1 /* 2 * Copyright (c) 2000, 2010, 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.AccessControlException; 33 import java.security.PrivilegedAction; 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.Set; 41 import java.util.ServiceLoader; 42 import java.util.ServiceConfigurationError; 43 import java.util.SortedMap; 44 import java.util.TreeMap; 45 import sun.misc.ASCIICaseInsensitiveComparator; 46 import sun.nio.cs.StandardCharsets; 47 import sun.nio.cs.ThreadLocalCoders; 48 import sun.security.action.GetPropertyAction; 49 50 51 /** 52 * A named mapping between sequences of sixteen-bit Unicode <a 53 * href="../../lang/Character.html#unicode">code units</a> and sequences of 54 * bytes. This class defines methods for creating decoders and encoders and 55 * for retrieving the various names associated with a charset. Instances of 56 * this class are immutable. 57 * 58 * <p> This class also defines static methods for testing whether a particular 59 * charset is supported, for locating charset instances by name, and for 60 * constructing a map that contains every charset for which support is 61 * available in the current Java virtual machine. Support for new charsets can 62 * be added via the service-provider interface defined in the {@link 63 * java.nio.charset.spi.CharsetProvider} class. 64 * 65 * <p> All of the methods defined in this class are safe for use by multiple 66 * concurrent threads. 67 * 68 * 69 * <a name="names"><a name="charenc"> 70 * <h4>Charset names</h4> 71 * 72 * <p> Charsets are named by strings composed of the following characters: 73 * 74 * <ul> 75 * 76 * <li> The uppercase letters <tt>'A'</tt> through <tt>'Z'</tt> 77 * (<tt>'\u0041'</tt> through <tt>'\u005a'</tt>), 78 * 79 * <li> The lowercase letters <tt>'a'</tt> through <tt>'z'</tt> 80 * (<tt>'\u0061'</tt> through <tt>'\u007a'</tt>), 81 * 82 * <li> The digits <tt>'0'</tt> through <tt>'9'</tt> 83 * (<tt>'\u0030'</tt> through <tt>'\u0039'</tt>), 84 * 85 * <li> The dash character <tt>'-'</tt> 86 * (<tt>'\u002d'</tt>, <small>HYPHEN-MINUS</small>), 87 * 88 * <li> The plus character <tt>'+'</tt> 89 * (<tt>'\u002b'</tt>, <small>PLUS SIGN</small>), 90 * 91 * <li> The period character <tt>'.'</tt> 92 * (<tt>'\u002e'</tt>, <small>FULL STOP</small>), 93 * 94 * <li> The colon character <tt>':'</tt> 95 * (<tt>'\u003a'</tt>, <small>COLON</small>), and 96 * 97 * <li> The underscore character <tt>'_'</tt> 98 * (<tt>'\u005f'</tt>, <small>LOW LINE</small>). 99 * 100 * </ul> 101 * 102 * A charset name must begin with either a letter or a digit. The empty string 103 * is not a legal charset name. Charset names are not case-sensitive; that is, 104 * case is always ignored when comparing charset names. Charset names 105 * generally follow the conventions documented in <a 106 * href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC 2278: IANA Charset 107 * Registration Procedures</i></a>. 108 * 109 * <p> Every charset has a <i>canonical name</i> and may also have one or more 110 * <i>aliases</i>. The canonical name is returned by the {@link #name() name} method 111 * of this class. Canonical names are, by convention, usually in upper case. 112 * The aliases of a charset are returned by the {@link #aliases() aliases} 113 * method. 114 * 115 * <a name="hn"> 116 * 117 * <p> Some charsets have an <i>historical name</i> that is defined for 118 * compatibility with previous versions of the Java platform. A charset's 119 * historical name is either its canonical name or one of its aliases. The 120 * historical name is returned by the <tt>getEncoding()</tt> methods of the 121 * {@link java.io.InputStreamReader#getEncoding InputStreamReader} and {@link 122 * java.io.OutputStreamWriter#getEncoding OutputStreamWriter} classes. 123 * 124 * <a name="iana"> 125 * 126 * <p> If a charset listed in the <a 127 * href="http://www.iana.org/assignments/character-sets"><i>IANA Charset 128 * Registry</i></a> is supported by an implementation of the Java platform then 129 * its canonical name must be the name listed in the registry. Many charsets 130 * are given more than one name in the registry, in which case the registry 131 * identifies one of the names as <i>MIME-preferred</i>. If a charset has more 132 * than one registry name then its canonical name must be the MIME-preferred 133 * name and the other names in the registry must be valid aliases. If a 134 * supported charset is not listed in the IANA registry then its canonical name 135 * must begin with one of the strings <tt>"X-"</tt> or <tt>"x-"</tt>. 136 * 137 * <p> The IANA charset registry does change over time, and so the canonical 138 * name and the aliases of a particular charset may also change over time. To 139 * ensure compatibility it is recommended that no alias ever be removed from a 140 * charset, and that if the canonical name of a charset is changed then its 141 * previous canonical name be made into an alias. 142 * 143 * 144 * <h4>Standard charsets</h4> 145 * 146 * <a name="standard"> 147 * 148 * <p> Every implementation of the Java platform is required to support the 149 * following standard charsets. Consult the release documentation for your 150 * implementation to see if any other charsets are supported. The behavior 151 * of such optional charsets may differ between implementations. 152 * 153 * <blockquote><table width="80%" summary="Description of standard charsets"> 154 * <tr><th><p align="left">Charset</p></th><th><p align="left">Description</p></th></tr> 155 * <tr><td valign=top><tt>US-ASCII</tt></td> 156 * <td>Seven-bit ASCII, a.k.a. <tt>ISO646-US</tt>, 157 * a.k.a. the Basic Latin block of the Unicode character set</td></tr> 158 * <tr><td valign=top><tt>ISO-8859-1 </tt></td> 159 * <td>ISO Latin Alphabet No. 1, a.k.a. <tt>ISO-LATIN-1</tt></td></tr> 160 * <tr><td valign=top><tt>UTF-8</tt></td> 161 * <td>Eight-bit UCS Transformation Format</td></tr> 162 * <tr><td valign=top><tt>UTF-16BE</tt></td> 163 * <td>Sixteen-bit UCS Transformation Format, 164 * big-endian byte order</td></tr> 165 * <tr><td valign=top><tt>UTF-16LE</tt></td> 166 * <td>Sixteen-bit UCS Transformation Format, 167 * little-endian byte order</td></tr> 168 * <tr><td valign=top><tt>UTF-16</tt></td> 169 * <td>Sixteen-bit UCS Transformation Format, 170 * byte order identified by an optional byte-order mark</td></tr> 171 * </table></blockquote> 172 * 173 * <p> The <tt>UTF-8</tt> charset is specified by <a 174 * href="http://www.ietf.org/rfc/rfc2279.txt"><i>RFC 2279</i></a>; the 175 * transformation format upon which it is based is specified in 176 * Amendment 2 of ISO 10646-1 and is also described in the <a 177 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode 178 * Standard</i></a>. 179 * 180 * <p> The <tt>UTF-16</tt> charsets are specified by <a 181 * href="http://www.ietf.org/rfc/rfc2781.txt"><i>RFC 2781</i></a>; the 182 * transformation formats upon which they are based are specified in 183 * Amendment 1 of ISO 10646-1 and are also described in the <a 184 * href="http://www.unicode.org/unicode/standard/standard.html"><i>Unicode 185 * Standard</i></a>. 186 * 187 * <p> The <tt>UTF-16</tt> charsets use sixteen-bit quantities and are 188 * therefore sensitive to byte order. In these encodings the byte order of a 189 * stream may be indicated by an initial <i>byte-order mark</i> represented by 190 * the Unicode character <tt>'\uFEFF'</tt>. Byte-order marks are handled 191 * as follows: 192 * 193 * <ul> 194 * 195 * <li><p> When decoding, the <tt>UTF-16BE</tt> and <tt>UTF-16LE</tt> 196 * charsets interpret the initial byte-order marks as a <small>ZERO-WIDTH 197 * NON-BREAKING SPACE</small>; when encoding, they do not write 198 * byte-order marks. </p></li> 199 200 * 201 * <li><p> When decoding, the <tt>UTF-16</tt> charset interprets the 202 * byte-order mark at the beginning of the input stream to indicate the 203 * byte-order of the stream but defaults to big-endian if there is no 204 * byte-order mark; when encoding, it uses big-endian byte order and writes 205 * a big-endian byte-order mark. </p></li> 206 * 207 * </ul> 208 * 209 * In any case, byte order marks occuring after the first element of an 210 * input sequence are not omitted since the same code is used to represent 211 * <small>ZERO-WIDTH NON-BREAKING SPACE</small>. 212 * 213 * <p> Every instance of the Java virtual machine has a default charset, which 214 * may or may not be one of the standard charsets. The default charset is 215 * determined during virtual-machine startup and typically depends upon the 216 * locale and charset being used by the underlying operating system. </p> 217 * 218 * <p>The {@link StandardCharset} class defines constants for each of the 219 * standard charsets. 220 * 221 * <h4>Terminology</h4> 222 * 223 * <p> The name of this class is taken from the terms used in 224 * <a href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC 2278</i></a>. 225 * In that document a <i>charset</i> is defined as the combination of 226 * one or more coded character sets and a character-encoding scheme. 227 * (This definition is confusing; some other software systems define 228 * <i>charset</i> as a synonym for <i>coded character set</i>.) 229 * 230 * <p> A <i>coded character set</i> is a mapping between a set of abstract 231 * characters and a set of integers. US-ASCII, ISO 8859-1, 232 * JIS X 0201, and Unicode are examples of coded character sets. 233 * 234 * <p> Some standards have defined a <i>character set</i> to be simply a 235 * set of abstract characters without an associated assigned numbering. 236 * An alphabet is an example of such a character set. However, the subtle 237 * distinction between <i>character set</i> and <i>coded character set</i> 238 * is rarely used in practice; the former has become a short form for the 239 * latter, including in the Java API specification. 240 * 241 * <p> A <i>character-encoding scheme</i> is a mapping between one or more 242 * coded character sets and a set of octet (eight-bit byte) sequences. 243 * UTF-8, UTF-16, ISO 2022, and EUC are examples of 244 * character-encoding schemes. Encoding schemes are often associated with 245 * a particular coded character set; UTF-8, for example, is used only to 246 * encode Unicode. Some schemes, however, are associated with multiple 247 * coded character sets; EUC, for example, can be used to encode 248 * characters in a variety of Asian coded character sets. 249 * 250 * <p> When a coded character set is used exclusively with a single 251 * character-encoding scheme then the corresponding charset is usually 252 * named for the coded character set; otherwise a charset is usually named 253 * for the encoding scheme and, possibly, the locale of the coded 254 * character sets that it supports. Hence <tt>US-ASCII</tt> is both the 255 * name of a coded character set and of the charset that encodes it, while 256 * <tt>EUC-JP</tt> is the name of the charset that encodes the 257 * JIS X 0201, JIS X 0208, and JIS X 0212 258 * coded character sets for the Japanese language. 259 * 260 * <p> The native character encoding of the Java programming language is 261 * UTF-16. A charset in the Java platform therefore defines a mapping 262 * between sequences of sixteen-bit UTF-16 code units (that is, sequences 263 * of chars) and sequences of bytes. </p> 264 * 265 * 266 * @author Mark Reinhold 267 * @author JSR-51 Expert Group 268 * @since 1.4 269 * 270 * @see CharsetDecoder 271 * @see CharsetEncoder 272 * @see java.nio.charset.spi.CharsetProvider 273 * @see java.lang.Character 274 */ 275 276 public abstract class Charset 277 implements Comparable<Charset> 278 { 279 280 /* -- Static methods -- */ 281 282 private static volatile String bugLevel = null; 283 284 static boolean atBugLevel(String bl) { // package-private 285 String level = bugLevel; 286 if (level == null) { 287 if (!sun.misc.VM.isBooted()) 288 return false; 289 bugLevel = level = AccessController.doPrivileged( 290 new GetPropertyAction("sun.nio.cs.bugLevel", "")); 291 } 292 return level.equals(bl); 293 } 294 295 /** 296 * Checks that the given string is a legal charset name. </p> 297 * 298 * @param s 299 * A purported charset name 300 * 301 * @throws IllegalCharsetNameException 302 * If the given name is not a legal charset name 303 */ 304 private static void checkName(String s) { 305 int n = s.length(); 306 if (!atBugLevel("1.4")) { 307 if (n == 0) 308 throw new IllegalCharsetNameException(s); 309 } 310 for (int i = 0; i < n; i++) { 311 char c = s.charAt(i); 312 if (c >= 'A' && c <= 'Z') continue; 313 if (c >= 'a' && c <= 'z') continue; 314 if (c >= '0' && c <= '9') continue; 315 if (c == '-' && i != 0) continue; 316 if (c == '+' && i != 0) continue; 317 if (c == ':' && i != 0) continue; 318 if (c == '_' && i != 0) continue; 319 if (c == '.' && i != 0) continue; 320 throw new IllegalCharsetNameException(s); 321 } 322 } 323 324 /* The standard set of charsets */ 325 private static CharsetProvider standardProvider = new StandardCharsets(); 326 327 // Cache of the most-recently-returned charsets, 328 // along with the names that were used to find them 329 // 330 private static volatile Object[] cache1 = null; // "Level 1" cache 331 private static volatile Object[] cache2 = null; // "Level 2" cache 332 333 private static void cache(String charsetName, Charset cs) { 334 cache2 = cache1; 335 cache1 = new Object[] { charsetName, cs }; 336 } 337 338 // Creates an iterator that walks over the available providers, ignoring 339 // those whose lookup or instantiation causes a security exception to be 340 // thrown. Should be invoked with full privileges. 341 // 342 private static Iterator providers() { 343 return new Iterator() { 344 345 ClassLoader cl = ClassLoader.getSystemClassLoader(); 346 ServiceLoader<CharsetProvider> sl = 347 ServiceLoader.load(CharsetProvider.class, cl); 348 Iterator<CharsetProvider> i = sl.iterator(); 349 350 Object next = null; 351 352 private boolean getNext() { 353 while (next == null) { 354 try { 355 if (!i.hasNext()) 356 return false; 357 next = i.next(); 358 } catch (ServiceConfigurationError sce) { 359 if (sce.getCause() instanceof SecurityException) { 360 // Ignore security exceptions 361 continue; 362 } 363 throw sce; 364 } 365 } 366 return true; 367 } 368 369 public boolean hasNext() { 370 return getNext(); 371 } 372 373 public Object next() { 374 if (!getNext()) 375 throw new NoSuchElementException(); 376 Object n = next; 377 next = null; 378 return n; 379 } 380 381 public void remove() { 382 throw new UnsupportedOperationException(); 383 } 384 385 }; 386 } 387 388 // Thread-local gate to prevent recursive provider lookups 389 private static ThreadLocal<ThreadLocal> gate = new ThreadLocal<ThreadLocal>(); 390 391 private static Charset lookupViaProviders(final String charsetName) { 392 393 // The runtime startup sequence looks up standard charsets as a 394 // consequence of the VM's invocation of System.initializeSystemClass 395 // in order to, e.g., set system properties and encode filenames. At 396 // that point the application class loader has not been initialized, 397 // however, so we can't look for providers because doing so will cause 398 // that loader to be prematurely initialized with incomplete 399 // information. 400 // 401 if (!sun.misc.VM.isBooted()) 402 return null; 403 404 if (gate.get() != null) 405 // Avoid recursive provider lookups 406 return null; 407 try { 408 gate.set(gate); 409 410 return AccessController.doPrivileged( 411 new PrivilegedAction<Charset>() { 412 public Charset run() { 413 for (Iterator i = providers(); i.hasNext();) { 414 CharsetProvider cp = (CharsetProvider)i.next(); 415 Charset cs = cp.charsetForName(charsetName); 416 if (cs != null) 417 return cs; 418 } 419 return null; 420 } 421 }); 422 423 } finally { 424 gate.set(null); 425 } 426 } 427 428 /* The extended set of charsets */ 429 private static Object extendedProviderLock = new Object(); 430 private static boolean extendedProviderProbed = false; 431 private static CharsetProvider extendedProvider = null; 432 433 private static void probeExtendedProvider() { 434 AccessController.doPrivileged(new PrivilegedAction<Object>() { 435 public Object run() { 436 try { 437 Class epc 438 = Class.forName("sun.nio.cs.ext.ExtendedCharsets"); 439 extendedProvider = (CharsetProvider)epc.newInstance(); 440 } catch (ClassNotFoundException x) { 441 // Extended charsets not available 442 // (charsets.jar not present) 443 } catch (InstantiationException x) { 444 throw new Error(x); 445 } catch (IllegalAccessException x) { 446 throw new Error(x); 447 } 448 return null; 449 } 450 }); 451 } 452 453 private static Charset lookupExtendedCharset(String charsetName) { 454 CharsetProvider ecp = null; 455 synchronized (extendedProviderLock) { 456 if (!extendedProviderProbed) { 457 probeExtendedProvider(); 458 extendedProviderProbed = true; 459 } 460 ecp = extendedProvider; 461 } 462 return (ecp != null) ? ecp.charsetForName(charsetName) : null; 463 } 464 465 private static Charset lookup(String charsetName) { 466 if (charsetName == null) 467 throw new IllegalArgumentException("Null charset name"); 468 469 Object[] a; 470 if ((a = cache1) != null && charsetName.equals(a[0])) 471 return (Charset)a[1]; 472 // We expect most programs to use one Charset repeatedly. 473 // We convey a hint to this effect to the VM by putting the 474 // level 1 cache miss code in a separate method. 475 return lookup2(charsetName); 476 } 477 478 private static Charset lookup2(String charsetName) { 479 Object[] a; 480 if ((a = cache2) != null && charsetName.equals(a[0])) { 481 cache2 = cache1; 482 cache1 = a; 483 return (Charset)a[1]; 484 } 485 486 Charset cs; 487 if ((cs = standardProvider.charsetForName(charsetName)) != null || 488 (cs = lookupExtendedCharset(charsetName)) != null || 489 (cs = lookupViaProviders(charsetName)) != null) 490 { 491 cache(charsetName, cs); 492 return cs; 493 } 494 495 /* Only need to check the name if we didn't find a charset for it */ 496 checkName(charsetName); 497 return null; 498 } 499 500 /** 501 * Tells whether the named charset is supported. </p> 502 * 503 * @param charsetName 504 * The name of the requested charset; may be either 505 * a canonical name or an alias 506 * 507 * @return <tt>true</tt> if, and only if, support for the named charset 508 * is available in the current Java virtual machine 509 * 510 * @throws IllegalCharsetNameException 511 * If the given charset name is illegal 512 * 513 * @throws IllegalArgumentException 514 * If the given <tt>charsetName</tt> is null 515 */ 516 public static boolean isSupported(String charsetName) { 517 return (lookup(charsetName) != null); 518 } 519 520 /** 521 * Returns a charset object for the named charset. </p> 522 * 523 * @param charsetName 524 * The name of the requested charset; may be either 525 * a canonical name or an alias 526 * 527 * @return A charset object for the named charset 528 * 529 * @throws IllegalCharsetNameException 530 * If the given charset name is illegal 531 * 532 * @throws IllegalArgumentException 533 * If the given <tt>charsetName</tt> is null 534 * 535 * @throws UnsupportedCharsetException 536 * If no support for the named charset is available 537 * in this instance of the Java virtual machine 538 */ 539 public static Charset forName(String charsetName) { 540 Charset cs = lookup(charsetName); 541 if (cs != null) 542 return cs; 543 throw new UnsupportedCharsetException(charsetName); 544 } 545 546 // Fold charsets from the given iterator into the given map, ignoring 547 // charsets whose names already have entries in the map. 548 // 549 private static void put(Iterator<Charset> i, Map<String,Charset> m) { 550 while (i.hasNext()) { 551 Charset cs = i.next(); 552 if (!m.containsKey(cs.name())) 553 m.put(cs.name(), cs); 554 } 555 } 556 557 /** 558 * Constructs a sorted map from canonical charset names to charset objects. 559 * 560 * <p> The map returned by this method will have one entry for each charset 561 * for which support is available in the current Java virtual machine. If 562 * two or more supported charsets have the same canonical name then the 563 * resulting map will contain just one of them; which one it will contain 564 * is not specified. </p> 565 * 566 * <p> The invocation of this method, and the subsequent use of the 567 * resulting map, may cause time-consuming disk or network I/O operations 568 * to occur. This method is provided for applications that need to 569 * enumerate all of the available charsets, for example to allow user 570 * charset selection. This method is not used by the {@link #forName 571 * forName} method, which instead employs an efficient incremental lookup 572 * algorithm. 573 * 574 * <p> This method may return different results at different times if new 575 * charset providers are dynamically made available to the current Java 576 * virtual machine. In the absence of such changes, the charsets returned 577 * by this method are exactly those that can be retrieved via the {@link 578 * #forName forName} method. </p> 579 * 580 * @return An immutable, case-insensitive map from canonical charset names 581 * to charset objects 582 */ 583 public static SortedMap<String,Charset> availableCharsets() { 584 return AccessController.doPrivileged( 585 new PrivilegedAction<SortedMap<String,Charset>>() { 586 public SortedMap<String,Charset> run() { 587 TreeMap<String,Charset> m = 588 new TreeMap<String,Charset>( 589 ASCIICaseInsensitiveComparator.CASE_INSENSITIVE_ORDER); 590 put(standardProvider.charsets(), m); 591 for (Iterator i = providers(); i.hasNext();) { 592 CharsetProvider cp = (CharsetProvider)i.next(); 593 put(cp.charsets(), m); 594 } 595 return Collections.unmodifiableSortedMap(m); 596 } 597 }); 598 } 599 600 private static volatile Charset defaultCharset; 601 602 /** 603 * Returns the default charset of this Java virtual machine. 604 * 605 * <p> The default charset is determined during virtual-machine startup and 606 * typically depends upon the locale and charset of the underlying 607 * operating system. 608 * 609 * @return A charset object for the default charset 610 * 611 * @since 1.5 612 */ 613 public static Charset defaultCharset() { 614 if (defaultCharset == null) { 615 synchronized (Charset.class) { 616 String csn = AccessController.doPrivileged( 617 new GetPropertyAction("file.encoding")); 618 Charset cs = lookup(csn); 619 if (cs != null) 620 defaultCharset = cs; 621 else 622 defaultCharset = forName("UTF-8"); 623 } 624 } 625 return defaultCharset; 626 } 627 628 629 /* -- Instance fields and methods -- */ 630 631 private final String name; // tickles a bug in oldjavac 632 private final String[] aliases; // tickles a bug in oldjavac 633 private Set<String> aliasSet = null; 634 635 /** 636 * Initializes a new charset with the given canonical name and alias 637 * set. </p> 638 * 639 * @param canonicalName 640 * The canonical name of this charset 641 * 642 * @param aliases 643 * An array of this charset's aliases, or null if it has no aliases 644 * 645 * @throws IllegalCharsetNameException 646 * If the canonical name or any of the aliases are illegal 647 */ 648 protected Charset(String canonicalName, String[] aliases) { 649 checkName(canonicalName); 650 String[] as = (aliases == null) ? new String[0] : aliases; 651 for (int i = 0; i < as.length; i++) 652 checkName(as[i]); 653 this.name = canonicalName; 654 this.aliases = as; 655 } 656 657 /** 658 * Returns this charset's canonical name. </p> 659 * 660 * @return The canonical name of this charset 661 */ 662 public final String name() { 663 return name; 664 } 665 666 /** 667 * Returns a set containing this charset's aliases. </p> 668 * 669 * @return An immutable set of this charset's aliases 670 */ 671 public final Set<String> aliases() { 672 if (aliasSet != null) 673 return aliasSet; 674 int n = aliases.length; 675 HashSet<String> hs = new HashSet<String>(n); 676 for (int i = 0; i < n; i++) 677 hs.add(aliases[i]); 678 aliasSet = Collections.unmodifiableSet(hs); 679 return aliasSet; 680 } 681 682 /** 683 * Returns this charset's human-readable name for the default locale. 684 * 685 * <p> The default implementation of this method simply returns this 686 * charset's canonical name. Concrete subclasses of this class may 687 * override this method in order to provide a localized display name. </p> 688 * 689 * @return The display name of this charset in the default locale 690 */ 691 public String displayName() { 692 return name; 693 } 694 695 /** 696 * Tells whether or not this charset is registered in the <a 697 * href="http://www.iana.org/assignments/character-sets">IANA Charset 698 * Registry</a>. </p> 699 * 700 * @return <tt>true</tt> if, and only if, this charset is known by its 701 * implementor to be registered with the IANA 702 */ 703 public final boolean isRegistered() { 704 return !name.startsWith("X-") && !name.startsWith("x-"); 705 } 706 707 /** 708 * Returns this charset's human-readable name for the given locale. 709 * 710 * <p> The default implementation of this method simply returns this 711 * charset's canonical name. Concrete subclasses of this class may 712 * override this method in order to provide a localized display name. </p> 713 * 714 * @param locale 715 * The locale for which the display name is to be retrieved 716 * 717 * @return The display name of this charset in the given locale 718 */ 719 public String displayName(Locale locale) { 720 return name; 721 } 722 723 /** 724 * Tells whether or not this charset contains the given charset. 725 * 726 * <p> A charset <i>C</i> is said to <i>contain</i> a charset <i>D</i> if, 727 * and only if, every character representable in <i>D</i> is also 728 * representable in <i>C</i>. If this relationship holds then it is 729 * guaranteed that every string that can be encoded in <i>D</i> can also be 730 * encoded in <i>C</i> without performing any replacements. 731 * 732 * <p> That <i>C</i> contains <i>D</i> does not imply that each character 733 * representable in <i>C</i> by a particular byte sequence is represented 734 * in <i>D</i> by the same byte sequence, although sometimes this is the 735 * case. 736 * 737 * <p> Every charset contains itself. 738 * 739 * <p> This method computes an approximation of the containment relation: 740 * If it returns <tt>true</tt> then the given charset is known to be 741 * contained by this charset; if it returns <tt>false</tt>, however, then 742 * it is not necessarily the case that the given charset is not contained 743 * in this charset. 744 * 745 * @return <tt>true</tt> if the given charset is contained in this charset 746 */ 747 public abstract boolean contains(Charset cs); 748 749 /** 750 * Constructs a new decoder for this charset. </p> 751 * 752 * @return A new decoder for this charset 753 */ 754 public abstract CharsetDecoder newDecoder(); 755 756 /** 757 * Constructs a new encoder for this charset. </p> 758 * 759 * @return A new encoder for this charset 760 * 761 * @throws UnsupportedOperationException 762 * If this charset does not support encoding 763 */ 764 public abstract CharsetEncoder newEncoder(); 765 766 /** 767 * Tells whether or not this charset supports encoding. 768 * 769 * <p> Nearly all charsets support encoding. The primary exceptions are 770 * special-purpose <i>auto-detect</i> charsets whose decoders can determine 771 * which of several possible encoding schemes is in use by examining the 772 * input byte sequence. Such charsets do not support encoding because 773 * there is no way to determine which encoding should be used on output. 774 * Implementations of such charsets should override this method to return 775 * <tt>false</tt>. </p> 776 * 777 * @return <tt>true</tt> if, and only if, this charset supports encoding 778 */ 779 public boolean canEncode() { 780 return true; 781 } 782 783 /** 784 * Convenience method that decodes bytes in this charset into Unicode 785 * characters. 786 * 787 * <p> An invocation of this method upon a charset <tt>cs</tt> returns the 788 * same result as the expression 789 * 790 * <pre> 791 * cs.newDecoder() 792 * .onMalformedInput(CodingErrorAction.REPLACE) 793 * .onUnmappableCharacter(CodingErrorAction.REPLACE) 794 * .decode(bb); </pre> 795 * 796 * except that it is potentially more efficient because it can cache 797 * decoders between successive invocations. 798 * 799 * <p> This method always replaces malformed-input and unmappable-character 800 * sequences with this charset's default replacement byte array. In order 801 * to detect such sequences, use the {@link 802 * CharsetDecoder#decode(java.nio.ByteBuffer)} method directly. </p> 803 * 804 * @param bb The byte buffer to be decoded 805 * 806 * @return A char buffer containing the decoded characters 807 */ 808 public final CharBuffer decode(ByteBuffer bb) { 809 try { 810 return ThreadLocalCoders.decoderFor(this) 811 .onMalformedInput(CodingErrorAction.REPLACE) 812 .onUnmappableCharacter(CodingErrorAction.REPLACE) 813 .decode(bb); 814 } catch (CharacterCodingException x) { 815 throw new Error(x); // Can't happen 816 } 817 } 818 819 /** 820 * Convenience method that encodes Unicode characters into bytes in this 821 * charset. 822 * 823 * <p> An invocation of this method upon a charset <tt>cs</tt> returns the 824 * same result as the expression 825 * 826 * <pre> 827 * cs.newEncoder() 828 * .onMalformedInput(CodingErrorAction.REPLACE) 829 * .onUnmappableCharacter(CodingErrorAction.REPLACE) 830 * .encode(bb); </pre> 831 * 832 * except that it is potentially more efficient because it can cache 833 * encoders between successive invocations. 834 * 835 * <p> This method always replaces malformed-input and unmappable-character 836 * sequences with this charset's default replacement string. In order to 837 * detect such sequences, use the {@link 838 * CharsetEncoder#encode(java.nio.CharBuffer)} method directly. </p> 839 * 840 * @param cb The char buffer to be encoded 841 * 842 * @return A byte buffer containing the encoded characters 843 */ 844 public final ByteBuffer encode(CharBuffer cb) { 845 try { 846 return ThreadLocalCoders.encoderFor(this) 847 .onMalformedInput(CodingErrorAction.REPLACE) 848 .onUnmappableCharacter(CodingErrorAction.REPLACE) 849 .encode(cb); 850 } catch (CharacterCodingException x) { 851 throw new Error(x); // Can't happen 852 } 853 } 854 855 /** 856 * Convenience method that encodes a string into bytes in this charset. 857 * 858 * <p> An invocation of this method upon a charset <tt>cs</tt> returns the 859 * same result as the expression 860 * 861 * <pre> 862 * cs.encode(CharBuffer.wrap(s)); </pre> 863 * 864 * @param str The string to be encoded 865 * 866 * @return A byte buffer containing the encoded characters 867 */ 868 public final ByteBuffer encode(String str) { 869 return encode(CharBuffer.wrap(str)); 870 } 871 872 /** 873 * Compares this charset to another. 874 * 875 * <p> Charsets are ordered by their canonical names, without regard to 876 * case. </p> 877 * 878 * @param that 879 * The charset to which this charset is to be compared 880 * 881 * @return A negative integer, zero, or a positive integer as this charset 882 * is less than, equal to, or greater than the specified charset 883 */ 884 public final int compareTo(Charset that) { 885 return (name().compareToIgnoreCase(that.name())); 886 } 887 888 /** 889 * Computes a hashcode for this charset. </p> 890 * 891 * @return An integer hashcode 892 */ 893 public final int hashCode() { 894 return name().hashCode(); 895 } 896 897 /** 898 * Tells whether or not this object is equal to another. 899 * 900 * <p> Two charsets are equal if, and only if, they have the same canonical 901 * names. A charset is never equal to any other type of object. </p> 902 * 903 * @return <tt>true</tt> if, and only if, this charset is equal to the 904 * given object 905 */ 906 public final boolean equals(Object ob) { 907 if (!(ob instanceof Charset)) 908 return false; 909 if (this == ob) 910 return true; 911 return name.equals(((Charset)ob).name()); 912 } 913 914 /** 915 * Returns a string describing this charset. </p> 916 * 917 * @return A string describing this charset 918 */ 919 public final String toString() { 920 return name(); 921 } 922 923 }