J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Portions Copyright 2001-2006 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 | ******************************************************************************* |
| 28 | * (C) Copyright IBM Corp. 1996-2005 - All Rights Reserved * |
| 29 | * * |
| 30 | * The original version of this source code and documentation is copyrighted * |
| 31 | * and owned by IBM, These materials are provided under terms of a License * |
| 32 | * Agreement between IBM and Sun. This technology is protected by multiple * |
| 33 | * US and International patents. This notice and attribution to IBM may not * |
| 34 | * to removed. * |
| 35 | ******************************************************************************* |
| 36 | */ |
| 37 | |
| 38 | package sun.text.normalizer; |
| 39 | |
| 40 | import java.text.CharacterIterator; |
| 41 | import java.text.Normalizer; |
| 42 | |
| 43 | /** |
| 44 | * Unicode Normalization |
| 45 | * |
| 46 | * <h2>Unicode normalization API</h2> |
| 47 | * |
| 48 | * <code>normalize</code> transforms Unicode text into an equivalent composed or |
| 49 | * decomposed form, allowing for easier sorting and searching of text. |
| 50 | * <code>normalize</code> supports the standard normalization forms described in |
| 51 | * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> |
| 52 | * Unicode Standard Annex #15 — Unicode Normalization Forms</a>. |
| 53 | * |
| 54 | * Characters with accents or other adornments can be encoded in |
| 55 | * several different ways in Unicode. For example, take the character A-acute. |
| 56 | * In Unicode, this can be encoded as a single character (the |
| 57 | * "composed" form): |
| 58 | * |
| 59 | * <p> |
| 60 | * 00C1 LATIN CAPITAL LETTER A WITH ACUTE |
| 61 | * </p> |
| 62 | * |
| 63 | * or as two separate characters (the "decomposed" form): |
| 64 | * |
| 65 | * <p> |
| 66 | * 0041 LATIN CAPITAL LETTER A |
| 67 | * 0301 COMBINING ACUTE ACCENT |
| 68 | * </p> |
| 69 | * |
| 70 | * To a user of your program, however, both of these sequences should be |
| 71 | * treated as the same "user-level" character "A with acute accent". When you |
| 72 | * are searching or comparing text, you must ensure that these two sequences are |
| 73 | * treated equivalently. In addition, you must handle characters with more than |
| 74 | * one accent. Sometimes the order of a character's combining accents is |
| 75 | * significant, while in other cases accent sequences in different orders are |
| 76 | * really equivalent. |
| 77 | * |
| 78 | * Similarly, the string "ffi" can be encoded as three separate letters: |
| 79 | * |
| 80 | * <p> |
| 81 | * 0066 LATIN SMALL LETTER F |
| 82 | * 0066 LATIN SMALL LETTER F |
| 83 | * 0069 LATIN SMALL LETTER I |
| 84 | * </p> |
| 85 | * |
| 86 | * or as the single character |
| 87 | * |
| 88 | * <p> |
| 89 | * FB03 LATIN SMALL LIGATURE FFI |
| 90 | * </p> |
| 91 | * |
| 92 | * The ffi ligature is not a distinct semantic character, and strictly speaking |
| 93 | * it shouldn't be in Unicode at all, but it was included for compatibility |
| 94 | * with existing character sets that already provided it. The Unicode standard |
| 95 | * identifies such characters by giving them "compatibility" decompositions |
| 96 | * into the corresponding semantic characters. When sorting and searching, you |
| 97 | * will often want to use these mappings. |
| 98 | * |
| 99 | * <code>normalize</code> helps solve these problems by transforming text into |
| 100 | * the canonical composed and decomposed forms as shown in the first example |
| 101 | * above. In addition, you can have it perform compatibility decompositions so |
| 102 | * that you can treat compatibility characters the same as their equivalents. |
| 103 | * Finally, <code>normalize</code> rearranges accents into the proper canonical |
| 104 | * order, so that you do not have to worry about accent rearrangement on your |
| 105 | * own. |
| 106 | * |
| 107 | * Form FCD, "Fast C or D", is also designed for collation. |
| 108 | * It allows to work on strings that are not necessarily normalized |
| 109 | * with an algorithm (like in collation) that works under "canonical closure", |
| 110 | * i.e., it treats precomposed characters and their decomposed equivalents the |
| 111 | * same. |
| 112 | * |
| 113 | * It is not a normalization form because it does not provide for uniqueness of |
| 114 | * representation. Multiple strings may be canonically equivalent (their NFDs |
| 115 | * are identical) and may all conform to FCD without being identical themselves. |
| 116 | * |
| 117 | * The form is defined such that the "raw decomposition", the recursive |
| 118 | * canonical decomposition of each character, results in a string that is |
| 119 | * canonically ordered. This means that precomposed characters are allowed for |
| 120 | * as long as their decompositions do not need canonical reordering. |
| 121 | * |
| 122 | * Its advantage for a process like collation is that all NFD and most NFC texts |
| 123 | * - and many unnormalized texts - already conform to FCD and do not need to be |
| 124 | * normalized (NFD) for such a process. The FCD quick check will return YES for |
| 125 | * most strings in practice. |
| 126 | * |
| 127 | * normalize(FCD) may be implemented with NFD. |
| 128 | * |
| 129 | * For more details on FCD see the collation design document: |
| 130 | * http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/collation/ICU_collation_design.htm |
| 131 | * |
| 132 | * ICU collation performs either NFD or FCD normalization automatically if |
| 133 | * normalization is turned on for the collator object. Beyond collation and |
| 134 | * string search, normalized strings may be useful for string equivalence |
| 135 | * comparisons, transliteration/transcription, unique representations, etc. |
| 136 | * |
| 137 | * The W3C generally recommends to exchange texts in NFC. |
| 138 | * Note also that most legacy character encodings use only precomposed forms and |
| 139 | * often do not encode any combining marks by themselves. For conversion to such |
| 140 | * character encodings the Unicode text needs to be normalized to NFC. |
| 141 | * For more usage examples, see the Unicode Standard Annex. |
| 142 | * @stable ICU 2.8 |
| 143 | */ |
| 144 | |
| 145 | public final class NormalizerBase implements Cloneable { |
| 146 | |
| 147 | //------------------------------------------------------------------------- |
| 148 | // Private data |
| 149 | //------------------------------------------------------------------------- |
| 150 | private char[] buffer = new char[100]; |
| 151 | private int bufferStart = 0; |
| 152 | private int bufferPos = 0; |
| 153 | private int bufferLimit = 0; |
| 154 | |
| 155 | // The input text and our position in it |
| 156 | private UCharacterIterator text; |
| 157 | private Mode mode = NFC; |
| 158 | private int options = 0; |
| 159 | private int currentIndex; |
| 160 | private int nextIndex; |
| 161 | |
| 162 | /** |
| 163 | * Options bit set value to select Unicode 3.2 normalization |
| 164 | * (except NormalizationCorrections). |
| 165 | * At most one Unicode version can be selected at a time. |
| 166 | * @stable ICU 2.6 |
| 167 | */ |
| 168 | public static final int UNICODE_3_2=0x20; |
| 169 | |
| 170 | /** |
| 171 | * Constant indicating that the end of the iteration has been reached. |
| 172 | * This is guaranteed to have the same value as {@link UCharacterIterator#DONE}. |
| 173 | * @stable ICU 2.8 |
| 174 | */ |
| 175 | public static final int DONE = UCharacterIterator.DONE; |
| 176 | |
| 177 | /** |
| 178 | * Constants for normalization modes. |
| 179 | * @stable ICU 2.8 |
| 180 | */ |
| 181 | public static class Mode { |
| 182 | private int modeValue; |
| 183 | private Mode(int value) { |
| 184 | modeValue = value; |
| 185 | } |
| 186 | |
| 187 | /** |
| 188 | * This method is used for method dispatch |
| 189 | * @stable ICU 2.6 |
| 190 | */ |
| 191 | protected int normalize(char[] src, int srcStart, int srcLimit, |
| 192 | char[] dest,int destStart,int destLimit, |
| 193 | UnicodeSet nx) { |
| 194 | int srcLen = (srcLimit - srcStart); |
| 195 | int destLen = (destLimit - destStart); |
| 196 | if( srcLen > destLen ) { |
| 197 | return srcLen; |
| 198 | } |
| 199 | System.arraycopy(src,srcStart,dest,destStart,srcLen); |
| 200 | return srcLen; |
| 201 | } |
| 202 | |
| 203 | /** |
| 204 | * This method is used for method dispatch |
| 205 | * @stable ICU 2.6 |
| 206 | */ |
| 207 | protected int normalize(char[] src, int srcStart, int srcLimit, |
| 208 | char[] dest,int destStart,int destLimit, |
| 209 | int options) { |
| 210 | return normalize( src, srcStart, srcLimit, |
| 211 | dest,destStart,destLimit, |
| 212 | NormalizerImpl.getNX(options) |
| 213 | ); |
| 214 | } |
| 215 | |
| 216 | /** |
| 217 | * This method is used for method dispatch |
| 218 | * @stable ICU 2.6 |
| 219 | */ |
| 220 | protected String normalize(String src, int options) { |
| 221 | return src; |
| 222 | } |
| 223 | |
| 224 | /** |
| 225 | * This method is used for method dispatch |
| 226 | * @stable ICU 2.8 |
| 227 | */ |
| 228 | protected int getMinC() { |
| 229 | return -1; |
| 230 | } |
| 231 | |
| 232 | /** |
| 233 | * This method is used for method dispatch |
| 234 | * @stable ICU 2.8 |
| 235 | */ |
| 236 | protected int getMask() { |
| 237 | return -1; |
| 238 | } |
| 239 | |
| 240 | /** |
| 241 | * This method is used for method dispatch |
| 242 | * @stable ICU 2.8 |
| 243 | */ |
| 244 | protected IsPrevBoundary getPrevBoundary() { |
| 245 | return null; |
| 246 | } |
| 247 | |
| 248 | /** |
| 249 | * This method is used for method dispatch |
| 250 | * @stable ICU 2.8 |
| 251 | */ |
| 252 | protected IsNextBoundary getNextBoundary() { |
| 253 | return null; |
| 254 | } |
| 255 | |
| 256 | /** |
| 257 | * This method is used for method dispatch |
| 258 | * @stable ICU 2.6 |
| 259 | */ |
| 260 | protected QuickCheckResult quickCheck(char[] src,int start, int limit, |
| 261 | boolean allowMaybe,UnicodeSet nx) { |
| 262 | if(allowMaybe) { |
| 263 | return MAYBE; |
| 264 | } |
| 265 | return NO; |
| 266 | } |
| 267 | |
| 268 | /** |
| 269 | * This method is used for method dispatch |
| 270 | * @stable ICU 2.8 |
| 271 | */ |
| 272 | protected boolean isNFSkippable(int c) { |
| 273 | return true; |
| 274 | } |
| 275 | } |
| 276 | |
| 277 | /** |
| 278 | * No decomposition/composition. |
| 279 | * @stable ICU 2.8 |
| 280 | */ |
| 281 | public static final Mode NONE = new Mode(1); |
| 282 | |
| 283 | /** |
| 284 | * Canonical decomposition. |
| 285 | * @stable ICU 2.8 |
| 286 | */ |
| 287 | public static final Mode NFD = new NFDMode(2); |
| 288 | |
| 289 | private static final class NFDMode extends Mode { |
| 290 | private NFDMode(int value) { |
| 291 | super(value); |
| 292 | } |
| 293 | |
| 294 | protected int normalize(char[] src, int srcStart, int srcLimit, |
| 295 | char[] dest,int destStart,int destLimit, |
| 296 | UnicodeSet nx) { |
| 297 | int[] trailCC = new int[1]; |
| 298 | return NormalizerImpl.decompose(src, srcStart,srcLimit, |
| 299 | dest, destStart,destLimit, |
| 300 | false, trailCC,nx); |
| 301 | } |
| 302 | |
| 303 | protected String normalize( String src, int options) { |
| 304 | return decompose(src,false,options); |
| 305 | } |
| 306 | |
| 307 | protected int getMinC() { |
| 308 | return NormalizerImpl.MIN_WITH_LEAD_CC; |
| 309 | } |
| 310 | |
| 311 | protected IsPrevBoundary getPrevBoundary() { |
| 312 | return new IsPrevNFDSafe(); |
| 313 | } |
| 314 | |
| 315 | protected IsNextBoundary getNextBoundary() { |
| 316 | return new IsNextNFDSafe(); |
| 317 | } |
| 318 | |
| 319 | protected int getMask() { |
| 320 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFD); |
| 321 | } |
| 322 | |
| 323 | protected QuickCheckResult quickCheck(char[] src,int start, |
| 324 | int limit,boolean allowMaybe, |
| 325 | UnicodeSet nx) { |
| 326 | return NormalizerImpl.quickCheck( |
| 327 | src, start,limit, |
| 328 | NormalizerImpl.getFromIndexesArr( |
| 329 | NormalizerImpl.INDEX_MIN_NFD_NO_MAYBE |
| 330 | ), |
| 331 | NormalizerImpl.QC_NFD, |
| 332 | 0, |
| 333 | allowMaybe, |
| 334 | nx |
| 335 | ); |
| 336 | } |
| 337 | |
| 338 | protected boolean isNFSkippable(int c) { |
| 339 | return NormalizerImpl.isNFSkippable(c,this, |
| 340 | (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFD) |
| 341 | ); |
| 342 | } |
| 343 | } |
| 344 | |
| 345 | /** |
| 346 | * Compatibility decomposition. |
| 347 | * @stable ICU 2.8 |
| 348 | */ |
| 349 | public static final Mode NFKD = new NFKDMode(3); |
| 350 | |
| 351 | private static final class NFKDMode extends Mode { |
| 352 | private NFKDMode(int value) { |
| 353 | super(value); |
| 354 | } |
| 355 | |
| 356 | protected int normalize(char[] src, int srcStart, int srcLimit, |
| 357 | char[] dest,int destStart,int destLimit, |
| 358 | UnicodeSet nx) { |
| 359 | int[] trailCC = new int[1]; |
| 360 | return NormalizerImpl.decompose(src, srcStart,srcLimit, |
| 361 | dest, destStart,destLimit, |
| 362 | true, trailCC, nx); |
| 363 | } |
| 364 | |
| 365 | protected String normalize( String src, int options) { |
| 366 | return decompose(src,true,options); |
| 367 | } |
| 368 | |
| 369 | protected int getMinC() { |
| 370 | return NormalizerImpl.MIN_WITH_LEAD_CC; |
| 371 | } |
| 372 | |
| 373 | protected IsPrevBoundary getPrevBoundary() { |
| 374 | return new IsPrevNFDSafe(); |
| 375 | } |
| 376 | |
| 377 | protected IsNextBoundary getNextBoundary() { |
| 378 | return new IsNextNFDSafe(); |
| 379 | } |
| 380 | |
| 381 | protected int getMask() { |
| 382 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFKD); |
| 383 | } |
| 384 | |
| 385 | protected QuickCheckResult quickCheck(char[] src,int start, |
| 386 | int limit,boolean allowMaybe, |
| 387 | UnicodeSet nx) { |
| 388 | return NormalizerImpl.quickCheck( |
| 389 | src,start,limit, |
| 390 | NormalizerImpl.getFromIndexesArr( |
| 391 | NormalizerImpl.INDEX_MIN_NFKD_NO_MAYBE |
| 392 | ), |
| 393 | NormalizerImpl.QC_NFKD, |
| 394 | NormalizerImpl.OPTIONS_COMPAT, |
| 395 | allowMaybe, |
| 396 | nx |
| 397 | ); |
| 398 | } |
| 399 | |
| 400 | protected boolean isNFSkippable(int c) { |
| 401 | return NormalizerImpl.isNFSkippable(c, this, |
| 402 | (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFKD) |
| 403 | ); |
| 404 | } |
| 405 | } |
| 406 | |
| 407 | /** |
| 408 | * Canonical decomposition followed by canonical composition. |
| 409 | * @stable ICU 2.8 |
| 410 | */ |
| 411 | public static final Mode NFC = new NFCMode(4); |
| 412 | |
| 413 | private static final class NFCMode extends Mode{ |
| 414 | private NFCMode(int value) { |
| 415 | super(value); |
| 416 | } |
| 417 | protected int normalize(char[] src, int srcStart, int srcLimit, |
| 418 | char[] dest,int destStart,int destLimit, |
| 419 | UnicodeSet nx) { |
| 420 | return NormalizerImpl.compose( src, srcStart, srcLimit, |
| 421 | dest,destStart,destLimit, |
| 422 | 0, nx); |
| 423 | } |
| 424 | |
| 425 | protected String normalize( String src, int options) { |
| 426 | return compose(src, false, options); |
| 427 | } |
| 428 | |
| 429 | protected int getMinC() { |
| 430 | return NormalizerImpl.getFromIndexesArr( |
| 431 | NormalizerImpl.INDEX_MIN_NFC_NO_MAYBE |
| 432 | ); |
| 433 | } |
| 434 | protected IsPrevBoundary getPrevBoundary() { |
| 435 | return new IsPrevTrueStarter(); |
| 436 | } |
| 437 | protected IsNextBoundary getNextBoundary() { |
| 438 | return new IsNextTrueStarter(); |
| 439 | } |
| 440 | protected int getMask() { |
| 441 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFC); |
| 442 | } |
| 443 | protected QuickCheckResult quickCheck(char[] src,int start, |
| 444 | int limit,boolean allowMaybe, |
| 445 | UnicodeSet nx) { |
| 446 | return NormalizerImpl.quickCheck( |
| 447 | src,start,limit, |
| 448 | NormalizerImpl.getFromIndexesArr( |
| 449 | NormalizerImpl.INDEX_MIN_NFC_NO_MAYBE |
| 450 | ), |
| 451 | NormalizerImpl.QC_NFC, |
| 452 | 0, |
| 453 | allowMaybe, |
| 454 | nx |
| 455 | ); |
| 456 | } |
| 457 | protected boolean isNFSkippable(int c) { |
| 458 | return NormalizerImpl.isNFSkippable(c,this, |
| 459 | ( NormalizerImpl.CC_MASK|NormalizerImpl.COMBINES_ANY| |
| 460 | (NormalizerImpl.QC_NFC & NormalizerImpl.QC_ANY_NO) |
| 461 | ) |
| 462 | ); |
| 463 | } |
| 464 | }; |
| 465 | |
| 466 | /** |
| 467 | * Compatibility decomposition followed by canonical composition. |
| 468 | * @stable ICU 2.8 |
| 469 | */ |
| 470 | public static final Mode NFKC =new NFKCMode(5); |
| 471 | |
| 472 | private static final class NFKCMode extends Mode{ |
| 473 | private NFKCMode(int value) { |
| 474 | super(value); |
| 475 | } |
| 476 | protected int normalize(char[] src, int srcStart, int srcLimit, |
| 477 | char[] dest,int destStart,int destLimit, |
| 478 | UnicodeSet nx) { |
| 479 | return NormalizerImpl.compose(src, srcStart,srcLimit, |
| 480 | dest, destStart,destLimit, |
| 481 | NormalizerImpl.OPTIONS_COMPAT, nx); |
| 482 | } |
| 483 | |
| 484 | protected String normalize( String src, int options) { |
| 485 | return compose(src, true, options); |
| 486 | } |
| 487 | protected int getMinC() { |
| 488 | return NormalizerImpl.getFromIndexesArr( |
| 489 | NormalizerImpl.INDEX_MIN_NFKC_NO_MAYBE |
| 490 | ); |
| 491 | } |
| 492 | protected IsPrevBoundary getPrevBoundary() { |
| 493 | return new IsPrevTrueStarter(); |
| 494 | } |
| 495 | protected IsNextBoundary getNextBoundary() { |
| 496 | return new IsNextTrueStarter(); |
| 497 | } |
| 498 | protected int getMask() { |
| 499 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFKC); |
| 500 | } |
| 501 | protected QuickCheckResult quickCheck(char[] src,int start, |
| 502 | int limit,boolean allowMaybe, |
| 503 | UnicodeSet nx) { |
| 504 | return NormalizerImpl.quickCheck( |
| 505 | src,start,limit, |
| 506 | NormalizerImpl.getFromIndexesArr( |
| 507 | NormalizerImpl.INDEX_MIN_NFKC_NO_MAYBE |
| 508 | ), |
| 509 | NormalizerImpl.QC_NFKC, |
| 510 | NormalizerImpl.OPTIONS_COMPAT, |
| 511 | allowMaybe, |
| 512 | nx |
| 513 | ); |
| 514 | } |
| 515 | protected boolean isNFSkippable(int c) { |
| 516 | return NormalizerImpl.isNFSkippable(c, this, |
| 517 | ( NormalizerImpl.CC_MASK|NormalizerImpl.COMBINES_ANY| |
| 518 | (NormalizerImpl.QC_NFKC & NormalizerImpl.QC_ANY_NO) |
| 519 | ) |
| 520 | ); |
| 521 | } |
| 522 | }; |
| 523 | |
| 524 | /** |
| 525 | * Result values for quickCheck(). |
| 526 | * For details see Unicode Technical Report 15. |
| 527 | * @stable ICU 2.8 |
| 528 | */ |
| 529 | public static final class QuickCheckResult{ |
| 530 | private int resultValue; |
| 531 | private QuickCheckResult(int value) { |
| 532 | resultValue=value; |
| 533 | } |
| 534 | } |
| 535 | /** |
| 536 | * Indicates that string is not in the normalized format |
| 537 | * @stable ICU 2.8 |
| 538 | */ |
| 539 | public static final QuickCheckResult NO = new QuickCheckResult(0); |
| 540 | |
| 541 | /** |
| 542 | * Indicates that string is in the normalized format |
| 543 | * @stable ICU 2.8 |
| 544 | */ |
| 545 | public static final QuickCheckResult YES = new QuickCheckResult(1); |
| 546 | |
| 547 | /** |
| 548 | * Indicates it cannot be determined if string is in the normalized |
| 549 | * format without further thorough checks. |
| 550 | * @stable ICU 2.8 |
| 551 | */ |
| 552 | public static final QuickCheckResult MAYBE = new QuickCheckResult(2); |
| 553 | |
| 554 | //------------------------------------------------------------------------- |
| 555 | // Constructors |
| 556 | //------------------------------------------------------------------------- |
| 557 | |
| 558 | /** |
| 559 | * Creates a new <tt>Normalizer</tt> object for iterating over the |
| 560 | * normalized form of a given string. |
| 561 | * <p> |
| 562 | * The <tt>options</tt> parameter specifies which optional |
| 563 | * <tt>Normalizer</tt> features are to be enabled for this object. |
| 564 | * <p> |
| 565 | * @param str The string to be normalized. The normalization |
| 566 | * will start at the beginning of the string. |
| 567 | * |
| 568 | * @param mode The normalization mode. |
| 569 | * |
| 570 | * @param opt Any optional features to be enabled. |
| 571 | * Currently the only available option is {@link #UNICODE_3_2}. |
| 572 | * If you want the default behavior corresponding to one of the |
| 573 | * standard Unicode Normalization Forms, use 0 for this argument. |
| 574 | * @stable ICU 2.6 |
| 575 | */ |
| 576 | public NormalizerBase(String str, Mode mode, int opt) { |
| 577 | this.text = UCharacterIterator.getInstance(str); |
| 578 | this.mode = mode; |
| 579 | this.options=opt; |
| 580 | } |
| 581 | |
| 582 | /** |
| 583 | * Creates a new <tt>Normalizer</tt> object for iterating over the |
| 584 | * normalized form of the given text. |
| 585 | * <p> |
| 586 | * @param iter The input text to be normalized. The normalization |
| 587 | * will start at the beginning of the string. |
| 588 | * |
| 589 | * @param mode The normalization mode. |
| 590 | */ |
| 591 | public NormalizerBase(CharacterIterator iter, Mode mode) { |
| 592 | this(iter, mode, UNICODE_LATEST); |
| 593 | } |
| 594 | |
| 595 | /** |
| 596 | * Creates a new <tt>Normalizer</tt> object for iterating over the |
| 597 | * normalized form of the given text. |
| 598 | * <p> |
| 599 | * @param iter The input text to be normalized. The normalization |
| 600 | * will start at the beginning of the string. |
| 601 | * |
| 602 | * @param mode The normalization mode. |
| 603 | * |
| 604 | * @param opt Any optional features to be enabled. |
| 605 | * Currently the only available option is {@link #UNICODE_3_2}. |
| 606 | * If you want the default behavior corresponding to one of the |
| 607 | * standard Unicode Normalization Forms, use 0 for this argument. |
| 608 | * @stable ICU 2.6 |
| 609 | */ |
| 610 | public NormalizerBase(CharacterIterator iter, Mode mode, int opt) { |
| 611 | this.text = UCharacterIterator.getInstance( |
| 612 | (CharacterIterator)iter.clone() |
| 613 | ); |
| 614 | this.mode = mode; |
| 615 | this.options = opt; |
| 616 | } |
| 617 | |
| 618 | /** |
| 619 | * Clones this <tt>Normalizer</tt> object. All properties of this |
| 620 | * object are duplicated in the new object, including the cloning of any |
| 621 | * {@link CharacterIterator} that was passed in to the constructor |
| 622 | * or to {@link #setText(CharacterIterator) setText}. |
| 623 | * However, the text storage underlying |
| 624 | * the <tt>CharacterIterator</tt> is not duplicated unless the |
| 625 | * iterator's <tt>clone</tt> method does so. |
| 626 | * @stable ICU 2.8 |
| 627 | */ |
| 628 | public Object clone() { |
| 629 | try { |
| 630 | NormalizerBase copy = (NormalizerBase) super.clone(); |
| 631 | copy.text = (UCharacterIterator) text.clone(); |
| 632 | //clone the internal buffer |
| 633 | if (buffer != null) { |
| 634 | copy.buffer = new char[buffer.length]; |
| 635 | System.arraycopy(buffer,0,copy.buffer,0,buffer.length); |
| 636 | } |
| 637 | return copy; |
| 638 | } |
| 639 | catch (CloneNotSupportedException e) { |
| 640 | throw new InternalError(e.toString()); |
| 641 | } |
| 642 | } |
| 643 | |
| 644 | //-------------------------------------------------------------------------- |
| 645 | // Static Utility methods |
| 646 | //-------------------------------------------------------------------------- |
| 647 | |
| 648 | /** |
| 649 | * Compose a string. |
| 650 | * The string will be composed to according the the specified mode. |
| 651 | * @param str The string to compose. |
| 652 | * @param compat If true the string will be composed accoding to |
| 653 | * NFKC rules and if false will be composed according to |
| 654 | * NFC rules. |
| 655 | * @param options The only recognized option is UNICODE_3_2 |
| 656 | * @return String The composed string |
| 657 | * @stable ICU 2.6 |
| 658 | */ |
| 659 | public static String compose(String str, boolean compat, int options) { |
| 660 | |
| 661 | char[] dest, src; |
| 662 | if (options == UNICODE_3_2_0_ORIGINAL) { |
| 663 | String mappedStr = NormalizerImpl.convert(str); |
| 664 | dest = new char[mappedStr.length()*MAX_BUF_SIZE_COMPOSE]; |
| 665 | src = mappedStr.toCharArray(); |
| 666 | } else { |
| 667 | dest = new char[str.length()*MAX_BUF_SIZE_COMPOSE]; |
| 668 | src = str.toCharArray(); |
| 669 | } |
| 670 | int destSize=0; |
| 671 | |
| 672 | UnicodeSet nx = NormalizerImpl.getNX(options); |
| 673 | |
| 674 | /* reset options bits that should only be set here or inside compose() */ |
| 675 | options&=~(NormalizerImpl.OPTIONS_SETS_MASK|NormalizerImpl.OPTIONS_COMPAT|NormalizerImpl.OPTIONS_COMPOSE_CONTIGUOUS); |
| 676 | |
| 677 | if(compat) { |
| 678 | options|=NormalizerImpl.OPTIONS_COMPAT; |
| 679 | } |
| 680 | |
| 681 | for(;;) { |
| 682 | destSize=NormalizerImpl.compose(src,0,src.length, |
| 683 | dest,0,dest.length,options, |
| 684 | nx); |
| 685 | if(destSize<=dest.length) { |
| 686 | return new String(dest,0,destSize); |
| 687 | } else { |
| 688 | dest = new char[destSize]; |
| 689 | } |
| 690 | } |
| 691 | } |
| 692 | |
| 693 | private static final int MAX_BUF_SIZE_COMPOSE = 2; |
| 694 | private static final int MAX_BUF_SIZE_DECOMPOSE = 3; |
| 695 | |
| 696 | /** |
| 697 | * Decompose a string. |
| 698 | * The string will be decomposed to according the the specified mode. |
| 699 | * @param str The string to decompose. |
| 700 | * @param compat If true the string will be decomposed accoding to NFKD |
| 701 | * rules and if false will be decomposed according to NFD |
| 702 | * rules. |
| 703 | * @return String The decomposed string |
| 704 | * @stable ICU 2.8 |
| 705 | */ |
| 706 | public static String decompose(String str, boolean compat) { |
| 707 | return decompose(str,compat,UNICODE_LATEST); |
| 708 | } |
| 709 | |
| 710 | /** |
| 711 | * Decompose a string. |
| 712 | * The string will be decomposed to according the the specified mode. |
| 713 | * @param str The string to decompose. |
| 714 | * @param compat If true the string will be decomposed accoding to NFKD |
| 715 | * rules and if false will be decomposed according to NFD |
| 716 | * rules. |
| 717 | * @param options The normalization options, ORed together (0 for no options). |
| 718 | * @return String The decomposed string |
| 719 | * @stable ICU 2.6 |
| 720 | */ |
| 721 | public static String decompose(String str, boolean compat, int options) { |
| 722 | |
| 723 | int[] trailCC = new int[1]; |
| 724 | int destSize=0; |
| 725 | UnicodeSet nx = NormalizerImpl.getNX(options); |
| 726 | char[] dest; |
| 727 | |
| 728 | if (options == UNICODE_3_2_0_ORIGINAL) { |
| 729 | String mappedStr = NormalizerImpl.convert(str); |
| 730 | dest = new char[mappedStr.length()*MAX_BUF_SIZE_DECOMPOSE]; |
| 731 | |
| 732 | for(;;) { |
| 733 | destSize=NormalizerImpl.decompose(mappedStr.toCharArray(),0,mappedStr.length(), |
| 734 | dest,0,dest.length, |
| 735 | compat,trailCC, nx); |
| 736 | if(destSize<=dest.length) { |
| 737 | return new String(dest,0,destSize); |
| 738 | } else { |
| 739 | dest = new char[destSize]; |
| 740 | } |
| 741 | } |
| 742 | } else { |
| 743 | dest = new char[str.length()*MAX_BUF_SIZE_DECOMPOSE]; |
| 744 | |
| 745 | for(;;) { |
| 746 | destSize=NormalizerImpl.decompose(str.toCharArray(),0,str.length(), |
| 747 | dest,0,dest.length, |
| 748 | compat,trailCC, nx); |
| 749 | if(destSize<=dest.length) { |
| 750 | return new String(dest,0,destSize); |
| 751 | } else { |
| 752 | dest = new char[destSize]; |
| 753 | } |
| 754 | } |
| 755 | } |
| 756 | } |
| 757 | |
| 758 | /** |
| 759 | * Normalize a string. |
| 760 | * The string will be normalized according the the specified normalization |
| 761 | * mode and options. |
| 762 | * @param src The char array to compose. |
| 763 | * @param srcStart Start index of the source |
| 764 | * @param srcLimit Limit index of the source |
| 765 | * @param dest The char buffer to fill in |
| 766 | * @param destStart Start index of the destination buffer |
| 767 | * @param destLimit End index of the destination buffer |
| 768 | * @param mode The normalization mode; one of Normalizer.NONE, |
| 769 | * Normalizer.NFD, Normalizer.NFC, Normalizer.NFKC, |
| 770 | * Normalizer.NFKD, Normalizer.DEFAULT |
| 771 | * @param options The normalization options, ORed together (0 for no options). |
| 772 | * @return int The total buffer size needed;if greater than length of |
| 773 | * result, the output was truncated. |
| 774 | * @exception IndexOutOfBoundsException if the target capacity is |
| 775 | * less than the required length |
| 776 | * @stable ICU 2.6 |
| 777 | */ |
| 778 | public static int normalize(char[] src,int srcStart, int srcLimit, |
| 779 | char[] dest,int destStart, int destLimit, |
| 780 | Mode mode, int options) { |
| 781 | int length = mode.normalize(src,srcStart,srcLimit,dest,destStart,destLimit, options); |
| 782 | |
| 783 | if(length<=(destLimit-destStart)) { |
| 784 | return length; |
| 785 | } else { |
| 786 | throw new IndexOutOfBoundsException(Integer.toString(length)); |
| 787 | } |
| 788 | } |
| 789 | |
| 790 | //------------------------------------------------------------------------- |
| 791 | // Iteration API |
| 792 | //------------------------------------------------------------------------- |
| 793 | |
| 794 | /** |
| 795 | * Return the current character in the normalized text-> |
| 796 | * @return The codepoint as an int |
| 797 | * @stable ICU 2.8 |
| 798 | */ |
| 799 | public int current() { |
| 800 | if(bufferPos<bufferLimit || nextNormalize()) { |
| 801 | return getCodePointAt(bufferPos); |
| 802 | } else { |
| 803 | return DONE; |
| 804 | } |
| 805 | } |
| 806 | |
| 807 | /** |
| 808 | * Return the next character in the normalized text and advance |
| 809 | * the iteration position by one. If the end |
| 810 | * of the text has already been reached, {@link #DONE} is returned. |
| 811 | * @return The codepoint as an int |
| 812 | * @stable ICU 2.8 |
| 813 | */ |
| 814 | public int next() { |
| 815 | if(bufferPos<bufferLimit || nextNormalize()) { |
| 816 | int c=getCodePointAt(bufferPos); |
| 817 | bufferPos+=(c>0xFFFF) ? 2 : 1; |
| 818 | return c; |
| 819 | } else { |
| 820 | return DONE; |
| 821 | } |
| 822 | } |
| 823 | |
| 824 | |
| 825 | /** |
| 826 | * Return the previous character in the normalized text and decrement |
| 827 | * the iteration position by one. If the beginning |
| 828 | * of the text has already been reached, {@link #DONE} is returned. |
| 829 | * @return The codepoint as an int |
| 830 | * @stable ICU 2.8 |
| 831 | */ |
| 832 | public int previous() { |
| 833 | if(bufferPos>0 || previousNormalize()) { |
| 834 | int c=getCodePointAt(bufferPos-1); |
| 835 | bufferPos-=(c>0xFFFF) ? 2 : 1; |
| 836 | return c; |
| 837 | } else { |
| 838 | return DONE; |
| 839 | } |
| 840 | } |
| 841 | |
| 842 | /** |
| 843 | * Reset the index to the beginning of the text. |
| 844 | * This is equivalent to setIndexOnly(startIndex)). |
| 845 | * @stable ICU 2.8 |
| 846 | */ |
| 847 | public void reset() { |
| 848 | text.setIndex(0); |
| 849 | currentIndex=nextIndex=0; |
| 850 | clearBuffer(); |
| 851 | } |
| 852 | |
| 853 | /** |
| 854 | * Set the iteration position in the input text that is being normalized, |
| 855 | * without any immediate normalization. |
| 856 | * After setIndexOnly(), getIndex() will return the same index that is |
| 857 | * specified here. |
| 858 | * |
| 859 | * @param index the desired index in the input text. |
| 860 | * @stable ICU 2.8 |
| 861 | */ |
| 862 | public void setIndexOnly(int index) { |
| 863 | text.setIndex(index); |
| 864 | currentIndex=nextIndex=index; // validates index |
| 865 | clearBuffer(); |
| 866 | } |
| 867 | |
| 868 | /** |
| 869 | * Set the iteration position in the input text that is being normalized |
| 870 | * and return the first normalized character at that position. |
| 871 | * <p> |
| 872 | * <b>Note:</b> This method sets the position in the <em>input</em> text, |
| 873 | * while {@link #next} and {@link #previous} iterate through characters |
| 874 | * in the normalized <em>output</em>. This means that there is not |
| 875 | * necessarily a one-to-one correspondence between characters returned |
| 876 | * by <tt>next</tt> and <tt>previous</tt> and the indices passed to and |
| 877 | * returned from <tt>setIndex</tt> and {@link #getIndex}. |
| 878 | * <p> |
| 879 | * @param index the desired index in the input text-> |
| 880 | * |
| 881 | * @return the first normalized character that is the result of iterating |
| 882 | * forward starting at the given index. |
| 883 | * |
| 884 | * @throws IllegalArgumentException if the given index is less than |
| 885 | * {@link #getBeginIndex} or greater than {@link #getEndIndex}. |
| 886 | * @return The codepoint as an int |
| 887 | * @deprecated ICU 3.2 |
| 888 | * @obsolete ICU 3.2 |
| 889 | */ |
| 890 | public int setIndex(int index) { |
| 891 | setIndexOnly(index); |
| 892 | return current(); |
| 893 | } |
| 894 | |
| 895 | /** |
| 896 | * Retrieve the index of the start of the input text. This is the begin |
| 897 | * index of the <tt>CharacterIterator</tt> or the start (i.e. 0) of the |
| 898 | * <tt>String</tt> over which this <tt>Normalizer</tt> is iterating |
| 899 | * @deprecated ICU 2.2. Use startIndex() instead. |
| 900 | * @return The codepoint as an int |
| 901 | * @see #startIndex |
| 902 | */ |
| 903 | public int getBeginIndex() { |
| 904 | return 0; |
| 905 | } |
| 906 | |
| 907 | /** |
| 908 | * Retrieve the index of the end of the input text. This is the end index |
| 909 | * of the <tt>CharacterIterator</tt> or the length of the <tt>String</tt> |
| 910 | * over which this <tt>Normalizer</tt> is iterating |
| 911 | * @deprecated ICU 2.2. Use endIndex() instead. |
| 912 | * @return The codepoint as an int |
| 913 | * @see #endIndex |
| 914 | */ |
| 915 | public int getEndIndex() { |
| 916 | return endIndex(); |
| 917 | } |
| 918 | |
| 919 | /** |
| 920 | * Retrieve the current iteration position in the input text that is |
| 921 | * being normalized. This method is useful in applications such as |
| 922 | * searching, where you need to be able to determine the position in |
| 923 | * the input text that corresponds to a given normalized output character. |
| 924 | * <p> |
| 925 | * <b>Note:</b> This method sets the position in the <em>input</em>, while |
| 926 | * {@link #next} and {@link #previous} iterate through characters in the |
| 927 | * <em>output</em>. This means that there is not necessarily a one-to-one |
| 928 | * correspondence between characters returned by <tt>next</tt> and |
| 929 | * <tt>previous</tt> and the indices passed to and returned from |
| 930 | * <tt>setIndex</tt> and {@link #getIndex}. |
| 931 | * @return The current iteration position |
| 932 | * @stable ICU 2.8 |
| 933 | */ |
| 934 | public int getIndex() { |
| 935 | if(bufferPos<bufferLimit) { |
| 936 | return currentIndex; |
| 937 | } else { |
| 938 | return nextIndex; |
| 939 | } |
| 940 | } |
| 941 | |
| 942 | /** |
| 943 | * Retrieve the index of the end of the input text-> This is the end index |
| 944 | * of the <tt>CharacterIterator</tt> or the length of the <tt>String</tt> |
| 945 | * over which this <tt>Normalizer</tt> is iterating |
| 946 | * @return The current iteration position |
| 947 | * @stable ICU 2.8 |
| 948 | */ |
| 949 | public int endIndex() { |
| 950 | return text.getLength(); |
| 951 | } |
| 952 | |
| 953 | //------------------------------------------------------------------------- |
| 954 | // Property access methods |
| 955 | //------------------------------------------------------------------------- |
| 956 | /** |
| 957 | * Set the normalization mode for this object. |
| 958 | * <p> |
| 959 | * <b>Note:</b>If the normalization mode is changed while iterating |
| 960 | * over a string, calls to {@link #next} and {@link #previous} may |
| 961 | * return previously buffers characters in the old normalization mode |
| 962 | * until the iteration is able to re-sync at the next base character. |
| 963 | * It is safest to call {@link #setText setText()}, {@link #first}, |
| 964 | * {@link #last}, etc. after calling <tt>setMode</tt>. |
| 965 | * <p> |
| 966 | * @param newMode the new mode for this <tt>Normalizer</tt>. |
| 967 | * The supported modes are: |
| 968 | * <ul> |
| 969 | * <li>{@link #COMPOSE} - Unicode canonical decompositiion |
| 970 | * followed by canonical composition. |
| 971 | * <li>{@link #COMPOSE_COMPAT} - Unicode compatibility decompositiion |
| 972 | * follwed by canonical composition. |
| 973 | * <li>{@link #DECOMP} - Unicode canonical decomposition |
| 974 | * <li>{@link #DECOMP_COMPAT} - Unicode compatibility decomposition. |
| 975 | * <li>{@link #NO_OP} - Do nothing but return characters |
| 976 | * from the underlying input text. |
| 977 | * </ul> |
| 978 | * |
| 979 | * @see #getMode |
| 980 | * @stable ICU 2.8 |
| 981 | */ |
| 982 | public void setMode(Mode newMode) { |
| 983 | mode = newMode; |
| 984 | } |
| 985 | /** |
| 986 | * Return the basic operation performed by this <tt>Normalizer</tt> |
| 987 | * |
| 988 | * @see #setMode |
| 989 | * @stable ICU 2.8 |
| 990 | */ |
| 991 | public Mode getMode() { |
| 992 | return mode; |
| 993 | } |
| 994 | |
| 995 | /** |
| 996 | * Set the input text over which this <tt>Normalizer</tt> will iterate. |
| 997 | * The iteration position is set to the beginning of the input text-> |
| 998 | * @param newText The new string to be normalized. |
| 999 | * @stable ICU 2.8 |
| 1000 | */ |
| 1001 | public void setText(String newText) { |
| 1002 | |
| 1003 | UCharacterIterator newIter = UCharacterIterator.getInstance(newText); |
| 1004 | if (newIter == null) { |
| 1005 | throw new InternalError("Could not create a new UCharacterIterator"); |
| 1006 | } |
| 1007 | text = newIter; |
| 1008 | reset(); |
| 1009 | } |
| 1010 | |
| 1011 | /** |
| 1012 | * Set the input text over which this <tt>Normalizer</tt> will iterate. |
| 1013 | * The iteration position is set to the beginning of the input text-> |
| 1014 | * @param newText The new string to be normalized. |
| 1015 | * @stable ICU 2.8 |
| 1016 | */ |
| 1017 | public void setText(CharacterIterator newText) { |
| 1018 | |
| 1019 | UCharacterIterator newIter = UCharacterIterator.getInstance(newText); |
| 1020 | if (newIter == null) { |
| 1021 | throw new InternalError("Could not create a new UCharacterIterator"); |
| 1022 | } |
| 1023 | text = newIter; |
| 1024 | currentIndex=nextIndex=0; |
| 1025 | clearBuffer(); |
| 1026 | } |
| 1027 | |
| 1028 | //------------------------------------------------------------------------- |
| 1029 | // Private utility methods |
| 1030 | //------------------------------------------------------------------------- |
| 1031 | |
| 1032 | |
| 1033 | /* backward iteration --------------------------------------------------- */ |
| 1034 | |
| 1035 | /* |
| 1036 | * read backwards and get norm32 |
| 1037 | * return 0 if the character is <minC |
| 1038 | * if c2!=0 then (c2, c) is a surrogate pair (reversed - c2 is first |
| 1039 | * surrogate but read second!) |
| 1040 | */ |
| 1041 | |
| 1042 | private static long getPrevNorm32(UCharacterIterator src, |
| 1043 | int/*unsigned*/ minC, |
| 1044 | int/*unsigned*/ mask, |
| 1045 | char[] chars) { |
| 1046 | long norm32; |
| 1047 | int ch=0; |
| 1048 | /* need src.hasPrevious() */ |
| 1049 | if((ch=src.previous()) == UCharacterIterator.DONE) { |
| 1050 | return 0; |
| 1051 | } |
| 1052 | chars[0]=(char)ch; |
| 1053 | chars[1]=0; |
| 1054 | |
| 1055 | /* check for a surrogate before getting norm32 to see if we need to |
| 1056 | * predecrement further */ |
| 1057 | if(chars[0]<minC) { |
| 1058 | return 0; |
| 1059 | } else if(!UTF16.isSurrogate(chars[0])) { |
| 1060 | return NormalizerImpl.getNorm32(chars[0]); |
| 1061 | } else if(UTF16.isLeadSurrogate(chars[0]) || (src.getIndex()==0)) { |
| 1062 | /* unpaired surrogate */ |
| 1063 | chars[1]=(char)src.current(); |
| 1064 | return 0; |
| 1065 | } else if(UTF16.isLeadSurrogate(chars[1]=(char)src.previous())) { |
| 1066 | norm32=NormalizerImpl.getNorm32(chars[1]); |
| 1067 | if((norm32&mask)==0) { |
| 1068 | /* all surrogate pairs with this lead surrogate have irrelevant |
| 1069 | * data */ |
| 1070 | return 0; |
| 1071 | } else { |
| 1072 | /* norm32 must be a surrogate special */ |
| 1073 | return NormalizerImpl.getNorm32FromSurrogatePair(norm32,chars[0]); |
| 1074 | } |
| 1075 | } else { |
| 1076 | /* unpaired second surrogate, undo the c2=src.previous() movement */ |
| 1077 | src.moveIndex( 1); |
| 1078 | return 0; |
| 1079 | } |
| 1080 | } |
| 1081 | |
| 1082 | private interface IsPrevBoundary{ |
| 1083 | public boolean isPrevBoundary(UCharacterIterator src, |
| 1084 | int/*unsigned*/ minC, |
| 1085 | int/*unsigned*/ mask, |
| 1086 | char[] chars); |
| 1087 | } |
| 1088 | private static final class IsPrevNFDSafe implements IsPrevBoundary{ |
| 1089 | /* |
| 1090 | * for NF*D: |
| 1091 | * read backwards and check if the lead combining class is 0 |
| 1092 | * if c2!=0 then (c2, c) is a surrogate pair (reversed - c2 is first |
| 1093 | * surrogate but read second!) |
| 1094 | */ |
| 1095 | public boolean isPrevBoundary(UCharacterIterator src, |
| 1096 | int/*unsigned*/ minC, |
| 1097 | int/*unsigned*/ ccOrQCMask, |
| 1098 | char[] chars) { |
| 1099 | |
| 1100 | return NormalizerImpl.isNFDSafe(getPrevNorm32(src, minC, |
| 1101 | ccOrQCMask, chars), |
| 1102 | ccOrQCMask, |
| 1103 | ccOrQCMask& NormalizerImpl.QC_MASK); |
| 1104 | } |
| 1105 | } |
| 1106 | |
| 1107 | private static final class IsPrevTrueStarter implements IsPrevBoundary{ |
| 1108 | /* |
| 1109 | * read backwards and check if the character is (or its decomposition |
| 1110 | * begins with) a "true starter" (cc==0 and NF*C_YES) |
| 1111 | * if c2!=0 then (c2, c) is a surrogate pair (reversed - c2 is first |
| 1112 | * surrogate but read second!) |
| 1113 | */ |
| 1114 | public boolean isPrevBoundary(UCharacterIterator src, |
| 1115 | int/*unsigned*/ minC, |
| 1116 | int/*unsigned*/ ccOrQCMask, |
| 1117 | char[] chars) { |
| 1118 | long norm32; |
| 1119 | int/*unsigned*/ decompQCMask; |
| 1120 | |
| 1121 | decompQCMask=(ccOrQCMask<<2)&0xf; /*decomposition quick check mask*/ |
| 1122 | norm32=getPrevNorm32(src, minC, ccOrQCMask|decompQCMask, chars); |
| 1123 | return NormalizerImpl.isTrueStarter(norm32,ccOrQCMask,decompQCMask); |
| 1124 | } |
| 1125 | } |
| 1126 | |
| 1127 | private static int findPreviousIterationBoundary(UCharacterIterator src, |
| 1128 | IsPrevBoundary obj, |
| 1129 | int/*unsigned*/ minC, |
| 1130 | int/*mask*/ mask, |
| 1131 | char[] buffer, |
| 1132 | int[] startIndex) { |
| 1133 | char[] chars=new char[2]; |
| 1134 | boolean isBoundary; |
| 1135 | |
| 1136 | /* fill the buffer from the end backwards */ |
| 1137 | startIndex[0] = buffer.length; |
| 1138 | chars[0]=0; |
| 1139 | while(src.getIndex()>0 && chars[0]!=UCharacterIterator.DONE) { |
| 1140 | isBoundary=obj.isPrevBoundary(src, minC, mask, chars); |
| 1141 | |
| 1142 | /* always write this character to the front of the buffer */ |
| 1143 | /* make sure there is enough space in the buffer */ |
| 1144 | if(startIndex[0] < (chars[1]==0 ? 1 : 2)) { |
| 1145 | |
| 1146 | // grow the buffer |
| 1147 | char[] newBuf = new char[buffer.length*2]; |
| 1148 | /* move the current buffer contents up */ |
| 1149 | System.arraycopy(buffer,startIndex[0],newBuf, |
| 1150 | newBuf.length-(buffer.length-startIndex[0]), |
| 1151 | buffer.length-startIndex[0]); |
| 1152 | //adjust the startIndex |
| 1153 | startIndex[0]+=newBuf.length-buffer.length; |
| 1154 | |
| 1155 | buffer=newBuf; |
| 1156 | newBuf=null; |
| 1157 | |
| 1158 | } |
| 1159 | |
| 1160 | buffer[--startIndex[0]]=chars[0]; |
| 1161 | if(chars[1]!=0) { |
| 1162 | buffer[--startIndex[0]]=chars[1]; |
| 1163 | } |
| 1164 | |
| 1165 | /* stop if this just-copied character is a boundary */ |
| 1166 | if(isBoundary) { |
| 1167 | break; |
| 1168 | } |
| 1169 | } |
| 1170 | |
| 1171 | /* return the length of the buffer contents */ |
| 1172 | return buffer.length-startIndex[0]; |
| 1173 | } |
| 1174 | |
| 1175 | private static int previous(UCharacterIterator src, |
| 1176 | char[] dest, int destStart, int destLimit, |
| 1177 | Mode mode, |
| 1178 | boolean doNormalize, |
| 1179 | boolean[] pNeededToNormalize, |
| 1180 | int options) { |
| 1181 | |
| 1182 | IsPrevBoundary isPreviousBoundary; |
| 1183 | int destLength, bufferLength; |
| 1184 | int/*unsigned*/ mask; |
| 1185 | int c,c2; |
| 1186 | |
| 1187 | char minC; |
| 1188 | int destCapacity = destLimit-destStart; |
| 1189 | destLength=0; |
| 1190 | |
| 1191 | if(pNeededToNormalize!=null) { |
| 1192 | pNeededToNormalize[0]=false; |
| 1193 | } |
| 1194 | minC = (char)mode.getMinC(); |
| 1195 | mask = mode.getMask(); |
| 1196 | isPreviousBoundary = mode.getPrevBoundary(); |
| 1197 | |
| 1198 | if(isPreviousBoundary==null) { |
| 1199 | destLength=0; |
| 1200 | if((c=src.previous())>=0) { |
| 1201 | destLength=1; |
| 1202 | if(UTF16.isTrailSurrogate((char)c)) { |
| 1203 | c2= src.previous(); |
| 1204 | if(c2!= UCharacterIterator.DONE) { |
| 1205 | if(UTF16.isLeadSurrogate((char)c2)) { |
| 1206 | if(destCapacity>=2) { |
| 1207 | dest[1]=(char)c; // trail surrogate |
| 1208 | destLength=2; |
| 1209 | } |
| 1210 | // lead surrogate to be written below |
| 1211 | c=c2; |
| 1212 | } else { |
| 1213 | src.moveIndex(1); |
| 1214 | } |
| 1215 | } |
| 1216 | } |
| 1217 | |
| 1218 | if(destCapacity>0) { |
| 1219 | dest[0]=(char)c; |
| 1220 | } |
| 1221 | } |
| 1222 | return destLength; |
| 1223 | } |
| 1224 | |
| 1225 | char[] buffer = new char[100]; |
| 1226 | int[] startIndex= new int[1]; |
| 1227 | bufferLength=findPreviousIterationBoundary(src, |
| 1228 | isPreviousBoundary, |
| 1229 | minC, mask,buffer, |
| 1230 | startIndex); |
| 1231 | if(bufferLength>0) { |
| 1232 | if(doNormalize) { |
| 1233 | destLength=NormalizerBase.normalize(buffer,startIndex[0], |
| 1234 | startIndex[0]+bufferLength, |
| 1235 | dest, destStart,destLimit, |
| 1236 | mode, options); |
| 1237 | |
| 1238 | if(pNeededToNormalize!=null) { |
| 1239 | pNeededToNormalize[0]=(boolean)(destLength!=bufferLength || |
| 1240 | Utility.arrayRegionMatches( |
| 1241 | buffer,0,dest, |
| 1242 | destStart,destLimit |
| 1243 | )); |
| 1244 | } |
| 1245 | } else { |
| 1246 | /* just copy the source characters */ |
| 1247 | if(destCapacity>0) { |
| 1248 | System.arraycopy(buffer,startIndex[0],dest,0, |
| 1249 | (bufferLength<destCapacity) ? |
| 1250 | bufferLength : destCapacity |
| 1251 | ); |
| 1252 | } |
| 1253 | } |
| 1254 | } |
| 1255 | |
| 1256 | |
| 1257 | return destLength; |
| 1258 | } |
| 1259 | |
| 1260 | |
| 1261 | |
| 1262 | /* forward iteration ---------------------------------------------------- */ |
| 1263 | /* |
| 1264 | * read forward and check if the character is a next-iteration boundary |
| 1265 | * if c2!=0 then (c, c2) is a surrogate pair |
| 1266 | */ |
| 1267 | private interface IsNextBoundary{ |
| 1268 | boolean isNextBoundary(UCharacterIterator src, |
| 1269 | int/*unsigned*/ minC, |
| 1270 | int/*unsigned*/ mask, |
| 1271 | int[] chars); |
| 1272 | } |
| 1273 | /* |
| 1274 | * read forward and get norm32 |
| 1275 | * return 0 if the character is <minC |
| 1276 | * if c2!=0 then (c2, c) is a surrogate pair |
| 1277 | * always reads complete characters |
| 1278 | */ |
| 1279 | private static long /*unsigned*/ getNextNorm32(UCharacterIterator src, |
| 1280 | int/*unsigned*/ minC, |
| 1281 | int/*unsigned*/ mask, |
| 1282 | int[] chars) { |
| 1283 | long norm32; |
| 1284 | |
| 1285 | /* need src.hasNext() to be true */ |
| 1286 | chars[0]=src.next(); |
| 1287 | chars[1]=0; |
| 1288 | |
| 1289 | if(chars[0]<minC) { |
| 1290 | return 0; |
| 1291 | } |
| 1292 | |
| 1293 | norm32=NormalizerImpl.getNorm32((char)chars[0]); |
| 1294 | if(UTF16.isLeadSurrogate((char)chars[0])) { |
| 1295 | if(src.current()!=UCharacterIterator.DONE && |
| 1296 | UTF16.isTrailSurrogate((char)(chars[1]=src.current()))) { |
| 1297 | src.moveIndex(1); /* skip the c2 surrogate */ |
| 1298 | if((norm32&mask)==0) { |
| 1299 | /* irrelevant data */ |
| 1300 | return 0; |
| 1301 | } else { |
| 1302 | /* norm32 must be a surrogate special */ |
| 1303 | return NormalizerImpl.getNorm32FromSurrogatePair(norm32,(char)chars[1]); |
| 1304 | } |
| 1305 | } else { |
| 1306 | /* unmatched surrogate */ |
| 1307 | return 0; |
| 1308 | } |
| 1309 | } |
| 1310 | return norm32; |
| 1311 | } |
| 1312 | |
| 1313 | |
| 1314 | /* |
| 1315 | * for NF*D: |
| 1316 | * read forward and check if the lead combining class is 0 |
| 1317 | * if c2!=0 then (c, c2) is a surrogate pair |
| 1318 | */ |
| 1319 | private static final class IsNextNFDSafe implements IsNextBoundary{ |
| 1320 | public boolean isNextBoundary(UCharacterIterator src, |
| 1321 | int/*unsigned*/ minC, |
| 1322 | int/*unsigned*/ ccOrQCMask, |
| 1323 | int[] chars) { |
| 1324 | return NormalizerImpl.isNFDSafe(getNextNorm32(src,minC,ccOrQCMask,chars), |
| 1325 | ccOrQCMask, ccOrQCMask&NormalizerImpl.QC_MASK); |
| 1326 | } |
| 1327 | } |
| 1328 | |
| 1329 | /* |
| 1330 | * for NF*C: |
| 1331 | * read forward and check if the character is (or its decomposition begins |
| 1332 | * with) a "true starter" (cc==0 and NF*C_YES) |
| 1333 | * if c2!=0 then (c, c2) is a surrogate pair |
| 1334 | */ |
| 1335 | private static final class IsNextTrueStarter implements IsNextBoundary{ |
| 1336 | public boolean isNextBoundary(UCharacterIterator src, |
| 1337 | int/*unsigned*/ minC, |
| 1338 | int/*unsigned*/ ccOrQCMask, |
| 1339 | int[] chars) { |
| 1340 | long norm32; |
| 1341 | int/*unsigned*/ decompQCMask; |
| 1342 | |
| 1343 | decompQCMask=(ccOrQCMask<<2)&0xf; /*decomposition quick check mask*/ |
| 1344 | norm32=getNextNorm32(src, minC, ccOrQCMask|decompQCMask, chars); |
| 1345 | return NormalizerImpl.isTrueStarter(norm32, ccOrQCMask, decompQCMask); |
| 1346 | } |
| 1347 | } |
| 1348 | |
| 1349 | private static int findNextIterationBoundary(UCharacterIterator src, |
| 1350 | IsNextBoundary obj, |
| 1351 | int/*unsigned*/ minC, |
| 1352 | int/*unsigned*/ mask, |
| 1353 | char[] buffer) { |
| 1354 | if(src.current()==UCharacterIterator.DONE) { |
| 1355 | return 0; |
| 1356 | } |
| 1357 | |
| 1358 | /* get one character and ignore its properties */ |
| 1359 | int[] chars = new int[2]; |
| 1360 | chars[0]=src.next(); |
| 1361 | buffer[0]=(char)chars[0]; |
| 1362 | int bufferIndex = 1; |
| 1363 | |
| 1364 | if(UTF16.isLeadSurrogate((char)chars[0])&& |
| 1365 | src.current()!=UCharacterIterator.DONE) { |
| 1366 | if(UTF16.isTrailSurrogate((char)(chars[1]=src.next()))) { |
| 1367 | buffer[bufferIndex++]=(char)chars[1]; |
| 1368 | } else { |
| 1369 | src.moveIndex(-1); /* back out the non-trail-surrogate */ |
| 1370 | } |
| 1371 | } |
| 1372 | |
| 1373 | /* get all following characters until we see a boundary */ |
| 1374 | /* checking hasNext() instead of c!=DONE on the off-chance that U+ffff |
| 1375 | * is part of the string */ |
| 1376 | while( src.current()!=UCharacterIterator.DONE) { |
| 1377 | if(obj.isNextBoundary(src, minC, mask, chars)) { |
| 1378 | /* back out the latest movement to stop at the boundary */ |
| 1379 | src.moveIndex(chars[1]==0 ? -1 : -2); |
| 1380 | break; |
| 1381 | } else { |
| 1382 | if(bufferIndex+(chars[1]==0 ? 1 : 2)<=buffer.length) { |
| 1383 | buffer[bufferIndex++]=(char)chars[0]; |
| 1384 | if(chars[1]!=0) { |
| 1385 | buffer[bufferIndex++]=(char)chars[1]; |
| 1386 | } |
| 1387 | } else { |
| 1388 | char[] newBuf = new char[buffer.length*2]; |
| 1389 | System.arraycopy(buffer,0,newBuf,0,bufferIndex); |
| 1390 | buffer = newBuf; |
| 1391 | buffer[bufferIndex++]=(char)chars[0]; |
| 1392 | if(chars[1]!=0) { |
| 1393 | buffer[bufferIndex++]=(char)chars[1]; |
| 1394 | } |
| 1395 | } |
| 1396 | } |
| 1397 | } |
| 1398 | |
| 1399 | /* return the length of the buffer contents */ |
| 1400 | return bufferIndex; |
| 1401 | } |
| 1402 | |
| 1403 | private static int next(UCharacterIterator src, |
| 1404 | char[] dest, int destStart, int destLimit, |
| 1405 | NormalizerBase.Mode mode, |
| 1406 | boolean doNormalize, |
| 1407 | boolean[] pNeededToNormalize, |
| 1408 | int options) { |
| 1409 | |
| 1410 | IsNextBoundary isNextBoundary; |
| 1411 | int /*unsigned*/ mask; |
| 1412 | int /*unsigned*/ bufferLength; |
| 1413 | int c,c2; |
| 1414 | char minC; |
| 1415 | int destCapacity = destLimit - destStart; |
| 1416 | int destLength = 0; |
| 1417 | if(pNeededToNormalize!=null) { |
| 1418 | pNeededToNormalize[0]=false; |
| 1419 | } |
| 1420 | |
| 1421 | minC = (char)mode.getMinC(); |
| 1422 | mask = mode.getMask(); |
| 1423 | isNextBoundary = mode.getNextBoundary(); |
| 1424 | |
| 1425 | if(isNextBoundary==null) { |
| 1426 | destLength=0; |
| 1427 | c=src.next(); |
| 1428 | if(c!=UCharacterIterator.DONE) { |
| 1429 | destLength=1; |
| 1430 | if(UTF16.isLeadSurrogate((char)c)) { |
| 1431 | c2= src.next(); |
| 1432 | if(c2!= UCharacterIterator.DONE) { |
| 1433 | if(UTF16.isTrailSurrogate((char)c2)) { |
| 1434 | if(destCapacity>=2) { |
| 1435 | dest[1]=(char)c2; // trail surrogate |
| 1436 | destLength=2; |
| 1437 | } |
| 1438 | // lead surrogate to be written below |
| 1439 | } else { |
| 1440 | src.moveIndex(-1); |
| 1441 | } |
| 1442 | } |
| 1443 | } |
| 1444 | |
| 1445 | if(destCapacity>0) { |
| 1446 | dest[0]=(char)c; |
| 1447 | } |
| 1448 | } |
| 1449 | return destLength; |
| 1450 | } |
| 1451 | |
| 1452 | char[] buffer=new char[100]; |
| 1453 | int[] startIndex = new int[1]; |
| 1454 | bufferLength=findNextIterationBoundary(src,isNextBoundary, minC, mask, |
| 1455 | buffer); |
| 1456 | if(bufferLength>0) { |
| 1457 | if(doNormalize) { |
| 1458 | destLength=mode.normalize(buffer,startIndex[0],bufferLength, |
| 1459 | dest,destStart,destLimit, options); |
| 1460 | |
| 1461 | if(pNeededToNormalize!=null) { |
| 1462 | pNeededToNormalize[0]=(boolean)(destLength!=bufferLength || |
| 1463 | Utility.arrayRegionMatches(buffer,startIndex[0], |
| 1464 | dest,destStart, |
| 1465 | destLength)); |
| 1466 | } |
| 1467 | } else { |
| 1468 | /* just copy the source characters */ |
| 1469 | if(destCapacity>0) { |
| 1470 | System.arraycopy(buffer,0,dest,destStart, |
| 1471 | Math.min(bufferLength,destCapacity) |
| 1472 | ); |
| 1473 | } |
| 1474 | |
| 1475 | |
| 1476 | } |
| 1477 | } |
| 1478 | return destLength; |
| 1479 | } |
| 1480 | |
| 1481 | private void clearBuffer() { |
| 1482 | bufferLimit=bufferStart=bufferPos=0; |
| 1483 | } |
| 1484 | |
| 1485 | private boolean nextNormalize() { |
| 1486 | |
| 1487 | clearBuffer(); |
| 1488 | currentIndex=nextIndex; |
| 1489 | text.setIndex(nextIndex); |
| 1490 | |
| 1491 | bufferLimit=next(text,buffer,bufferStart,buffer.length,mode,true,null,options); |
| 1492 | |
| 1493 | nextIndex=text.getIndex(); |
| 1494 | return (bufferLimit>0); |
| 1495 | } |
| 1496 | |
| 1497 | private boolean previousNormalize() { |
| 1498 | |
| 1499 | clearBuffer(); |
| 1500 | nextIndex=currentIndex; |
| 1501 | text.setIndex(currentIndex); |
| 1502 | bufferLimit=previous(text,buffer,bufferStart,buffer.length,mode,true,null,options); |
| 1503 | |
| 1504 | currentIndex=text.getIndex(); |
| 1505 | bufferPos = bufferLimit; |
| 1506 | return bufferLimit>0; |
| 1507 | } |
| 1508 | |
| 1509 | private int getCodePointAt(int index) { |
| 1510 | if( UTF16.isSurrogate(buffer[index])) { |
| 1511 | if(UTF16.isLeadSurrogate(buffer[index])) { |
| 1512 | if((index+1)<bufferLimit && |
| 1513 | UTF16.isTrailSurrogate(buffer[index+1])) { |
| 1514 | return UCharacterProperty.getRawSupplementary( |
| 1515 | buffer[index], |
| 1516 | buffer[index+1] |
| 1517 | ); |
| 1518 | } |
| 1519 | }else if(UTF16.isTrailSurrogate(buffer[index])) { |
| 1520 | if(index>0 && UTF16.isLeadSurrogate(buffer[index-1])) { |
| 1521 | return UCharacterProperty.getRawSupplementary( |
| 1522 | buffer[index-1], |
| 1523 | buffer[index] |
| 1524 | ); |
| 1525 | } |
| 1526 | } |
| 1527 | } |
| 1528 | return buffer[index]; |
| 1529 | |
| 1530 | } |
| 1531 | |
| 1532 | /** |
| 1533 | * Internal API |
| 1534 | * @internal |
| 1535 | */ |
| 1536 | public static boolean isNFSkippable(int c, Mode mode) { |
| 1537 | return mode.isNFSkippable(c); |
| 1538 | } |
| 1539 | |
| 1540 | // |
| 1541 | // Options |
| 1542 | // |
| 1543 | |
| 1544 | /* |
| 1545 | * Default option for Unicode 3.2.0 normalization. |
| 1546 | * Corrigendum 4 was fixed in Unicode 3.2.0 but isn't supported in |
| 1547 | * IDNA/StringPrep. |
| 1548 | * The public review issue #29 was fixed in Unicode 4.1.0. Corrigendum 5 |
| 1549 | * allowed Unicode 3.2 to 4.0.1 to apply the fix for PRI #29, but it isn't |
| 1550 | * supported by IDNA/StringPrep as well as Corrigendum 4. |
| 1551 | */ |
| 1552 | public static final int UNICODE_3_2_0_ORIGINAL = |
| 1553 | UNICODE_3_2 | |
| 1554 | NormalizerImpl.WITHOUT_CORRIGENDUM4_CORRECTIONS | |
| 1555 | NormalizerImpl.BEFORE_PRI_29; |
| 1556 | |
| 1557 | /* |
| 1558 | * Default option for the latest Unicode normalization. This option is |
| 1559 | * provided mainly for testing. |
| 1560 | * The value zero means that normalization is done with the fixes for |
| 1561 | * - Corrigendum 4 (Five CJK Canonical Mapping Errors) |
| 1562 | * - Corrigendum 5 (Normalization Idempotency) |
| 1563 | */ |
| 1564 | public static final int UNICODE_LATEST = 0x00; |
| 1565 | |
| 1566 | // |
| 1567 | // public constructor and methods for java.text.Normalizer and |
| 1568 | // sun.text.Normalizer |
| 1569 | // |
| 1570 | |
| 1571 | /** |
| 1572 | * Creates a new <tt>Normalizer</tt> object for iterating over the |
| 1573 | * normalized form of a given string. |
| 1574 | * |
| 1575 | * @param str The string to be normalized. The normalization |
| 1576 | * will start at the beginning of the string. |
| 1577 | * |
| 1578 | * @param mode The normalization mode. |
| 1579 | */ |
| 1580 | public NormalizerBase(String str, Mode mode) { |
| 1581 | this(str, mode, UNICODE_LATEST); |
| 1582 | } |
| 1583 | |
| 1584 | /** |
| 1585 | * Normalizes a <code>String</code> using the given normalization form. |
| 1586 | * |
| 1587 | * @param str the input string to be normalized. |
| 1588 | * @param form the normalization form |
| 1589 | */ |
| 1590 | public static String normalize(String str, Normalizer.Form form) { |
| 1591 | return normalize(str, form, UNICODE_LATEST); |
| 1592 | } |
| 1593 | |
| 1594 | /** |
| 1595 | * Normalizes a <code>String</code> using the given normalization form. |
| 1596 | * |
| 1597 | * @param str the input string to be normalized. |
| 1598 | * @param form the normalization form |
| 1599 | * @param options the optional features to be enabled. |
| 1600 | */ |
| 1601 | public static String normalize(String str, Normalizer.Form form, int options) { |
| 1602 | switch (form) { |
| 1603 | case NFC : |
| 1604 | return NFC.normalize(str, options); |
| 1605 | case NFD : |
| 1606 | return NFD.normalize(str, options); |
| 1607 | case NFKC : |
| 1608 | return NFKC.normalize(str, options); |
| 1609 | case NFKD : |
| 1610 | return NFKD.normalize(str, options); |
| 1611 | } |
| 1612 | |
| 1613 | throw new IllegalArgumentException("Unexpected normalization form: " + |
| 1614 | form); |
| 1615 | } |
| 1616 | |
| 1617 | /** |
| 1618 | * Test if a string is in a given normalization form. |
| 1619 | * This is semantically equivalent to source.equals(normalize(source, mode)). |
| 1620 | * |
| 1621 | * Unlike quickCheck(), this function returns a definitive result, |
| 1622 | * never a "maybe". |
| 1623 | * For NFD, NFKD, and FCD, both functions work exactly the same. |
| 1624 | * For NFC and NFKC where quickCheck may return "maybe", this function will |
| 1625 | * perform further tests to arrive at a true/false result. |
| 1626 | * @param str the input string to be checked to see if it is normalized |
| 1627 | * @param form the normalization form |
| 1628 | * @param options the optional features to be enabled. |
| 1629 | */ |
| 1630 | public static boolean isNormalized(String str, Normalizer.Form form) { |
| 1631 | return isNormalized(str, form, UNICODE_LATEST); |
| 1632 | } |
| 1633 | |
| 1634 | /** |
| 1635 | * Test if a string is in a given normalization form. |
| 1636 | * This is semantically equivalent to source.equals(normalize(source, mode)). |
| 1637 | * |
| 1638 | * Unlike quickCheck(), this function returns a definitive result, |
| 1639 | * never a "maybe". |
| 1640 | * For NFD, NFKD, and FCD, both functions work exactly the same. |
| 1641 | * For NFC and NFKC where quickCheck may return "maybe", this function will |
| 1642 | * perform further tests to arrive at a true/false result. |
| 1643 | * @param str the input string to be checked to see if it is normalized |
| 1644 | * @param form the normalization form |
| 1645 | * @param options the optional features to be enabled. |
| 1646 | */ |
| 1647 | public static boolean isNormalized(String str, Normalizer.Form form, int options) { |
| 1648 | switch (form) { |
| 1649 | case NFC: |
| 1650 | return (NFC.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); |
| 1651 | case NFD: |
| 1652 | return (NFD.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); |
| 1653 | case NFKC: |
| 1654 | return (NFKC.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); |
| 1655 | case NFKD: |
| 1656 | return (NFKD.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); |
| 1657 | } |
| 1658 | |
| 1659 | throw new IllegalArgumentException("Unexpected normalization form: " + |
| 1660 | form); |
| 1661 | } |
| 1662 | } |