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