1 /* 2 * Copyright (c) 2000, 2020, 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 jdk.internal.misc.VM; 29 import sun.nio.cs.ThreadLocalCoders; 30 import sun.security.action.GetPropertyAction; 31 32 import java.nio.ByteBuffer; 33 import java.nio.CharBuffer; 34 import java.nio.charset.spi.CharsetProvider; 35 import java.security.AccessController; 36 import java.security.PrivilegedAction; 37 import java.util.Arrays; 38 import java.util.Collections; 39 import java.util.HashSet; 40 import java.util.Iterator; 41 import java.util.Locale; 42 import java.util.Map; 43 import java.util.NoSuchElementException; 44 import java.util.Objects; 45 import java.util.ServiceConfigurationError; 46 import java.util.ServiceLoader; 47 import java.util.Set; 48 import java.util.SortedMap; 49 import java.util.TreeMap; 50 51 52 /** 53 * A named mapping between sequences of sixteen-bit Unicode <a 54 * href="../../lang/Character.html#unicode">code units</a> and sequences of 55 * bytes. This class defines methods for creating decoders and encoders and 56 * for retrieving the various names associated with a charset. Instances of 57 * this class are immutable. 58 * 59 * <p> This class also defines static methods for testing whether a particular 60 * charset is supported, for locating charset instances by name, and for 61 * constructing a map that contains every charset for which support is 62 * available in the current Java virtual machine. Support for new charsets can 63 * be added via the service-provider interface defined in the {@link 64 * java.nio.charset.spi.CharsetProvider} class. 65 * 66 * <p> All of the methods defined in this class are safe for use by multiple 67 * concurrent threads. 68 * 69 * 70 * <h2><a id="names">Charset names</a></h2> 71 * 72 * <p> Charsets are named by strings composed of the following characters: 73 * 74 * <ul> 75 * 76 * <li> The uppercase letters {@code 'A'} through {@code 'Z'} 77 * (<code>'\u0041'</code> through <code>'\u005a'</code>), 78 * 79 * <li> The lowercase letters {@code 'a'} through {@code 'z'} 80 * (<code>'\u0061'</code> through <code>'\u007a'</code>), 81 * 82 * <li> The digits {@code '0'} through {@code '9'} 83 * (<code>'\u0030'</code> through <code>'\u0039'</code>), 84 * 85 * <li> The dash character {@code '-'} 86 * (<code>'\u002d'</code>, <small>HYPHEN-MINUS</small>), 87 * 88 * <li> The plus character {@code '+'} 89 * (<code>'\u002b'</code>, <small>PLUS SIGN</small>), 90 * 91 * <li> The period character {@code '.'} 92 * (<code>'\u002e'</code>, <small>FULL STOP</small>), 93 * 94 * <li> The colon character {@code ':'} 95 * (<code>'\u003a'</code>, <small>COLON</small>), and 96 * 97 * <li> The underscore character {@code '_'} 98 * (<code>'\u005f'</code>, <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 id="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 {@code getEncoding()} methods of the 119 * {@link java.io.InputStreamReader#getEncoding InputStreamReader} and {@link 120 * java.io.OutputStreamWriter#getEncoding OutputStreamWriter} classes. 121 * 122 * <p><a id="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 {@code "X-"} or {@code "x-"}. 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><a id="standard">Standard charsets</a></h2> 141 * 142 * 143 * <p> Every implementation of the Java platform is required to support the 144 * following standard charsets. 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 class="striped" style="width:80%"> 149 * <caption style="display:none">Description of standard charsets</caption> 150 * <thead> 151 * <tr><th scope="col" style="text-align:left">Charset</th><th scope="col" style="text-align:left">Description</th></tr> 152 * </thead> 153 * <tbody> 154 * <tr><th scope="row" style="vertical-align:top">{@code US-ASCII}</th> 155 * <td>Seven-bit ASCII, a.k.a. {@code ISO646-US}, 156 * a.k.a. the Basic Latin block of the Unicode character set</td></tr> 157 * <tr><th scope="row" style="vertical-align:top"><code>ISO-8859-1 </code></th> 158 * <td>ISO Latin Alphabet No. 1, a.k.a. {@code ISO-LATIN-1}</td></tr> 159 * <tr><th scope="row" style="vertical-align:top">{@code UTF-8}</th> 160 * <td>Eight-bit UCS Transformation Format</td></tr> 161 * <tr><th scope="row" style="vertical-align:top">{@code UTF-16BE}</th> 162 * <td>Sixteen-bit UCS Transformation Format, 163 * big-endian byte order</td></tr> 164 * <tr><th scope="row" style="vertical-align:top">{@code UTF-16LE}</th> 165 * <td>Sixteen-bit UCS Transformation Format, 166 * little-endian byte order</td></tr> 167 * <tr><th scope="row" style="vertical-align:top">{@code UTF-16}</th> 168 * <td>Sixteen-bit UCS Transformation Format, 169 * byte order identified by an optional byte-order mark</td></tr> 170 * </tbody> 171 * </table></blockquote> 172 * 173 * <p> The {@code UTF-8} 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 {@code UTF-16} 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 {@code UTF-16} 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 <code>'\uFEFF'</code>. Byte-order marks are handled 191 * as follows: 192 * 193 * <ul> 194 * 195 * <li><p> When decoding, the {@code UTF-16BE} and {@code UTF-16LE} 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 * <li><p> When decoding, the {@code UTF-16} charset interprets the 201 * byte-order mark at the beginning of the input stream to indicate the 202 * byte-order of the stream but defaults to big-endian if there is no 203 * byte-order mark; when encoding, it uses big-endian byte order and writes 204 * a big-endian byte-order mark. </p></li> 205 * 206 * </ul> 207 * 208 * In any case, byte order marks occurring after the first element of an 209 * input sequence are not omitted since the same code is used to represent 210 * <small>ZERO-WIDTH NON-BREAKING SPACE</small>. 211 * 212 * <p> Every instance of the Java virtual machine has a default charset, which 213 * may or may not be one of the standard charsets. The default charset is 214 * determined during virtual-machine startup and typically depends upon the 215 * locale and charset being used by the underlying operating system. </p> 216 * 217 * <p> The {@link StandardCharsets} class defines constants for each of the 218 * standard charsets. 219 * 220 * <h2>Terminology</h2> 221 * 222 * <p> The name of this class is taken from the terms used in 223 * <a href="http://www.ietf.org/rfc/rfc2278.txt"><i>RFC 2278</i></a>. 224 * In that document a <i>charset</i> is defined as the combination of 225 * one or more coded character sets and a character-encoding scheme. 226 * (This definition is confusing; some other software systems define 227 * <i>charset</i> as a synonym for <i>coded character set</i>.) 228 * 229 * <p> A <i>coded character set</i> is a mapping between a set of abstract 230 * characters and a set of integers. US-ASCII, ISO 8859-1, 231 * JIS X 0201, and Unicode are examples of coded character sets. 232 * 233 * <p> Some standards have defined a <i>character set</i> to be simply a 234 * set of abstract characters without an associated assigned numbering. 235 * An alphabet is an example of such a character set. However, the subtle 236 * distinction between <i>character set</i> and <i>coded character set</i> 237 * is rarely used in practice; the former has become a short form for the 238 * latter, including in the Java API specification. 239 * 240 * <p> A <i>character-encoding scheme</i> is a mapping between one or more 241 * coded character sets and a set of octet (eight-bit byte) sequences. 242 * UTF-8, UTF-16, ISO 2022, and EUC are examples of 243 * character-encoding schemes. Encoding schemes are often associated with 244 * a particular coded character set; UTF-8, for example, is used only to 245 * encode Unicode. Some schemes, however, are associated with multiple 246 * coded character sets; EUC, for example, can be used to encode 247 * characters in a variety of Asian coded character sets. 248 * 249 * <p> When a coded character set is used exclusively with a single 250 * character-encoding scheme then the corresponding charset is usually 251 * named for the coded character set; otherwise a charset is usually named 252 * for the encoding scheme and, possibly, the locale of the coded 253 * character sets that it supports. Hence {@code US-ASCII} is both the 254 * name of a coded character set and of the charset that encodes it, while 255 * {@code EUC-JP} is the name of the charset that encodes the 256 * JIS X 0201, JIS X 0208, and JIS X 0212 257 * coded character sets for the Japanese language. 258 * 259 * <p> The native character encoding of the Java programming language is 260 * UTF-16. A charset in the Java platform therefore defines a mapping 261 * between sequences of sixteen-bit UTF-16 code units (that is, sequences 262 * of chars) and sequences of bytes. </p> 263 * 264 * 265 * @author Mark Reinhold 266 * @author JSR-51 Expert Group 267 * @since 1.4 268 * 269 * @see CharsetDecoder 270 * @see CharsetEncoder 271 * @see java.nio.charset.spi.CharsetProvider 272 * @see java.lang.Character 273 */ 274 275 public abstract class Charset 276 implements Comparable<Charset> 277 { 278 279 /* -- Static methods -- */ 280 281 /** 282 * Checks that the given string is a legal charset name. </p> 283 * 284 * @param s 285 * A purported charset name 286 * 287 * @throws IllegalCharsetNameException 288 * If the given name is not a legal charset name 289 */ checkName(String s)290 private static void checkName(String s) { 291 int n = s.length(); 292 if (n == 0) { 293 throw new IllegalCharsetNameException(s); 294 } 295 for (int i = 0; i < n; i++) { 296 char c = s.charAt(i); 297 if (c >= 'A' && c <= 'Z') continue; 298 if (c >= 'a' && c <= 'z') continue; 299 if (c >= '0' && c <= '9') continue; 300 if (c == '-' && i != 0) continue; 301 if (c == '+' && i != 0) continue; 302 if (c == ':' && i != 0) continue; 303 if (c == '_' && i != 0) continue; 304 if (c == '.' && i != 0) continue; 305 throw new IllegalCharsetNameException(s); 306 } 307 } 308 309 /* The standard set of charsets */ 310 private static final CharsetProvider standardProvider 311 = new sun.nio.cs.StandardCharsets(); 312 313 private static final String[] zeroAliases = new String[0]; 314 315 // Cache of the most-recently-returned charsets, 316 // along with the names that were used to find them 317 // 318 private static volatile Object[] cache1; // "Level 1" cache 319 private static volatile Object[] cache2; // "Level 2" cache 320 cache(String charsetName, Charset cs)321 private static void cache(String charsetName, Charset cs) { 322 cache2 = cache1; 323 cache1 = new Object[] { charsetName, cs }; 324 } 325 326 // Creates an iterator that walks over the available providers, ignoring 327 // those whose lookup or instantiation causes a security exception to be 328 // thrown. Should be invoked with full privileges. 329 // providers()330 private static Iterator<CharsetProvider> providers() { 331 return new Iterator<>() { 332 ClassLoader cl = ClassLoader.getSystemClassLoader(); 333 ServiceLoader<CharsetProvider> sl = 334 ServiceLoader.load(CharsetProvider.class, cl); 335 Iterator<CharsetProvider> i = sl.iterator(); 336 CharsetProvider next = null; 337 338 private boolean getNext() { 339 while (next == null) { 340 try { 341 if (!i.hasNext()) 342 return false; 343 next = i.next(); 344 } catch (ServiceConfigurationError sce) { 345 if (sce.getCause() instanceof SecurityException) { 346 // Ignore security exceptions 347 continue; 348 } 349 throw sce; 350 } 351 } 352 return true; 353 } 354 355 public boolean hasNext() { 356 return getNext(); 357 } 358 359 public CharsetProvider next() { 360 if (!getNext()) 361 throw new NoSuchElementException(); 362 CharsetProvider n = next; 363 next = null; 364 return n; 365 } 366 367 public void remove() { 368 throw new UnsupportedOperationException(); 369 } 370 371 }; 372 } 373 374 // Thread-local gate to prevent recursive provider lookups 375 private static ThreadLocal<ThreadLocal<?>> gate = 376 new ThreadLocal<ThreadLocal<?>>(); 377 lookupViaProviders(final String charsetName)378 private static Charset lookupViaProviders(final String charsetName) { 379 380 // The runtime startup sequence looks up standard charsets as a 381 // consequence of the VM's invocation of System.initializeSystemClass 382 // in order to, e.g., set system properties and encode filenames. At 383 // that point the application class loader has not been initialized, 384 // however, so we can't look for providers because doing so will cause 385 // that loader to be prematurely initialized with incomplete 386 // information. 387 // 388 if (!VM.isBooted()) 389 return null; 390 391 if (gate.get() != null) 392 // Avoid recursive provider lookups 393 return null; 394 try { 395 gate.set(gate); 396 397 return AccessController.doPrivileged( 398 new PrivilegedAction<>() { 399 public Charset run() { 400 for (Iterator<CharsetProvider> i = providers(); 401 i.hasNext();) { 402 CharsetProvider cp = i.next(); 403 Charset cs = cp.charsetForName(charsetName); 404 if (cs != null) 405 return cs; 406 } 407 return null; 408 } 409 }); 410 411 } finally { 412 gate.set(null); 413 } 414 } 415 416 /* The extended set of charsets */ 417 private static class ExtendedProviderHolder { 418 static final CharsetProvider[] extendedProviders = extendedProviders(); 419 // returns ExtendedProvider, if installed 420 private static CharsetProvider[] extendedProviders() { 421 return AccessController.doPrivileged(new PrivilegedAction<>() { 422 public CharsetProvider[] run() { 423 CharsetProvider[] cps = new CharsetProvider[1]; 424 int n = 0; 425 ServiceLoader<CharsetProvider> sl = 426 ServiceLoader.loadInstalled(CharsetProvider.class); 427 for (CharsetProvider cp : sl) { 428 if (n + 1 > cps.length) { 429 cps = Arrays.copyOf(cps, cps.length << 1); 430 } 431 cps[n++] = cp; 432 } 433 return n == cps.length ? cps : Arrays.copyOf(cps, n); 434 }}); 435 } 436 } 437 438 private static Charset lookupExtendedCharset(String charsetName) { 439 if (!VM.isBooted()) // see lookupViaProviders() 440 return null; 441 CharsetProvider[] ecps = ExtendedProviderHolder.extendedProviders; 442 for (CharsetProvider cp : ecps) { 443 Charset cs = cp.charsetForName(charsetName); 444 if (cs != null) 445 return cs; 446 } 447 return null; 448 } 449 450 private static Charset lookup(String charsetName) { 451 if (charsetName == null) 452 throw new IllegalArgumentException("Null charset name"); 453 Object[] a; 454 if ((a = cache1) != null && charsetName.equals(a[0])) 455 return (Charset)a[1]; 456 // We expect most programs to use one Charset repeatedly. 457 // We convey a hint to this effect to the VM by putting the 458 // level 1 cache miss code in a separate method. 459 return lookup2(charsetName); 460 } 461 462 private static Charset lookup2(String charsetName) { 463 Object[] a; 464 if ((a = cache2) != null && charsetName.equals(a[0])) { 465 cache2 = cache1; 466 cache1 = a; 467 return (Charset)a[1]; 468 } 469 Charset cs; 470 if ((cs = standardProvider.charsetForName(charsetName)) != null || 471 (cs = lookupExtendedCharset(charsetName)) != null || 472 (cs = lookupViaProviders(charsetName)) != null) 473 { 474 cache(charsetName, cs); 475 return cs; 476 } 477 478 /* Only need to check the name if we didn't find a charset for it */ 479 checkName(charsetName); 480 return null; 481 } 482 483 /** 484 * Tells whether the named charset is supported. 485 * 486 * @param charsetName 487 * The name of the requested charset; may be either 488 * a canonical name or an alias 489 * 490 * @return {@code true} if, and only if, support for the named charset 491 * is available in the current Java virtual machine 492 * 493 * @throws IllegalCharsetNameException 494 * If the given charset name is illegal 495 * 496 * @throws IllegalArgumentException 497 * If the given {@code charsetName} is null 498 */ 499 public static boolean isSupported(String charsetName) { 500 return (lookup(charsetName) != null); 501 } 502 503 /** 504 * Returns a charset object for the named charset. 505 * 506 * @param charsetName 507 * The name of the requested charset; may be either 508 * a canonical name or an alias 509 * 510 * @return A charset object for the named charset 511 * 512 * @throws IllegalCharsetNameException 513 * If the given charset name is illegal 514 * 515 * @throws IllegalArgumentException 516 * If the given {@code charsetName} is null 517 * 518 * @throws UnsupportedCharsetException 519 * If no support for the named charset is available 520 * in this instance of the Java virtual machine 521 */ 522 public static Charset forName(String charsetName) { 523 Charset cs = lookup(charsetName); 524 if (cs != null) 525 return cs; 526 throw new UnsupportedCharsetException(charsetName); 527 } 528 529 // Fold charsets from the given iterator into the given map, ignoring 530 // charsets whose names already have entries in the map. 531 // 532 private static void put(Iterator<Charset> i, Map<String,Charset> m) { 533 while (i.hasNext()) { 534 Charset cs = i.next(); 535 if (!m.containsKey(cs.name())) 536 m.put(cs.name(), cs); 537 } 538 } 539 540 /** 541 * Constructs a sorted map from canonical charset names to charset objects. 542 * 543 * <p> The map returned by this method will have one entry for each charset 544 * for which support is available in the current Java virtual machine. If 545 * two or more supported charsets have the same canonical name then the 546 * resulting map will contain just one of them; which one it will contain 547 * is not specified. </p> 548 * 549 * <p> The invocation of this method, and the subsequent use of the 550 * resulting map, may cause time-consuming disk or network I/O operations 551 * to occur. This method is provided for applications that need to 552 * enumerate all of the available charsets, for example to allow user 553 * charset selection. This method is not used by the {@link #forName 554 * forName} method, which instead employs an efficient incremental lookup 555 * algorithm. 556 * 557 * <p> This method may return different results at different times if new 558 * charset providers are dynamically made available to the current Java 559 * virtual machine. In the absence of such changes, the charsets returned 560 * by this method are exactly those that can be retrieved via the {@link 561 * #forName forName} method. </p> 562 * 563 * @return An immutable, case-insensitive map from canonical charset names 564 * to charset objects 565 */ 566 public static SortedMap<String,Charset> availableCharsets() { 567 return AccessController.doPrivileged( 568 new PrivilegedAction<>() { 569 public SortedMap<String,Charset> run() { 570 TreeMap<String,Charset> m = 571 new TreeMap<>( 572 String.CASE_INSENSITIVE_ORDER); 573 put(standardProvider.charsets(), m); 574 CharsetProvider[] ecps = ExtendedProviderHolder.extendedProviders; 575 for (CharsetProvider ecp :ecps) { 576 put(ecp.charsets(), m); 577 } 578 for (Iterator<CharsetProvider> i = providers(); i.hasNext();) { 579 CharsetProvider cp = i.next(); 580 put(cp.charsets(), m); 581 } 582 return Collections.unmodifiableSortedMap(m); 583 } 584 }); 585 } 586 587 private static volatile Charset defaultCharset; 588 589 /** 590 * Returns the default charset of this Java virtual machine. 591 * 592 * <p> The default charset is determined during virtual-machine startup and 593 * typically depends upon the locale and charset of the underlying 594 * operating system. 595 * 596 * @return A charset object for the default charset 597 * 598 * @since 1.5 599 */ 600 public static Charset defaultCharset() { 601 if (defaultCharset == null) { 602 synchronized (Charset.class) { 603 String csn = GetPropertyAction 604 .privilegedGetProperty("file.encoding"); 605 Charset cs = lookup(csn); 606 if (cs != null) 607 defaultCharset = cs; 608 else 609 defaultCharset = sun.nio.cs.UTF_8.INSTANCE; 610 } 611 } 612 return defaultCharset; 613 } 614 615 616 /* -- Instance fields and methods -- */ 617 618 private final String name; // tickles a bug in oldjavac 619 private final String[] aliases; // tickles a bug in oldjavac 620 private Set<String> aliasSet = null; 621 622 /** 623 * Initializes a new charset with the given canonical name and alias 624 * set. 625 * 626 * @param canonicalName 627 * The canonical name of this charset 628 * 629 * @param aliases 630 * An array of this charset's aliases, or null if it has no aliases 631 * 632 * @throws IllegalCharsetNameException 633 * If the canonical name or any of the aliases are illegal 634 */ 635 protected Charset(String canonicalName, String[] aliases) { 636 String[] as = Objects.requireNonNullElse(aliases, zeroAliases); 637 638 // Skip checks for the standard, built-in Charsets we always load 639 // during initialization. 640 if (canonicalName != "ISO-8859-1" 641 && canonicalName != "US-ASCII" 642 && canonicalName != "UTF-8") { 643 checkName(canonicalName); 644 for (int i = 0; i < as.length; i++) { 645 checkName(as[i]); 646 } 647 } 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 {@code true} 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 {@code true} then the given charset is known to be 736 * contained by this charset; if it returns {@code false}, 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 {@code true} 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 * {@code false}. </p> 774 * 775 * @return {@code true} 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 {@code cs} 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 {@code cs} 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 {@code cs} 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 {@code true} 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 } 922