
199 * charsets interpret the initial byte-order marks as a <small>ZERO-WIDTH
200 * NON-BREAKING SPACE</small>; when encoding, they do not write
201 * byte-order marks. </p></li>
202
203 *
204 * <li><p> When decoding, the {@code UTF-16} charset interprets the
205 * byte-order mark at the beginning of the input stream to indicate the
206 * byte-order of the stream but defaults to big-endian if there is no
207 * byte-order mark; when encoding, it uses big-endian byte order and writes
208 * a big-endian byte-order mark. </p></li>
209 *
210 * </ul>
211 *
212 * In any case, byte order marks occurring after the first element of an
213 * input sequence are not omitted since the same code is used to represent
214 * <small>ZERO-WIDTH NON-BREAKING SPACE</small>.
215 *
216 * <p> Every instance of the Java virtual machine has a default charset, which
217 * may or may not be one of the standard charsets. The default charset is
218 * determined during virtual-machine startup and typically depends upon the
219 * locale and charset being used by the underlying operating system. </p>
220 *
221 * <p>The {@link StandardCharsets} class defines constants for each of the
222 * standard charsets.
223 *
224 * <h2>Terminology</h2>
225 *
226 * <p> The name of this class is taken from the terms used in
227 * <a href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC 2278</i></a>.
228 * In that document a <i>charset</i> is defined as the combination of
229 * one or more coded character sets and a character-encoding scheme.
230 * (This definition is confusing; some other software systems define
231 * <i>charset</i> as a synonym for <i>coded character set</i>.)
232 *
233 * <p> A <i>coded character set</i> is a mapping between a set of abstract
234 * characters and a set of integers. US-ASCII, ISO 8859-1,
235 * JIS X 0201, and Unicode are examples of coded character sets.
236 *
237 * <p> Some standards have defined a <i>character set</i> to be simply a
238 * set of abstract characters without an associated assigned numbering.
239 * An alphabet is an example of such a character set. However, the subtle
240 * distinction between <i>character set</i> and <i>coded character set</i>
241 * is rarely used in practice; the former has become a short form for the
242 * latter, including in the Java API specification.
243 *
244 * <p> A <i>character-encoding scheme</i> is a mapping between one or more
245 * coded character sets and a set of octet (eight-bit byte) sequences.
246 * UTF-8, UTF-16, ISO 2022, and EUC are examples of
247 * character-encoding schemes. Encoding schemes are often associated with
248 * a particular coded character set; UTF-8, for example, is used only to
249 * encode Unicode. Some schemes, however, are associated with multiple
250 * coded character sets; EUC, for example, can be used to encode
251 * characters in a variety of Asian coded character sets.
252 *
253 * <p> When a coded character set is used exclusively with a single
254 * character-encoding scheme then the corresponding charset is usually
255 * named for the coded character set; otherwise a charset is usually named
256 * for the encoding scheme and, possibly, the locale of the coded
257 * character sets that it supports. Hence {@code US-ASCII} is both the
258 * name of a coded character set and of the charset that encodes it, while
259 * {@code EUC-JP} is the name of the charset that encodes the
260 * JIS X 0201, JIS X 0208, and JIS X 0212
261 * coded character sets for the Japanese language.
262 *
263 * <p> The native character encoding of the Java programming language is
264 * UTF-16. A charset in the Java platform therefore defines a mapping
265 * between sequences of sixteen-bit UTF-16 code units (that is, sequences
266 * of chars) and sequences of bytes. </p>
267 *
268 *
269 * @author Mark Reinhold
270 * @author JSR-51 Expert Group
271 * @since 1.4
272 *
273 * @see CharsetDecoder
274 * @see CharsetEncoder
275 * @see java.nio.charset.spi.CharsetProvider
276 * @see java.lang.Character
277 */
278
279 public abstract class Charset
280 implements Comparable<Charset>
281 {
282
283 /* -- Static methods -- */
284
285 /**
286 * Checks that the given string is a legal charset name. </p>
287 *
288 * @param s
289 * A purported charset name
290 *
291 * @throws IllegalCharsetNameException
292 * If the given name is not a legal charset name
293 */
294 private static void checkName(String s) {
295 int n = s.length();
296 if (n == 0) {
297 throw new IllegalCharsetNameException(s);
298 }
299 for (int i = 0; i < n; i++) {
300 char c = s.charAt(i);
301 if (c >= 'A' && c <= 'Z') continue;
302 if (c >= 'a' && c <= 'z') continue;
303 if (c >= '0' && c <= '9') continue;
304 if (c == '-' && i != 0) continue;
305 if (c == '+' && i != 0) continue;
306 if (c == ':' && i != 0) continue;
307 if (c == '_' && i != 0) continue;
308 if (c == '.' && i != 0) continue;
309 throw new IllegalCharsetNameException(s);
310 }
311 }
312
313 /* The standard set of charsets */
314 private static final CharsetProvider standardProvider = new StandardCharsets();
315
316 private static final String[] zeroAliases = new String[0];
317
318 // Cache of the most-recently-returned charsets,
319 // along with the names that were used to find them
320 //
321 private static volatile Object[] cache1; // "Level 1" cache
322 private static volatile Object[] cache2; // "Level 2" cache
323
324 private static void cache(String charsetName, Charset cs) {
325 cache2 = cache1;
326 cache1 = new Object[] { charsetName, cs };
327 }
328
329 // Creates an iterator that walks over the available providers, ignoring
330 // those whose lookup or instantiation causes a security exception to be
331 // thrown. Should be invoked with full privileges.
332 //
333 private static Iterator<CharsetProvider> providers() {
334 return new Iterator<>() {
335 ClassLoader cl = ClassLoader.getSystemClassLoader();
336 ServiceLoader<CharsetProvider> sl =
337 ServiceLoader.load(CharsetProvider.class, cl);
338 Iterator<CharsetProvider> i = sl.iterator();
339 CharsetProvider next = null;
340
341 private boolean getNext() {
342 while (next == null) {
343 try {
344 if (!i.hasNext())
345 return false;
346 next = i.next();
347 } catch (ServiceConfigurationError sce) {
348 if (sce.getCause() instanceof SecurityException) {
349 // Ignore security exceptions
350 continue;
351 }
352 throw sce;
353 }
354 }
355 return true;
356 }
357
358 public boolean hasNext() {
359 return getNext();
360 }
361
362 public CharsetProvider next() {
363 if (!getNext())
364 throw new NoSuchElementException();
365 CharsetProvider n = next;
366 next = null;
367 return n;
368 }
369
370 public void remove() {
371 throw new UnsupportedOperationException();
372 }
373
374 };
375 }
376
377 // Thread-local gate to prevent recursive provider lookups
378 private static ThreadLocal<ThreadLocal<?>> gate =
379 new ThreadLocal<ThreadLocal<?>>();
380
381 private static Charset lookupViaProviders(final String charsetName) {
382
383 // The runtime startup sequence looks up standard charsets as a
384 // consequence of the VM's invocation of System.initializeSystemClass
385 // in order to, e.g., set system properties and encode filenames. At
386 // that point the application class loader has not been initialized,
387 // however, so we can't look for providers because doing so will cause
388 // that loader to be prematurely initialized with incomplete
389 // information.
390 //
391 if (!VM.isBooted())
392 return null;
393
394 if (gate.get() != null)
395 // Avoid recursive provider lookups
396 return null;
397 try {
398 gate.set(gate);
399
400 return AccessController.doPrivileged(
401 new PrivilegedAction<>() {
402 public Charset run() {
403 for (Iterator<CharsetProvider> i = providers();
404 i.hasNext();) {
405 CharsetProvider cp = i.next();
406 Charset cs = cp.charsetForName(charsetName);
407 if (cs != null)
408 return cs;
409 }
410 return null;
411 }
412 });
413
414 } finally {
415 gate.set(null);
416 }
417 }
418
419 /* The extended set of charsets */
420 private static class ExtendedProviderHolder {
421 static final CharsetProvider[] extendedProviders = extendedProviders();
422 // returns ExtendedProvider, if installed
423 private static CharsetProvider[] extendedProviders() {
424 return AccessController.doPrivileged(new PrivilegedAction<>() {
425 public CharsetProvider[] run() {
426 CharsetProvider[] cps = new CharsetProvider[1];
427 int n = 0;
428 ServiceLoader<CharsetProvider> sl =
429 ServiceLoader.loadInstalled(CharsetProvider.class);
430 for (CharsetProvider cp : sl) {
431 if (n + 1 > cps.length) {
432 cps = Arrays.copyOf(cps, cps.length << 1);
433 }
434 cps[n++] = cp;
435 }
436 return n == cps.length ? cps : Arrays.copyOf(cps, n);
437 }});
438 }
439 }
440
441 private static Charset lookupExtendedCharset(String charsetName) {
442 if (!VM.isBooted()) // see lookupViaProviders()
443 return null;
444 CharsetProvider[] ecps = ExtendedProviderHolder.extendedProviders;
445 for (CharsetProvider cp : ecps) {
446 Charset cs = cp.charsetForName(charsetName);
447 if (cs != null)
448 return cs;
449 }
450 return null;
451 }
452
453 private static Charset lookup(String charsetName) {
454 if (charsetName == null)
455 throw new IllegalArgumentException("Null charset name");
456 Object[] a;
457 if ((a = cache1) != null && charsetName.equals(a[0]))
458 return (Charset)a[1];
459 // We expect most programs to use one Charset repeatedly.
460 // We convey a hint to this effect to the VM by putting the
461 // level 1 cache miss code in a separate method.
462 return lookup2(charsetName);
463 }
464
465 private static Charset lookup2(String charsetName) {
466 Object[] a;
467 if ((a = cache2) != null && charsetName.equals(a[0])) {
468 cache2 = cache1;
469 cache1 = a;
470 return (Charset)a[1];
471 }
472 Charset cs;
473 if ((cs = standardProvider.charsetForName(charsetName)) != null ||
474 (cs = lookupExtendedCharset(charsetName)) != null ||
475 (cs = lookupViaProviders(charsetName)) != null)
476 {
477 cache(charsetName, cs);
478 return cs;
479 }
480
481 /* Only need to check the name if we didn't find a charset for it */
482 checkName(charsetName);
483 return null;
484 }
485
486 /**
487 * Tells whether the named charset is supported.
488 *
489 * @param charsetName
490 * The name of the requested charset; may be either
491 * a canonical name or an alias
492 *
493 * @return {@code true} if, and only if, support for the named charset
494 * is available in the current Java virtual machine
495 *
496 * @throws IllegalCharsetNameException
497 * If the given charset name is illegal
498 *
499 * @throws IllegalArgumentException
500 * If the given {@code charsetName} is null
501 */
502 public static boolean isSupported(String charsetName) {
503 return (lookup(charsetName) != null);
504 }
505
506 /**
507 * Returns a charset object for the named charset.
508 *
509 * @param charsetName
510 * The name of the requested charset; may be either
511 * a canonical name or an alias
512 *
513 * @return A charset object for the named charset
514 *
515 * @throws IllegalCharsetNameException
516 * If the given charset name is illegal
517 *
518 * @throws IllegalArgumentException
519 * If the given {@code charsetName} is null
520 *
521 * @throws UnsupportedCharsetException
522 * If no support for the named charset is available
523 * in this instance of the Java virtual machine
524 */
525 public static Charset forName(String charsetName) {
526 Charset cs = lookup(charsetName);
527 if (cs != null)
528 return cs;
529 throw new UnsupportedCharsetException(charsetName);
530 }
531
532 // Fold charsets from the given iterator into the given map, ignoring
533 // charsets whose names already have entries in the map.
534 //
535 private static void put(Iterator<Charset> i, Map<String,Charset> m) {
536 while (i.hasNext()) {
537 Charset cs = i.next();
538 if (!m.containsKey(cs.name()))
539 m.put(cs.name(), cs);
540 }
541 }
542
543 /**
544 * Constructs a sorted map from canonical charset names to charset objects.
545 *
546 * <p> The map returned by this method will have one entry for each charset
547 * for which support is available in the current Java virtual machine. If
548 * two or more supported charsets have the same canonical name then the
549 * resulting map will contain just one of them; which one it will contain
550 * is not specified. </p>
551 *
552 * <p> The invocation of this method, and the subsequent use of the
553 * resulting map, may cause time-consuming disk or network I/O operations
554 * to occur. This method is provided for applications that need to
555 * enumerate all of the available charsets, for example to allow user
556 * charset selection. This method is not used by the {@link #forName
557 * forName} method, which instead employs an efficient incremental lookup
558 * algorithm.
559 *
560 * <p> This method may return different results at different times if new
561 * charset providers are dynamically made available to the current Java
562 * virtual machine. In the absence of such changes, the charsets returned
563 * by this method are exactly those that can be retrieved via the {@link
564 * #forName forName} method. </p>
565 *
566 * @return An immutable, case-insensitive map from canonical charset names
567 * to charset objects
568 */
569 public static SortedMap<String,Charset> availableCharsets() {
570 return AccessController.doPrivileged(
571 new PrivilegedAction<>() {
572 public SortedMap<String,Charset> run() {
573 TreeMap<String,Charset> m =
574 new TreeMap<>(
575 String.CASE_INSENSITIVE_ORDER);
576 put(standardProvider.charsets(), m);
577 CharsetProvider[] ecps = ExtendedProviderHolder.extendedProviders;
578 for (CharsetProvider ecp :ecps) {
579 put(ecp.charsets(), m);
580 }
581 for (Iterator<CharsetProvider> i = providers(); i.hasNext();) {
582 CharsetProvider cp = i.next();
583 put(cp.charsets(), m);
584 }
585 return Collections.unmodifiableSortedMap(m);
586 }
587 });
588 }
589
590 private static volatile Charset defaultCharset;
591
592 /**
593 * Returns the default charset of this Java virtual machine.
594 *
595 * <p> The default charset is determined during virtual-machine startup and
596 * typically depends upon the locale and charset of the underlying
597 * operating system.
598 *
599 * @return A charset object for the default charset
600 *
601 * @since 1.5
602 */
603 public static Charset defaultCharset() {
604 if (defaultCharset == null) {
605 synchronized (Charset.class) {
606 String csn = GetPropertyAction
607 .privilegedGetProperty("file.encoding");
608 Charset cs = lookup(csn);
609 if (cs != null)
610 defaultCharset = cs;
611 else
612 defaultCharset = forName("UTF-8");
613 }
614 }
615 return defaultCharset;
616 }
617
618
619 /* -- Instance fields and methods -- */
620
621 private final String name; // tickles a bug in oldjavac
622 private final String[] aliases; // tickles a bug in oldjavac
623 private Set<String> aliasSet = null;
624
625 /**
626 * Initializes a new charset with the given canonical name and alias
627 * set.
628 *
629 * @param canonicalName
630 * The canonical name of this charset
631 *
632 * @param aliases
633 * An array of this charset's aliases, or null if it has no aliases
634 *
635 * @throws IllegalCharsetNameException
636 * If the canonical name or any of the aliases are illegal
637 */
638 protected Charset(String canonicalName, String[] aliases) {
639 String[] as = Objects.requireNonNullElse(aliases, zeroAliases);
640
641 // Skip checks for the standard, built-in Charsets we always load
642 // during initialization. Use of identity is intentional to be
643 // consistent with sun.nio.cs.StandardCharsets
644 if (canonicalName != StandardCharsets.ISO_8859_1
645 && canonicalName != StandardCharsets.US_ASCII
646 && canonicalName != StandardCharsets.UTF_8) {
647 checkName(canonicalName);
648 for (int i = 0; i < as.length; i++) {
649 checkName(as[i]);
650 }
651 }
652 this.name = canonicalName;
653 this.aliases = as;
654 }
655
656 /**
657 * Returns this charset's canonical name.
658 *
659 * @return The canonical name of this charset
660 */
661 public final String name() {
662 return name;
663 }
664
665 /**
666 * Returns a set containing this charset's aliases.
667 *
668 * @return An immutable set of this charset's aliases
669 */
670 public final Set<String> aliases() {
671 if (aliasSet != null)
672 return aliasSet;
673 int n = aliases.length;
674 HashSet<String> hs = new HashSet<>(n);
675 for (int i = 0; i < n; i++)
676 hs.add(aliases[i]);
677 aliasSet = Collections.unmodifiableSet(hs);
678 return aliasSet;
679 }
680
681 /**
682 * Returns this charset's human-readable name for the default locale.
683 *
684 * <p> The default implementation of this method simply returns this
685 * charset's canonical name. Concrete subclasses of this class may
686 * override this method in order to provide a localized display name. </p>
687 *
688 * @return The display name of this charset in the default locale
689 */
690 public String displayName() {
691 return name;
692 }
693
694 /**
695 * Tells whether or not this charset is registered in the <a
696 * href="http://www.iana.org/assignments/character-sets">IANA Charset
697 * Registry</a>.
698 *
699 * @return {@code true} if, and only if, this charset is known by its
700 * implementor to be registered with the IANA
701 */
702 public final boolean isRegistered() {
703 return !name.startsWith("X-") && !name.startsWith("x-");
704 }
705
706 /**
707 * Returns this charset's human-readable name for the given locale.
708 *
709 * <p> The default implementation of this method simply returns this
710 * charset's canonical name. Concrete subclasses of this class may
711 * override this method in order to provide a localized display name. </p>
712 *
713 * @param locale
714 * The locale for which the display name is to be retrieved
715 *
716 * @return The display name of this charset in the given locale
717 */
718 public String displayName(Locale locale) {
719 return name;
720 }
721
722 /**
723 * Tells whether or not this charset contains the given charset.
724 *
725 * <p> A charset <i>C</i> is said to <i>contain</i> a charset <i>D</i> if,
726 * and only if, every character representable in <i>D</i> is also
727 * representable in <i>C</i>. If this relationship holds then it is
728 * guaranteed that every string that can be encoded in <i>D</i> can also be
729 * encoded in <i>C</i> without performing any replacements.
730 *
731 * <p> That <i>C</i> contains <i>D</i> does not imply that each character
732 * representable in <i>C</i> by a particular byte sequence is represented
733 * in <i>D</i> by the same byte sequence, although sometimes this is the
734 * case.
735 *
736 * <p> Every charset contains itself.
737 *
738 * <p> This method computes an approximation of the containment relation:
739 * If it returns {@code true} then the given charset is known to be
740 * contained by this charset; if it returns {@code false}, however, then
741 * it is not necessarily the case that the given charset is not contained
742 * in this charset.
743 *
744 * @param cs
745 * The given charset
746 *
747 * @return {@code true} if the given charset is contained in this charset
748 */
749 public abstract boolean contains(Charset cs);
750
751 /**
752 * Constructs a new decoder for this charset.
753 *
754 * @return A new decoder for this charset
755 */
756 public abstract CharsetDecoder newDecoder();
757
758 /**
759 * Constructs a new encoder for this charset.
760 *
761 * @return A new encoder for this charset
762 *
763 * @throws UnsupportedOperationException
764 * If this charset does not support encoding
765 */
766 public abstract CharsetEncoder newEncoder();
767
768 /**
769 * Tells whether or not this charset supports encoding.
770 *
771 * <p> Nearly all charsets support encoding. The primary exceptions are
772 * special-purpose <i>auto-detect</i> charsets whose decoders can determine
773 * which of several possible encoding schemes is in use by examining the
774 * input byte sequence. Such charsets do not support encoding because
775 * there is no way to determine which encoding should be used on output.
776 * Implementations of such charsets should override this method to return
777 * {@code false}. </p>
778 *
779 * @return {@code true} if, and only if, this charset supports encoding
780 */
781 public boolean canEncode() {
782 return true;
783 }
784
785 /**
786 * Convenience method that decodes bytes in this charset into Unicode
787 * characters.
788 *
789 * <p> An invocation of this method upon a charset {@code cs} returns the
790 * same result as the expression
791 *
792 * <pre>
793 * cs.newDecoder()
794 * .onMalformedInput(CodingErrorAction.REPLACE)
795 * .onUnmappableCharacter(CodingErrorAction.REPLACE)
796 * .decode(bb); </pre>
797 *
798 * except that it is potentially more efficient because it can cache
799 * decoders between successive invocations.
800 *
801 * <p> This method always replaces malformed-input and unmappable-character
802 * sequences with this charset's default replacement byte array. In order
803 * to detect such sequences, use the {@link
804 * CharsetDecoder#decode(java.nio.ByteBuffer)} method directly. </p>
805 *
806 * @param bb The byte buffer to be decoded
807 *
808 * @return A char buffer containing the decoded characters
809 */
810 public final CharBuffer decode(ByteBuffer bb) {
811 try {
812 return ThreadLocalCoders.decoderFor(this)
813 .onMalformedInput(CodingErrorAction.REPLACE)
814 .onUnmappableCharacter(CodingErrorAction.REPLACE)
815 .decode(bb);
816 } catch (CharacterCodingException x) {
817 throw new Error(x); // Can't happen
818 }
819 }
820
821 /**
822 * Convenience method that encodes Unicode characters into bytes in this
823 * charset.
824 *
825 * <p> An invocation of this method upon a charset {@code cs} returns the
826 * same result as the expression
827 *
828 * <pre>
829 * cs.newEncoder()
830 * .onMalformedInput(CodingErrorAction.REPLACE)
831 * .onUnmappableCharacter(CodingErrorAction.REPLACE)
832 * .encode(bb); </pre>
833 *
834 * except that it is potentially more efficient because it can cache
835 * encoders between successive invocations.
836 *
837 * <p> This method always replaces malformed-input and unmappable-character
838 * sequences with this charset's default replacement string. In order to
839 * detect such sequences, use the {@link
840 * CharsetEncoder#encode(java.nio.CharBuffer)} method directly. </p>
841 *
842 * @param cb The char buffer to be encoded
843 *
844 * @return A byte buffer containing the encoded characters
845 */
846 public final ByteBuffer encode(CharBuffer cb) {
847 try {
848 return ThreadLocalCoders.encoderFor(this)
849 .onMalformedInput(CodingErrorAction.REPLACE)
850 .onUnmappableCharacter(CodingErrorAction.REPLACE)
851 .encode(cb);
852 } catch (CharacterCodingException x) {
853 throw new Error(x); // Can't happen
854 }
855 }
856
857 /**
858 * Convenience method that encodes a string into bytes in this charset.
859 *
860 * <p> An invocation of this method upon a charset {@code cs} returns the
861 * same result as the expression
862 *
863 * <pre>
864 * cs.encode(CharBuffer.wrap(s)); </pre>
865 *
866 * @param str The string to be encoded
867 *
868 * @return A byte buffer containing the encoded characters
869 */
870 public final ByteBuffer encode(String str) {
871 return encode(CharBuffer.wrap(str));
872 }
873
874 /**
875 * Compares this charset to another.
876 *
877 * <p> Charsets are ordered by their canonical names, without regard to
878 * case. </p>
879 *
880 * @param that
881 * The charset to which this charset is to be compared
882 *
883 * @return A negative integer, zero, or a positive integer as this charset
884 * is less than, equal to, or greater than the specified charset
885 */
886 public final int compareTo(Charset that) {
887 return (name().compareToIgnoreCase(that.name()));
888 }
889
890 /**
891 * Computes a hashcode for this charset.
892 *
893 * @return An integer hashcode
894 */
895 public final int hashCode() {
896 return name().hashCode();
897 }
898
899 /**
900 * Tells whether or not this object is equal to another.
901 *
902 * <p> Two charsets are equal if, and only if, they have the same canonical
903 * names. A charset is never equal to any other type of object. </p>
904 *
905 * @return {@code true} if, and only if, this charset is equal to the
906 * given object
907 */
908 public final boolean equals(Object ob) {
909 if (!(ob instanceof Charset))
910 return false;
911 if (this == ob)
912 return true;
913 return name.equals(((Charset)ob).name());
914 }
915
916 /**
917 * Returns a string describing this charset.
918 *
919 * @return A string describing this charset
920 */
921 public final String toString() {
922 return name();
923 }
924
925 }