J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 1996-2006 Sun Microsystems, Inc. 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. Sun designates this |
| 8 | * particular file as subject to the "Classpath" exception as provided |
| 9 | * by Sun 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 Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 22 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 23 | * have any questions. |
| 24 | */ |
| 25 | |
| 26 | /* |
| 27 | * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved |
| 28 | * (C) Copyright IBM Corp. 1996 - 1998 - All Rights Reserved |
| 29 | * |
| 30 | * The original version of this source code and documentation |
| 31 | * is copyrighted and owned by Taligent, Inc., a wholly-owned |
| 32 | * subsidiary of IBM. These materials are provided under terms |
| 33 | * of a License Agreement between Taligent and Sun. This technology |
| 34 | * is protected by multiple US and International patents. |
| 35 | * |
| 36 | * This notice and attribution to Taligent may not be removed. |
| 37 | * Taligent is a registered trademark of Taligent, Inc. |
| 38 | * |
| 39 | */ |
| 40 | |
| 41 | package java.text; |
| 42 | |
| 43 | import java.lang.ref.SoftReference; |
| 44 | import java.net.URL; |
| 45 | import java.io.InputStream; |
| 46 | import java.io.IOException; |
| 47 | import java.security.AccessController; |
| 48 | import java.security.PrivilegedAction; |
| 49 | import java.text.CharacterIterator; |
| 50 | import java.text.StringCharacterIterator; |
| 51 | import java.text.spi.BreakIteratorProvider; |
| 52 | import java.util.Locale; |
| 53 | import java.util.MissingResourceException; |
| 54 | import java.util.ResourceBundle; |
| 55 | import java.util.spi.LocaleServiceProvider; |
| 56 | import sun.util.LocaleServiceProviderPool; |
| 57 | import sun.util.resources.LocaleData; |
| 58 | |
| 59 | |
| 60 | /** |
| 61 | * The <code>BreakIterator</code> class implements methods for finding |
| 62 | * the location of boundaries in text. Instances of <code>BreakIterator</code> |
| 63 | * maintain a current position and scan over text |
| 64 | * returning the index of characters where boundaries occur. |
| 65 | * Internally, <code>BreakIterator</code> scans text using a |
| 66 | * <code>CharacterIterator</code>, and is thus able to scan text held |
| 67 | * by any object implementing that protocol. A <code>StringCharacterIterator</code> |
| 68 | * is used to scan <code>String</code> objects passed to <code>setText</code>. |
| 69 | * |
| 70 | * <p> |
| 71 | * You use the factory methods provided by this class to create |
| 72 | * instances of various types of break iterators. In particular, |
| 73 | * use <code>getWordInstance</code>, <code>getLineInstance</code>, |
| 74 | * <code>getSentenceInstance</code>, and <code>getCharacterInstance</code> |
| 75 | * to create <code>BreakIterator</code>s that perform |
| 76 | * word, line, sentence, and character boundary analysis respectively. |
| 77 | * A single <code>BreakIterator</code> can work only on one unit |
| 78 | * (word, line, sentence, and so on). You must use a different iterator |
| 79 | * for each unit boundary analysis you wish to perform. |
| 80 | * |
| 81 | * <p><a name="line"></a> |
| 82 | * Line boundary analysis determines where a text string can be |
| 83 | * broken when line-wrapping. The mechanism correctly handles |
| 84 | * punctuation and hyphenated words. Actual line breaking needs |
| 85 | * to also consider the available line width and is handled by |
| 86 | * higher-level software. |
| 87 | * |
| 88 | * <p><a name="sentence"></a> |
| 89 | * Sentence boundary analysis allows selection with correct interpretation |
| 90 | * of periods within numbers and abbreviations, and trailing punctuation |
| 91 | * marks such as quotation marks and parentheses. |
| 92 | * |
| 93 | * <p><a name="word"></a> |
| 94 | * Word boundary analysis is used by search and replace functions, as |
| 95 | * well as within text editing applications that allow the user to |
| 96 | * select words with a double click. Word selection provides correct |
| 97 | * interpretation of punctuation marks within and following |
| 98 | * words. Characters that are not part of a word, such as symbols |
| 99 | * or punctuation marks, have word-breaks on both sides. |
| 100 | * |
| 101 | * <p><a name="character"></a> |
| 102 | * Character boundary analysis allows users to interact with characters |
| 103 | * as they expect to, for example, when moving the cursor through a text |
| 104 | * string. Character boundary analysis provides correct navigation |
| 105 | * through character strings, regardless of how the character is stored. |
| 106 | * The boundaries returned may be those of supplementary characters, |
| 107 | * combining character sequences, or ligature clusters. |
| 108 | * For example, an accented character might be stored as a base character |
| 109 | * and a diacritical mark. What users consider to be a character can |
| 110 | * differ between languages. |
| 111 | * |
| 112 | * <p> |
| 113 | * The <code>BreakIterator</code> instances returned by the factory methods |
| 114 | * of this class are intended for use with natural languages only, not for |
| 115 | * programming language text. It is however possible to define subclasses |
| 116 | * that tokenize a programming language. |
| 117 | * |
| 118 | * <P> |
| 119 | * <strong>Examples</strong>:<P> |
| 120 | * Creating and using text boundaries: |
| 121 | * <blockquote> |
| 122 | * <pre> |
| 123 | * public static void main(String args[]) { |
| 124 | * if (args.length == 1) { |
| 125 | * String stringToExamine = args[0]; |
| 126 | * //print each word in order |
| 127 | * BreakIterator boundary = BreakIterator.getWordInstance(); |
| 128 | * boundary.setText(stringToExamine); |
| 129 | * printEachForward(boundary, stringToExamine); |
| 130 | * //print each sentence in reverse order |
| 131 | * boundary = BreakIterator.getSentenceInstance(Locale.US); |
| 132 | * boundary.setText(stringToExamine); |
| 133 | * printEachBackward(boundary, stringToExamine); |
| 134 | * printFirst(boundary, stringToExamine); |
| 135 | * printLast(boundary, stringToExamine); |
| 136 | * } |
| 137 | * } |
| 138 | * </pre> |
| 139 | * </blockquote> |
| 140 | * |
| 141 | * Print each element in order: |
| 142 | * <blockquote> |
| 143 | * <pre> |
| 144 | * public static void printEachForward(BreakIterator boundary, String source) { |
| 145 | * int start = boundary.first(); |
| 146 | * for (int end = boundary.next(); |
| 147 | * end != BreakIterator.DONE; |
| 148 | * start = end, end = boundary.next()) { |
| 149 | * System.out.println(source.substring(start,end)); |
| 150 | * } |
| 151 | * } |
| 152 | * </pre> |
| 153 | * </blockquote> |
| 154 | * |
| 155 | * Print each element in reverse order: |
| 156 | * <blockquote> |
| 157 | * <pre> |
| 158 | * public static void printEachBackward(BreakIterator boundary, String source) { |
| 159 | * int end = boundary.last(); |
| 160 | * for (int start = boundary.previous(); |
| 161 | * start != BreakIterator.DONE; |
| 162 | * end = start, start = boundary.previous()) { |
| 163 | * System.out.println(source.substring(start,end)); |
| 164 | * } |
| 165 | * } |
| 166 | * </pre> |
| 167 | * </blockquote> |
| 168 | * |
| 169 | * Print first element: |
| 170 | * <blockquote> |
| 171 | * <pre> |
| 172 | * public static void printFirst(BreakIterator boundary, String source) { |
| 173 | * int start = boundary.first(); |
| 174 | * int end = boundary.next(); |
| 175 | * System.out.println(source.substring(start,end)); |
| 176 | * } |
| 177 | * </pre> |
| 178 | * </blockquote> |
| 179 | * |
| 180 | * Print last element: |
| 181 | * <blockquote> |
| 182 | * <pre> |
| 183 | * public static void printLast(BreakIterator boundary, String source) { |
| 184 | * int end = boundary.last(); |
| 185 | * int start = boundary.previous(); |
| 186 | * System.out.println(source.substring(start,end)); |
| 187 | * } |
| 188 | * </pre> |
| 189 | * </blockquote> |
| 190 | * |
| 191 | * Print the element at a specified position: |
| 192 | * <blockquote> |
| 193 | * <pre> |
| 194 | * public static void printAt(BreakIterator boundary, int pos, String source) { |
| 195 | * int end = boundary.following(pos); |
| 196 | * int start = boundary.previous(); |
| 197 | * System.out.println(source.substring(start,end)); |
| 198 | * } |
| 199 | * </pre> |
| 200 | * </blockquote> |
| 201 | * |
| 202 | * Find the next word: |
| 203 | * <blockquote> |
| 204 | * <pre> |
| 205 | * public static int nextWordStartAfter(int pos, String text) { |
| 206 | * BreakIterator wb = BreakIterator.getWordInstance(); |
| 207 | * wb.setText(text); |
| 208 | * int last = wb.following(pos); |
| 209 | * int current = wb.next(); |
| 210 | * while (current != BreakIterator.DONE) { |
| 211 | * for (int p = last; p < current; p++) { |
| 212 | * if (Character.isLetter(text.codePointAt(p))) |
| 213 | * return last; |
| 214 | * } |
| 215 | * last = current; |
| 216 | * current = wb.next(); |
| 217 | * } |
| 218 | * return BreakIterator.DONE; |
| 219 | * } |
| 220 | * </pre> |
| 221 | * (The iterator returned by BreakIterator.getWordInstance() is unique in that |
| 222 | * the break positions it returns don't represent both the start and end of the |
| 223 | * thing being iterated over. That is, a sentence-break iterator returns breaks |
| 224 | * that each represent the end of one sentence and the beginning of the next. |
| 225 | * With the word-break iterator, the characters between two boundaries might be a |
| 226 | * word, or they might be the punctuation or whitespace between two words. The |
| 227 | * above code uses a simple heuristic to determine which boundary is the beginning |
| 228 | * of a word: If the characters between this boundary and the next boundary |
| 229 | * include at least one letter (this can be an alphabetical letter, a CJK ideograph, |
| 230 | * a Hangul syllable, a Kana character, etc.), then the text between this boundary |
| 231 | * and the next is a word; otherwise, it's the material between words.) |
| 232 | * </blockquote> |
| 233 | * |
| 234 | * @see CharacterIterator |
| 235 | * |
| 236 | */ |
| 237 | |
| 238 | public abstract class BreakIterator implements Cloneable |
| 239 | { |
| 240 | /** |
| 241 | * Constructor. BreakIterator is stateless and has no default behavior. |
| 242 | */ |
| 243 | protected BreakIterator() |
| 244 | { |
| 245 | } |
| 246 | |
| 247 | /** |
| 248 | * Create a copy of this iterator |
| 249 | * @return A copy of this |
| 250 | */ |
| 251 | public Object clone() |
| 252 | { |
| 253 | try { |
| 254 | return super.clone(); |
| 255 | } |
| 256 | catch (CloneNotSupportedException e) { |
| 257 | throw new InternalError(); |
| 258 | } |
| 259 | } |
| 260 | |
| 261 | /** |
| 262 | * DONE is returned by previous(), next(), next(int), preceding(int) |
| 263 | * and following(int) when either the first or last text boundary has been |
| 264 | * reached. |
| 265 | */ |
| 266 | public static final int DONE = -1; |
| 267 | |
| 268 | /** |
| 269 | * Returns the first boundary. The iterator's current position is set |
| 270 | * to the first text boundary. |
| 271 | * @return The character index of the first text boundary. |
| 272 | */ |
| 273 | public abstract int first(); |
| 274 | |
| 275 | /** |
| 276 | * Returns the last boundary. The iterator's current position is set |
| 277 | * to the last text boundary. |
| 278 | * @return The character index of the last text boundary. |
| 279 | */ |
| 280 | public abstract int last(); |
| 281 | |
| 282 | /** |
| 283 | * Returns the nth boundary from the current boundary. If either |
| 284 | * the first or last text boundary has been reached, it returns |
| 285 | * <code>BreakIterator.DONE</code> and the current position is set to either |
| 286 | * the first or last text boundary depending on which one is reached. Otherwise, |
| 287 | * the iterator's current position is set to the new boundary. |
| 288 | * For example, if the iterator's current position is the mth text boundary |
| 289 | * and three more boundaries exist from the current boundary to the last text |
| 290 | * boundary, the next(2) call will return m + 2. The new text position is set |
| 291 | * to the (m + 2)th text boundary. A next(4) call would return |
| 292 | * <code>BreakIterator.DONE</code> and the last text boundary would become the |
| 293 | * new text position. |
| 294 | * @param n which boundary to return. A value of 0 |
| 295 | * does nothing. Negative values move to previous boundaries |
| 296 | * and positive values move to later boundaries. |
| 297 | * @return The character index of the nth boundary from the current position |
| 298 | * or <code>BreakIterator.DONE</code> if either first or last text boundary |
| 299 | * has been reached. |
| 300 | */ |
| 301 | public abstract int next(int n); |
| 302 | |
| 303 | /** |
| 304 | * Returns the boundary following the current boundary. If the current boundary |
| 305 | * is the last text boundary, it returns <code>BreakIterator.DONE</code> and |
| 306 | * the iterator's current position is unchanged. Otherwise, the iterator's |
| 307 | * current position is set to the boundary following the current boundary. |
| 308 | * @return The character index of the next text boundary or |
| 309 | * <code>BreakIterator.DONE</code> if the current boundary is the last text |
| 310 | * boundary. |
| 311 | * Equivalent to next(1). |
| 312 | * @see #next(int) |
| 313 | */ |
| 314 | public abstract int next(); |
| 315 | |
| 316 | /** |
| 317 | * Returns the boundary preceding the current boundary. If the current boundary |
| 318 | * is the first text boundary, it returns <code>BreakIterator.DONE</code> and |
| 319 | * the iterator's current position is unchanged. Otherwise, the iterator's |
| 320 | * current position is set to the boundary preceding the current boundary. |
| 321 | * @return The character index of the previous text boundary or |
| 322 | * <code>BreakIterator.DONE</code> if the current boundary is the first text |
| 323 | * boundary. |
| 324 | */ |
| 325 | public abstract int previous(); |
| 326 | |
| 327 | /** |
| 328 | * Returns the first boundary following the specified character offset. If the |
| 329 | * specified offset equals to the last text boundary, it returns |
| 330 | * <code>BreakIterator.DONE</code> and the iterator's current position is unchanged. |
| 331 | * Otherwise, the iterator's current position is set to the returned boundary. |
| 332 | * The value returned is always greater than the offset or the value |
| 333 | * <code>BreakIterator.DONE</code>. |
| 334 | * @param offset the character offset to begin scanning. |
| 335 | * @return The first boundary after the specified offset or |
| 336 | * <code>BreakIterator.DONE</code> if the last text boundary is passed in |
| 337 | * as the offset. |
| 338 | * @exception IllegalArgumentException if the specified offset is less than |
| 339 | * the first text boundary or greater than the last text boundary. |
| 340 | */ |
| 341 | public abstract int following(int offset); |
| 342 | |
| 343 | /** |
| 344 | * Returns the last boundary preceding the specified character offset. If the |
| 345 | * specified offset equals to the first text boundary, it returns |
| 346 | * <code>BreakIterator.DONE</code> and the iterator's current position is unchanged. |
| 347 | * Otherwise, the iterator's current position is set to the returned boundary. |
| 348 | * The value returned is always less than the offset or the value |
| 349 | * <code>BreakIterator.DONE</code>. |
| 350 | * @param offset the characater offset to begin scanning. |
| 351 | * @return The last boundary before the specified offset or |
| 352 | * <code>BreakIterator.DONE</code> if the first text boundary is passed in |
| 353 | * as the offset. |
| 354 | * @exception IllegalArgumentException if the specified offset is less than |
| 355 | * the first text boundary or greater than the last text boundary. |
| 356 | * @since 1.2 |
| 357 | */ |
| 358 | public int preceding(int offset) { |
| 359 | // NOTE: This implementation is here solely because we can't add new |
| 360 | // abstract methods to an existing class. There is almost ALWAYS a |
| 361 | // better, faster way to do this. |
| 362 | int pos = following(offset); |
| 363 | while (pos >= offset && pos != DONE) |
| 364 | pos = previous(); |
| 365 | return pos; |
| 366 | } |
| 367 | |
| 368 | /** |
| 369 | * Returns true if the specified character offset is a text boundary. |
| 370 | * @param offset the character offset to check. |
| 371 | * @return <code>true</code> if "offset" is a boundary position, |
| 372 | * <code>false</code> otherwise. |
| 373 | * @exception IllegalArgumentException if the specified offset is less than |
| 374 | * the first text boundary or greater than the last text boundary. |
| 375 | * @since 1.2 |
| 376 | */ |
| 377 | public boolean isBoundary(int offset) { |
| 378 | // NOTE: This implementation probably is wrong for most situations |
| 379 | // because it fails to take into account the possibility that a |
| 380 | // CharacterIterator passed to setText() may not have a begin offset |
| 381 | // of 0. But since the abstract BreakIterator doesn't have that |
| 382 | // knowledge, it assumes the begin offset is 0. If you subclass |
| 383 | // BreakIterator, copy the SimpleTextBoundary implementation of this |
| 384 | // function into your subclass. [This should have been abstract at |
| 385 | // this level, but it's too late to fix that now.] |
| 386 | if (offset == 0) { |
| 387 | return true; |
| 388 | } |
| 389 | int boundary = following(offset - 1); |
| 390 | if (boundary == DONE) { |
| 391 | throw new IllegalArgumentException(); |
| 392 | } |
| 393 | return boundary == offset; |
| 394 | } |
| 395 | |
| 396 | /** |
| 397 | * Returns character index of the text boundary that was most |
| 398 | * recently returned by next(), next(int), previous(), first(), last(), |
| 399 | * following(int) or preceding(int). If any of these methods returns |
| 400 | * <code>BreakIterator.DONE</code> because either first or last text boundary |
| 401 | * has been reached, it returns the first or last text boundary depending on |
| 402 | * which one is reached. |
| 403 | * @return The text boundary returned from the above methods, first or last |
| 404 | * text boundary. |
| 405 | * @see #next() |
| 406 | * @see #next(int) |
| 407 | * @see #previous() |
| 408 | * @see #first() |
| 409 | * @see #last() |
| 410 | * @see #following(int) |
| 411 | * @see #preceding(int) |
| 412 | */ |
| 413 | public abstract int current(); |
| 414 | |
| 415 | /** |
| 416 | * Get the text being scanned |
| 417 | * @return the text being scanned |
| 418 | */ |
| 419 | public abstract CharacterIterator getText(); |
| 420 | |
| 421 | /** |
| 422 | * Set a new text string to be scanned. The current scan |
| 423 | * position is reset to first(). |
| 424 | * @param newText new text to scan. |
| 425 | */ |
| 426 | public void setText(String newText) |
| 427 | { |
| 428 | setText(new StringCharacterIterator(newText)); |
| 429 | } |
| 430 | |
| 431 | /** |
| 432 | * Set a new text for scanning. The current scan |
| 433 | * position is reset to first(). |
| 434 | * @param newText new text to scan. |
| 435 | */ |
| 436 | public abstract void setText(CharacterIterator newText); |
| 437 | |
| 438 | private static final int CHARACTER_INDEX = 0; |
| 439 | private static final int WORD_INDEX = 1; |
| 440 | private static final int LINE_INDEX = 2; |
| 441 | private static final int SENTENCE_INDEX = 3; |
| 442 | private static final SoftReference[] iterCache = new SoftReference[4]; |
| 443 | |
| 444 | /** |
| 445 | * Returns a new <code>BreakIterator</code> instance |
| 446 | * for <a href="#word">word breaks</a> |
| 447 | * for the {@linkplain Locale#getDefault() default locale}. |
| 448 | * @return A break iterator for word breaks |
| 449 | */ |
| 450 | public static BreakIterator getWordInstance() |
| 451 | { |
| 452 | return getWordInstance(Locale.getDefault()); |
| 453 | } |
| 454 | |
| 455 | /** |
| 456 | * Returns a new <code>BreakIterator</code> instance |
| 457 | * for <a href="#word">word breaks</a> |
| 458 | * for the given locale. |
| 459 | * @param locale the desired locale |
| 460 | * @return A break iterator for word breaks |
| 461 | * @exception NullPointerException if <code>locale</code> is null |
| 462 | */ |
| 463 | public static BreakIterator getWordInstance(Locale locale) |
| 464 | { |
| 465 | return getBreakInstance(locale, |
| 466 | WORD_INDEX, |
| 467 | "WordData", |
| 468 | "WordDictionary"); |
| 469 | } |
| 470 | |
| 471 | /** |
| 472 | * Returns a new <code>BreakIterator</code> instance |
| 473 | * for <a href="#line">line breaks</a> |
| 474 | * for the {@linkplain Locale#getDefault() default locale}. |
| 475 | * @return A break iterator for line breaks |
| 476 | */ |
| 477 | public static BreakIterator getLineInstance() |
| 478 | { |
| 479 | return getLineInstance(Locale.getDefault()); |
| 480 | } |
| 481 | |
| 482 | /** |
| 483 | * Returns a new <code>BreakIterator</code> instance |
| 484 | * for <a href="#line">line breaks</a> |
| 485 | * for the given locale. |
| 486 | * @param locale the desired locale |
| 487 | * @return A break iterator for line breaks |
| 488 | * @exception NullPointerException if <code>locale</code> is null |
| 489 | */ |
| 490 | public static BreakIterator getLineInstance(Locale locale) |
| 491 | { |
| 492 | return getBreakInstance(locale, |
| 493 | LINE_INDEX, |
| 494 | "LineData", |
| 495 | "LineDictionary"); |
| 496 | } |
| 497 | |
| 498 | /** |
| 499 | * Returns a new <code>BreakIterator</code> instance |
| 500 | * for <a href="#character">character breaks</a> |
| 501 | * for the {@linkplain Locale#getDefault() default locale}. |
| 502 | * @return A break iterator for character breaks |
| 503 | */ |
| 504 | public static BreakIterator getCharacterInstance() |
| 505 | { |
| 506 | return getCharacterInstance(Locale.getDefault()); |
| 507 | } |
| 508 | |
| 509 | /** |
| 510 | * Returns a new <code>BreakIterator</code> instance |
| 511 | * for <a href="#character">character breaks</a> |
| 512 | * for the given locale. |
| 513 | * @param locale the desired locale |
| 514 | * @return A break iterator for character breaks |
| 515 | * @exception NullPointerException if <code>locale</code> is null |
| 516 | */ |
| 517 | public static BreakIterator getCharacterInstance(Locale locale) |
| 518 | { |
| 519 | return getBreakInstance(locale, |
| 520 | CHARACTER_INDEX, |
| 521 | "CharacterData", |
| 522 | "CharacterDictionary"); |
| 523 | } |
| 524 | |
| 525 | /** |
| 526 | * Returns a new <code>BreakIterator</code> instance |
| 527 | * for <a href="#sentence">sentence breaks</a> |
| 528 | * for the {@linkplain Locale#getDefault() default locale}. |
| 529 | * @return A break iterator for sentence breaks |
| 530 | */ |
| 531 | public static BreakIterator getSentenceInstance() |
| 532 | { |
| 533 | return getSentenceInstance(Locale.getDefault()); |
| 534 | } |
| 535 | |
| 536 | /** |
| 537 | * Returns a new <code>BreakIterator</code> instance |
| 538 | * for <a href="#sentence">sentence breaks</a> |
| 539 | * for the given locale. |
| 540 | * @param locale the desired locale |
| 541 | * @return A break iterator for sentence breaks |
| 542 | * @exception NullPointerException if <code>locale</code> is null |
| 543 | */ |
| 544 | public static BreakIterator getSentenceInstance(Locale locale) |
| 545 | { |
| 546 | return getBreakInstance(locale, |
| 547 | SENTENCE_INDEX, |
| 548 | "SentenceData", |
| 549 | "SentenceDictionary"); |
| 550 | } |
| 551 | |
| 552 | private static BreakIterator getBreakInstance(Locale locale, |
| 553 | int type, |
| 554 | String dataName, |
| 555 | String dictionaryName) { |
| 556 | if (iterCache[type] != null) { |
| 557 | BreakIteratorCache cache = (BreakIteratorCache) iterCache[type].get(); |
| 558 | if (cache != null) { |
| 559 | if (cache.getLocale().equals(locale)) { |
| 560 | return cache.createBreakInstance(); |
| 561 | } |
| 562 | } |
| 563 | } |
| 564 | |
| 565 | BreakIterator result = createBreakInstance(locale, |
| 566 | type, |
| 567 | dataName, |
| 568 | dictionaryName); |
| 569 | BreakIteratorCache cache = new BreakIteratorCache(locale, result); |
| 570 | iterCache[type] = new SoftReference(cache); |
| 571 | return result; |
| 572 | } |
| 573 | |
| 574 | private static ResourceBundle getBundle(final String baseName, final Locale locale) { |
| 575 | return (ResourceBundle) AccessController.doPrivileged(new PrivilegedAction() { |
| 576 | public Object run() { |
| 577 | return ResourceBundle.getBundle(baseName, locale); |
| 578 | } |
| 579 | }); |
| 580 | } |
| 581 | |
| 582 | private static BreakIterator createBreakInstance(Locale locale, |
| 583 | int type, |
| 584 | String dataName, |
| 585 | String dictionaryName) { |
| 586 | |
| 587 | // Check whether a provider can provide an implementation that's closer |
| 588 | // to the requested locale than what the Java runtime itself can provide. |
| 589 | LocaleServiceProviderPool pool = |
| 590 | LocaleServiceProviderPool.getPool(BreakIteratorProvider.class); |
| 591 | if (pool.hasProviders()) { |
| 592 | BreakIterator providersInstance = pool.getLocalizedObject( |
| 593 | BreakIteratorGetter.INSTANCE, |
| 594 | locale, type); |
| 595 | if (providersInstance != null) { |
| 596 | return providersInstance; |
| 597 | } |
| 598 | } |
| 599 | |
| 600 | ResourceBundle bundle = getBundle( |
| 601 | "sun.text.resources.BreakIteratorInfo", locale); |
| 602 | String[] classNames = bundle.getStringArray("BreakIteratorClasses"); |
| 603 | |
| 604 | String dataFile = bundle.getString(dataName); |
| 605 | |
| 606 | try { |
| 607 | if (classNames[type].equals("RuleBasedBreakIterator")) { |
| 608 | return new RuleBasedBreakIterator(dataFile); |
| 609 | } |
| 610 | else if (classNames[type].equals("DictionaryBasedBreakIterator")) { |
| 611 | String dictionaryFile = bundle.getString(dictionaryName); |
| 612 | return new DictionaryBasedBreakIterator(dataFile, dictionaryFile); |
| 613 | } |
| 614 | else { |
| 615 | throw new IllegalArgumentException("Invalid break iterator class \"" + |
| 616 | classNames[type] + "\""); |
| 617 | } |
| 618 | } |
| 619 | catch (Exception e) { |
| 620 | throw new InternalError(e.toString()); |
| 621 | } |
| 622 | } |
| 623 | |
| 624 | /** |
| 625 | * Returns an array of all locales for which the |
| 626 | * <code>get*Instance</code> methods of this class can return |
| 627 | * localized instances. |
| 628 | * The returned array represents the union of locales supported by the Java |
| 629 | * runtime and by installed |
| 630 | * {@link java.text.spi.BreakIteratorProvider BreakIteratorProvider} implementations. |
| 631 | * It must contain at least a <code>Locale</code> |
| 632 | * instance equal to {@link java.util.Locale#US Locale.US}. |
| 633 | * |
| 634 | * @return An array of locales for which localized |
| 635 | * <code>BreakIterator</code> instances are available. |
| 636 | */ |
| 637 | public static synchronized Locale[] getAvailableLocales() |
| 638 | { |
| 639 | LocaleServiceProviderPool pool = |
| 640 | LocaleServiceProviderPool.getPool(BreakIteratorProvider.class); |
| 641 | return pool.getAvailableLocales(); |
| 642 | } |
| 643 | |
| 644 | private static final class BreakIteratorCache { |
| 645 | |
| 646 | private BreakIterator iter; |
| 647 | private Locale locale; |
| 648 | |
| 649 | BreakIteratorCache(Locale locale, BreakIterator iter) { |
| 650 | this.locale = locale; |
| 651 | this.iter = (BreakIterator) iter.clone(); |
| 652 | } |
| 653 | |
| 654 | Locale getLocale() { |
| 655 | return locale; |
| 656 | } |
| 657 | |
| 658 | BreakIterator createBreakInstance() { |
| 659 | return (BreakIterator) iter.clone(); |
| 660 | } |
| 661 | } |
| 662 | |
| 663 | static long getLong(byte[] buf, int offset) { |
| 664 | long num = buf[offset]&0xFF; |
| 665 | for (int i = 1; i < 8; i++) { |
| 666 | num = num<<8 | (buf[offset+i]&0xFF); |
| 667 | } |
| 668 | return num; |
| 669 | } |
| 670 | |
| 671 | static int getInt(byte[] buf, int offset) { |
| 672 | int num = buf[offset]&0xFF; |
| 673 | for (int i = 1; i < 4; i++) { |
| 674 | num = num<<8 | (buf[offset+i]&0xFF); |
| 675 | } |
| 676 | return num; |
| 677 | } |
| 678 | |
| 679 | static short getShort(byte[] buf, int offset) { |
| 680 | short num = (short)(buf[offset]&0xFF); |
| 681 | num = (short)(num<<8 | (buf[offset+1]&0xFF)); |
| 682 | return num; |
| 683 | } |
| 684 | |
| 685 | /** |
| 686 | * Obtains a BreakIterator instance from a BreakIteratorProvider |
| 687 | * implementation. |
| 688 | */ |
| 689 | private static class BreakIteratorGetter |
| 690 | implements LocaleServiceProviderPool.LocalizedObjectGetter<BreakIteratorProvider, BreakIterator> { |
| 691 | private static final BreakIteratorGetter INSTANCE = |
| 692 | new BreakIteratorGetter(); |
| 693 | |
| 694 | public BreakIterator getObject(BreakIteratorProvider breakIteratorProvider, |
| 695 | Locale locale, |
| 696 | String key, |
| 697 | Object... params) { |
| 698 | assert params.length == 1; |
| 699 | |
| 700 | switch ((Integer)params[0]) { |
| 701 | case CHARACTER_INDEX: |
| 702 | return breakIteratorProvider.getCharacterInstance(locale); |
| 703 | case WORD_INDEX: |
| 704 | return breakIteratorProvider.getWordInstance(locale); |
| 705 | case LINE_INDEX: |
| 706 | return breakIteratorProvider.getLineInstance(locale); |
| 707 | case SENTENCE_INDEX: |
| 708 | return breakIteratorProvider.getSentenceInstance(locale); |
| 709 | default: |
| 710 | assert false : "should not happen"; |
| 711 | } |
| 712 | return null; |
| 713 | } |
| 714 | } |
| 715 | } |