1 /* 2 * Copyright (c) 2000, 2013, 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 name="names"></a><a name="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 name="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 name="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 name="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 width="80%" summary="Description of standard charsets"> 151 * <tr><th align="left">Charset</th><th align="left">Description</th></tr> 152 * <tr><td valign=top>{@code US-ASCII}</td> 153 * <td>Seven-bit ASCII, a.k.a. {@code ISO646-US}, 154 * a.k.a. the Basic Latin block of the Unicode character set</td></tr> 155 * <tr><td valign=top><code>ISO-8859-1 </code></td> 156 * <td>ISO Latin Alphabet No. 1, a.k.a. {@code ISO-LATIN-1}</td></tr> 157 * <tr><td valign=top>{@code UTF-8}</td> 158 * <td>Eight-bit UCS Transformation Format</td></tr> 159 * <tr><td valign=top>{@code UTF-16BE}</td> 160 * <td>Sixteen-bit UCS Transformation Format, 161 * big-endian byte order</td></tr> 162 * <tr><td valign=top>{@code UTF-16LE}</td> 163 * <td>Sixteen-bit UCS Transformation Format, 164 * little-endian byte order</td></tr> 165 * <tr><td valign=top>{@code UTF-16}</td> 166 * <td>Sixteen-bit UCS Transformation Format, 167 * byte order identified by an optional byte-order mark</td></tr> 168 * </table></blockquote> 169 * 170 * <p> The {@code UTF-8} charset is specified by <a 171 * href="http://www.ietf.org/rfc/rfc2279.txt"><i>RFC 2279</i></a>; the 172 * transformation format upon which it is based is specified in 173 * Amendment 2 of ISO 10646-1 and is also described in the <a 174 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode 175 * Standard</i></a>. 176 * 177 * <p> The {@code UTF-16} charsets are specified by <a 178 * href="http://www.ietf.org/rfc/rfc2781.txt"><i>RFC 2781</i></a>; the 179 * transformation formats upon which they are based are specified in 180 * Amendment 1 of ISO 10646-1 and are also described in the <a 181 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode 182 * Standard</i></a>. 183 * 184 * <p> The {@code UTF-16} charsets use sixteen-bit quantities and are 185 * therefore sensitive to byte order. In these encodings the byte order of a 186 * stream may be indicated by an initial <i>byte-order mark</i> represented by 187 * the Unicode character <code>'\uFEFF'</code>. Byte-order marks are handled 188 * as follows: 189 * 190 * <ul> 191 * 192 * <li><p> When decoding, the {@code UTF-16BE} and {@code UTF-16LE} 193 * charsets interpret the initial byte-order marks as a <small>ZERO-WIDTH 194 * NON-BREAKING SPACE</small>; when encoding, they do not write 195 * byte-order marks. </p></li> 196 197 * 198 * <li><p> When decoding, the {@code UTF-16} charset interprets the 199 * byte-order mark at the beginning of the input stream to indicate the 200 * byte-order of the stream but defaults to big-endian if there is no 201 * byte-order mark; when encoding, it uses big-endian byte order and writes 202 * a big-endian byte-order mark. </p></li> 203 * 204 * </ul> 205 * 206 * In any case, byte order marks occurring after the first element of an 207 * input sequence are not omitted since the same code is used to represent 208 * <small>ZERO-WIDTH NON-BREAKING SPACE</small>. 209 * 210 * <p> Every instance of the Java virtual machine has a default charset, which 211 * may or may not be one of the standard charsets. The default charset is 212 * determined during virtual-machine startup and typically depends upon the 213 * locale and charset being used by the underlying operating system. </p> 214 * 215 * <p>The {@link StandardCharsets} class defines constants for each of the 216 * standard charsets. 217 * 218 * <h2>Terminology</h2> 219 * 220 * <p> The name of this class is taken from the terms used in 221 * <a href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC 2278</i></a>. 222 * In that document a <i>charset</i> is defined as the combination of 223 * one or more coded character sets and a character-encoding scheme. 224 * (This definition is confusing; some other software systems define 225 * <i>charset</i> as a synonym for <i>coded character set</i>.) 226 * 227 * <p> A <i>coded character set</i> is a mapping between a set of abstract 228 * characters and a set of integers. US-ASCII, ISO 8859-1, 229 * JIS X 0201, and Unicode are examples of coded character sets. 230 * 231 * <p> Some standards have defined a <i>character set</i> to be simply a 232 * set of abstract characters without an associated assigned numbering. 233 * An alphabet is an example of such a character set. However, the subtle 234 * distinction between <i>character set</i> and <i>coded character set</i> 235 * is rarely used in practice; the former has become a short form for the 236 * latter, including in the Java API specification. 237 * 238 * <p> A <i>character-encoding scheme</i> is a mapping between one or more 239 * coded character sets and a set of octet (eight-bit byte) sequences. 240 * UTF-8, UTF-16, ISO 2022, and EUC are examples of 241 * character-encoding schemes. Encoding schemes are often associated with 242 * a particular coded character set; UTF-8, for example, is used only to 243 * encode Unicode. Some schemes, however, are associated with multiple 244 * coded character sets; EUC, for example, can be used to encode 245 * characters in a variety of Asian coded character sets. 246 * 247 * <p> When a coded character set is used exclusively with a single 248 * character-encoding scheme then the corresponding charset is usually 249 * named for the coded character set; otherwise a charset is usually named 250 * for the encoding scheme and, possibly, the locale of the coded 251 * character sets that it supports. Hence {@code US-ASCII} is both the 252 * name of a coded character set and of the charset that encodes it, while 253 * {@code EUC-JP} is the name of the charset that encodes the 254 * JIS X 0201, JIS X 0208, and JIS X 0212 255 * coded character sets for the Japanese language. 256 * 257 * <p> The native character encoding of the Java programming language is 258 * UTF-16. A charset in the Java platform therefore defines a mapping 259 * between sequences of sixteen-bit UTF-16 code units (that is, sequences 260 * of chars) and sequences of bytes. </p> 261 * 262 * 263 * @author Mark Reinhold 264 * @author JSR-51 Expert Group 265 * @since 1.4 266 * 267 * @see CharsetDecoder 268 * @see CharsetEncoder 269 * @see java.nio.charset.spi.CharsetProvider 270 * @see java.lang.Character 271 */ 272 273 public abstract class Charset 274 implements Comparable<Charset> 275 { 276 277 /* -- Static methods -- */ 278 279 private static volatile String bugLevel; 280 281 static boolean atBugLevel(String bl) { // package-private 282 String level = bugLevel; 283 if (level == null) { 284 if (!VM.isBooted()) 285 return false; 286 bugLevel = level = 287 GetPropertyAction.getProperty("sun.nio.cs.bugLevel", ""); 288 } 289 return level.equals(bl); 290 } 291 292 /** 293 * Checks that the given string is a legal charset name. </p> 294 * 295 * @param s 296 * A purported charset name 297 * 298 * @throws IllegalCharsetNameException 299 * If the given name is not a legal charset name 300 */ 301 private static void checkName(String s) { 302 int n = s.length(); 303 if (!atBugLevel("1.4")) { 304 if (n == 0) 305 throw new IllegalCharsetNameException(s); 306 } 307 for (int i = 0; i < n; i++) { 308 char c = s.charAt(i); 309 if (c >= 'A' && c <= 'Z') continue; 310 if (c >= 'a' && c <= 'z') continue; 311 if (c >= '0' && c <= '9') continue; 312 if (c == '-' && i != 0) continue; 313 if (c == '+' && i != 0) continue; 314 if (c == ':' && i != 0) continue; 315 if (c == '_' && i != 0) continue; 316 if (c == '.' && i != 0) continue; 317 throw new IllegalCharsetNameException(s); 318 } 319 } 320 321 /* The standard set of charsets */ 322 private static CharsetProvider standardProvider = new StandardCharsets(); 323 324 // Cache of the most-recently-returned charsets, 325 // along with the names that were used to find them 326 // 327 private static volatile Object[] cache1; // "Level 1" cache 328 private static volatile Object[] cache2; // "Level 2" cache 329 330 private static void cache(String charsetName, Charset cs) { 331 cache2 = cache1; 332 cache1 = new Object[] { charsetName, cs }; 333 } 334 335 // Creates an iterator that walks over the available providers, ignoring 336 // those whose lookup or instantiation causes a security exception to be 337 // thrown. Should be invoked with full privileges. 338 // 339 private static Iterator<CharsetProvider> providers() { 340 return new Iterator<>() { 341 ClassLoader cl = ClassLoader.getSystemClassLoader(); 342 ServiceLoader<CharsetProvider> sl = 343 ServiceLoader.load(CharsetProvider.class, cl); 344 Iterator<CharsetProvider> i = sl.iterator(); 345 CharsetProvider next = null; 346 347 private boolean getNext() { 348 while (next == null) { 349 try { 350 if (!i.hasNext()) 351 return false; 352 next = i.next(); 353 } catch (ServiceConfigurationError sce) { 354 if (sce.getCause() instanceof SecurityException) { 355 // Ignore security exceptions 356 continue; 357 } 358 throw sce; 359 } 360 } 361 return true; 362 } 363 364 public boolean hasNext() { 365 return getNext(); 366 } 367 368 public CharsetProvider next() { 369 if (!getNext()) 370 throw new NoSuchElementException(); 371 CharsetProvider n = next; 372 next = null; 373 return n; 374 } 375 376 public void remove() { 377 throw new UnsupportedOperationException(); 378 } 379 380 }; 381 } 382 383 // Thread-local gate to prevent recursive provider lookups 384 private static ThreadLocal<ThreadLocal<?>> gate = 385 new ThreadLocal<ThreadLocal<?>>(); 386 387 private static Charset lookupViaProviders(final String charsetName) { 388 389 // The runtime startup sequence looks up standard charsets as a 390 // consequence of the VM's invocation of System.initializeSystemClass 391 // in order to, e.g., set system properties and encode filenames. At 392 // that point the application class loader has not been initialized, 393 // however, so we can't look for providers because doing so will cause 394 // that loader to be prematurely initialized with incomplete 395 // information. 396 // 397 if (!VM.isBooted()) 398 return null; 399 400 if (gate.get() != null) 401 // Avoid recursive provider lookups 402 return null; 403 try { 404 gate.set(gate); 405 406 return AccessController.doPrivileged( 407 new PrivilegedAction<>() { 408 public Charset run() { 409 for (Iterator<CharsetProvider> i = providers(); 410 i.hasNext();) { 411 CharsetProvider cp = i.next(); 412 Charset cs = cp.charsetForName(charsetName); 413 if (cs != null) 414 return cs; 415 } 416 return null; 417 } 418 }); 419 420 } finally { 421 gate.set(null); 422 } 423 } 424 425 /* The extended set of charsets */ 426 private static class ExtendedProviderHolder { 427 static final CharsetProvider[] extendedProviders = extendedProviders(); 428 // returns ExtendedProvider, if installed 429 private static CharsetProvider[] extendedProviders() { 430 return AccessController.doPrivileged(new PrivilegedAction<>() { 431 public CharsetProvider[] run() { 432 CharsetProvider[] cps = new CharsetProvider[1]; 433 int n = 0; 434 ServiceLoader<CharsetProvider> sl = 435 ServiceLoader.loadInstalled(CharsetProvider.class); 436 for (CharsetProvider cp : sl) { 437 if (n + 1 > cps.length) { 438 cps = Arrays.copyOf(cps, cps.length << 1); 439 } 440 cps[n++] = cp; 441 } 442 return n == cps.length ? cps : Arrays.copyOf(cps, n); 443 }}); 444 } 445 } 446 447 private static Charset lookupExtendedCharset(String charsetName) { 448 if (!VM.isBooted()) // see lookupViaProviders() 449 return null; 450 CharsetProvider[] ecps = ExtendedProviderHolder.extendedProviders; 451 for (CharsetProvider cp : ecps) { 452 Charset cs = cp.charsetForName(charsetName); 453 if (cs != null) 454 return cs; 455 } 456 return null; 457 } 458 459 private static Charset lookup(String charsetName) { 460 if (charsetName == null) 461 throw new IllegalArgumentException("Null charset name"); 462 Object[] a; 463 if ((a = cache1) != null && charsetName.equals(a[0])) 464 return (Charset)a[1]; 465 // We expect most programs to use one Charset repeatedly. 466 // We convey a hint to this effect to the VM by putting the 467 // level 1 cache miss code in a separate method. 468 return lookup2(charsetName); 469 } 470 471 private static Charset lookup2(String charsetName) { 472 Object[] a; 473 if ((a = cache2) != null && charsetName.equals(a[0])) { 474 cache2 = cache1; 475 cache1 = a; 476 return (Charset)a[1]; 477 } 478 Charset cs; 479 if ((cs = standardProvider.charsetForName(charsetName)) != null || 480 (cs = lookupExtendedCharset(charsetName)) != null || 481 (cs = lookupViaProviders(charsetName)) != null) 482 { 483 cache(charsetName, cs); 484 return cs; 485 } 486 487 /* Only need to check the name if we didn't find a charset for it */ 488 checkName(charsetName); 489 return null; 490 } 491 492 /** 493 * Tells whether the named charset is supported. 494 * 495 * @param charsetName 496 * The name of the requested charset; may be either 497 * a canonical name or an alias 498 * 499 * @return {@code true} if, and only if, support for the named charset 500 * is available in the current Java virtual machine 501 * 502 * @throws IllegalCharsetNameException 503 * If the given charset name is illegal 504 * 505 * @throws IllegalArgumentException 506 * If the given {@code charsetName} is null 507 */ 508 public static boolean isSupported(String charsetName) { 509 return (lookup(charsetName) != null); 510 } 511 512 /** 513 * Returns a charset object for the named charset. 514 * 515 * @param charsetName 516 * The name of the requested charset; may be either 517 * a canonical name or an alias 518 * 519 * @return A charset object for the named charset 520 * 521 * @throws IllegalCharsetNameException 522 * If the given charset name is illegal 523 * 524 * @throws IllegalArgumentException 525 * If the given {@code charsetName} is null 526 * 527 * @throws UnsupportedCharsetException 528 * If no support for the named charset is available 529 * in this instance of the Java virtual machine 530 */ 531 public static Charset forName(String charsetName) { 532 Charset cs = lookup(charsetName); 533 if (cs != null) 534 return cs; 535 throw new UnsupportedCharsetException(charsetName); 536 } 537 538 // Fold charsets from the given iterator into the given map, ignoring 539 // charsets whose names already have entries in the map. 540 // 541 private static void put(Iterator<Charset> i, Map<String,Charset> m) { 542 while (i.hasNext()) { 543 Charset cs = i.next(); 544 if (!m.containsKey(cs.name())) 545 m.put(cs.name(), cs); 546 } 547 } 548 549 /** 550 * Constructs a sorted map from canonical charset names to charset objects. 551 * 552 * <p> The map returned by this method will have one entry for each charset 553 * for which support is available in the current Java virtual machine. If 554 * two or more supported charsets have the same canonical name then the 555 * resulting map will contain just one of them; which one it will contain 556 * is not specified. </p> 557 * 558 * <p> The invocation of this method, and the subsequent use of the 559 * resulting map, may cause time-consuming disk or network I/O operations 560 * to occur. This method is provided for applications that need to 561 * enumerate all of the available charsets, for example to allow user 562 * charset selection. This method is not used by the {@link #forName 563 * forName} method, which instead employs an efficient incremental lookup 564 * algorithm. 565 * 566 * <p> This method may return different results at different times if new 567 * charset providers are dynamically made available to the current Java 568 * virtual machine. In the absence of such changes, the charsets returned 569 * by this method are exactly those that can be retrieved via the {@link 570 * #forName forName} method. </p> 571 * 572 * @return An immutable, case-insensitive map from canonical charset names 573 * to charset objects 574 */ 575 public static SortedMap<String,Charset> availableCharsets() { 576 return AccessController.doPrivileged( 577 new PrivilegedAction<>() { 578 public SortedMap<String,Charset> run() { 579 TreeMap<String,Charset> m = 580 new TreeMap<>( 581 String.CASE_INSENSITIVE_ORDER); 582 put(standardProvider.charsets(), m); 583 CharsetProvider[] ecps = ExtendedProviderHolder.extendedProviders; 584 for (CharsetProvider ecp :ecps) { 585 put(ecp.charsets(), m); 586 } 587 for (Iterator<CharsetProvider> i = providers(); i.hasNext();) { 588 CharsetProvider cp = i.next(); 589 put(cp.charsets(), m); 590 } 591 return Collections.unmodifiableSortedMap(m); 592 } 593 }); 594 } 595 596 private static volatile Charset defaultCharset; 597 598 /** 599 * Returns the default charset of this Java virtual machine. 600 * 601 * <p> The default charset is determined during virtual-machine startup and 602 * typically depends upon the locale and charset of the underlying 603 * operating system. 604 * 605 * @return A charset object for the default charset 606 * 607 * @since 1.5 608 */ 609 public static Charset defaultCharset() { 610 if (defaultCharset == null) { 611 synchronized (Charset.class) { 612 String csn = GetPropertyAction.getProperty("file.encoding"); 613 Charset cs = lookup(csn); 614 if (cs != null) 615 defaultCharset = cs; 616 else 617 defaultCharset = forName("UTF-8"); 618 } 619 } 620 return defaultCharset; 621 } 622 623 624 /* -- Instance fields and methods -- */ 625 626 private final String name; // tickles a bug in oldjavac 627 private final String[] aliases; // tickles a bug in oldjavac 628 private final String[] zeroAliases = new String[0]; 629 private Set<String> aliasSet = null; 630 631 /** 632 * Initializes a new charset with the given canonical name and alias 633 * set. 634 * 635 * @param canonicalName 636 * The canonical name of this charset 637 * 638 * @param aliases 639 * An array of this charset's aliases, or null if it has no aliases 640 * 641 * @throws IllegalCharsetNameException 642 * If the canonical name or any of the aliases are illegal 643 */ 644 protected Charset(String canonicalName, String[] aliases) { 645 checkName(canonicalName); 646 String[] as = Objects.requireNonNullElse(aliases, zeroAliases); 647 for (int i = 0; i < as.length; i++) 648 checkName(as[i]); 649 this.name = canonicalName; 650 this.aliases = as; 651 } 652 653 /** 654 * Returns this charset's canonical name. 655 * 656 * @return The canonical name of this charset 657 */ 658 public final String name() { 659 return name; 660 } 661 662 /** 663 * Returns a set containing this charset's aliases. 664 * 665 * @return An immutable set of this charset's aliases 666 */ 667 public final Set<String> aliases() { 668 if (aliasSet != null) 669 return aliasSet; 670 int n = aliases.length; 671 HashSet<String> hs = new HashSet<>(n); 672 for (int i = 0; i < n; i++) 673 hs.add(aliases[i]); 674 aliasSet = Collections.unmodifiableSet(hs); 675 return aliasSet; 676 } 677 678 /** 679 * Returns this charset's human-readable name for the default locale. 680 * 681 * <p> The default implementation of this method simply returns this 682 * charset's canonical name. Concrete subclasses of this class may 683 * override this method in order to provide a localized display name. </p> 684 * 685 * @return The display name of this charset in the default locale 686 */ 687 public String displayName() { 688 return name; 689 } 690 691 /** 692 * Tells whether or not this charset is registered in the <a 693 * href="http://www.iana.org/assignments/character-sets">IANA Charset 694 * Registry</a>. 695 * 696 * @return {@code true} if, and only if, this charset is known by its 697 * implementor to be registered with the IANA 698 */ 699 public final boolean isRegistered() { 700 return !name.startsWith("X-") && !name.startsWith("x-"); 701 } 702 703 /** 704 * Returns this charset's human-readable name for the given locale. 705 * 706 * <p> The default implementation of this method simply returns this 707 * charset's canonical name. Concrete subclasses of this class may 708 * override this method in order to provide a localized display name. </p> 709 * 710 * @param locale 711 * The locale for which the display name is to be retrieved 712 * 713 * @return The display name of this charset in the given locale 714 */ 715 public String displayName(Locale locale) { 716 return name; 717 } 718 719 /** 720 * Tells whether or not this charset contains the given charset. 721 * 722 * <p> A charset <i>C</i> is said to <i>contain</i> a charset <i>D</i> if, 723 * and only if, every character representable in <i>D</i> is also 724 * representable in <i>C</i>. If this relationship holds then it is 725 * guaranteed that every string that can be encoded in <i>D</i> can also be 726 * encoded in <i>C</i> without performing any replacements. 727 * 728 * <p> That <i>C</i> contains <i>D</i> does not imply that each character 729 * representable in <i>C</i> by a particular byte sequence is represented 730 * in <i>D</i> by the same byte sequence, although sometimes this is the 731 * case. 732 * 733 * <p> Every charset contains itself. 734 * 735 * <p> This method computes an approximation of the containment relation: 736 * If it returns {@code true} then the given charset is known to be 737 * contained by this charset; if it returns {@code false}, however, then 738 * it is not necessarily the case that the given charset is not contained 739 * in this charset. 740 * 741 * @param cs 742 * The given charset 743 * 744 * @return {@code true} if the given charset is contained in this charset 745 */ 746 public abstract boolean contains(Charset cs); 747 748 /** 749 * Constructs a new decoder for this charset. 750 * 751 * @return A new decoder for this charset 752 */ 753 public abstract CharsetDecoder newDecoder(); 754 755 /** 756 * Constructs a new encoder for this charset. 757 * 758 * @return A new encoder for this charset 759 * 760 * @throws UnsupportedOperationException 761 * If this charset does not support encoding 762 */ 763 public abstract CharsetEncoder newEncoder(); 764 765 /** 766 * Tells whether or not this charset supports encoding. 767 * 768 * <p> Nearly all charsets support encoding. The primary exceptions are 769 * special-purpose <i>auto-detect</i> charsets whose decoders can determine 770 * which of several possible encoding schemes is in use by examining the 771 * input byte sequence. Such charsets do not support encoding because 772 * there is no way to determine which encoding should be used on output. 773 * Implementations of such charsets should override this method to return 774 * {@code false}. </p> 775 * 776 * @return {@code true} if, and only if, this charset supports encoding 777 */ 778 public boolean canEncode() { 779 return true; 780 } 781 782 /** 783 * Convenience method that decodes bytes in this charset into Unicode 784 * characters. 785 * 786 * <p> An invocation of this method upon a charset {@code cs} returns the 787 * same result as the expression 788 * 789 * <pre> 790 * cs.newDecoder() 791 * .onMalformedInput(CodingErrorAction.REPLACE) 792 * .onUnmappableCharacter(CodingErrorAction.REPLACE) 793 * .decode(bb); </pre> 794 * 795 * except that it is potentially more efficient because it can cache 796 * decoders between successive invocations. 797 * 798 * <p> This method always replaces malformed-input and unmappable-character 799 * sequences with this charset's default replacement byte array. In order 800 * to detect such sequences, use the {@link 801 * CharsetDecoder#decode(java.nio.ByteBuffer)} method directly. </p> 802 * 803 * @param bb The byte buffer to be decoded 804 * 805 * @return A char buffer containing the decoded characters 806 */ 807 public final CharBuffer decode(ByteBuffer bb) { 808 try { 809 return ThreadLocalCoders.decoderFor(this) 810 .onMalformedInput(CodingErrorAction.REPLACE) 811 .onUnmappableCharacter(CodingErrorAction.REPLACE) 812 .decode(bb); 813 } catch (CharacterCodingException x) { 814 throw new Error(x); // Can't happen 815 } 816 } 817 818 /** 819 * Convenience method that encodes Unicode characters into bytes in this 820 * charset. 821 * 822 * <p> An invocation of this method upon a charset {@code cs} returns the 823 * same result as the expression 824 * 825 * <pre> 826 * cs.newEncoder() 827 * .onMalformedInput(CodingErrorAction.REPLACE) 828 * .onUnmappableCharacter(CodingErrorAction.REPLACE) 829 * .encode(bb); </pre> 830 * 831 * except that it is potentially more efficient because it can cache 832 * encoders between successive invocations. 833 * 834 * <p> This method always replaces malformed-input and unmappable-character 835 * sequences with this charset's default replacement string. In order to 836 * detect such sequences, use the {@link 837 * CharsetEncoder#encode(java.nio.CharBuffer)} method directly. </p> 838 * 839 * @param cb The char buffer to be encoded 840 * 841 * @return A byte buffer containing the encoded characters 842 */ 843 public final ByteBuffer encode(CharBuffer cb) { 844 try { 845 return ThreadLocalCoders.encoderFor(this) 846 .onMalformedInput(CodingErrorAction.REPLACE) 847 .onUnmappableCharacter(CodingErrorAction.REPLACE) 848 .encode(cb); 849 } catch (CharacterCodingException x) { 850 throw new Error(x); // Can't happen 851 } 852 } 853 854 /** 855 * Convenience method that encodes a string into bytes in this charset. 856 * 857 * <p> An invocation of this method upon a charset {@code cs} returns the 858 * same result as the expression 859 * 860 * <pre> 861 * cs.encode(CharBuffer.wrap(s)); </pre> 862 * 863 * @param str The string to be encoded 864 * 865 * @return A byte buffer containing the encoded characters 866 */ 867 public final ByteBuffer encode(String str) { 868 return encode(CharBuffer.wrap(str)); 869 } 870 871 /** 872 * Compares this charset to another. 873 * 874 * <p> Charsets are ordered by their canonical names, without regard to 875 * case. </p> 876 * 877 * @param that 878 * The charset to which this charset is to be compared 879 * 880 * @return A negative integer, zero, or a positive integer as this charset 881 * is less than, equal to, or greater than the specified charset 882 */ 883 public final int compareTo(Charset that) { 884 return (name().compareToIgnoreCase(that.name())); 885 } 886 887 /** 888 * Computes a hashcode for this charset. 889 * 890 * @return An integer hashcode 891 */ 892 public final int hashCode() { 893 return name().hashCode(); 894 } 895 896 /** 897 * Tells whether or not this object is equal to another. 898 * 899 * <p> Two charsets are equal if, and only if, they have the same canonical 900 * names. A charset is never equal to any other type of object. </p> 901 * 902 * @return {@code true} if, and only if, this charset is equal to the 903 * given object 904 */ 905 public final boolean equals(Object ob) { 906 if (!(ob instanceof Charset)) 907 return false; 908 if (this == ob) 909 return true; 910 return name.equals(((Charset)ob).name()); 911 } 912 913 /** 914 * Returns a string describing this charset. 915 * 916 * @return A string describing this charset 917 */ 918 public final String toString() { 919 return name(); 920 } 921 922 }