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