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