Showing the changes to java/pkg/sun/text/normalizer/NormalizerBase.java (1 of 18352 files). Show all
Unified · Split
| @@ -0,0 +1,1680 @@ | |||
| 1 | /* | ||
| 2 | * Copyright (c) 2005, 2009, Oracle and/or its affiliates. All rights reserved. | ||
| 3 | * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. | ||
| 4 | * | ||
| 5 | * This code is free software; you can redistribute it and/or modify it | ||
| 6 | * under the terms of the GNU General Public License version 2 only, as | ||
| 7 | * published by the Free Software Foundation. Oracle designates this | ||
| 8 | * particular file as subject to the "Classpath" exception as provided | ||
| 9 | * by Oracle in the LICENSE file that accompanied this code. | ||
| 10 | * | ||
| 11 | * This code is distributed in the hope that it will be useful, but WITHOUT | ||
| 12 | * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
| 13 | * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License | ||
| 14 | * version 2 for more details (a copy is included in the LICENSE file that | ||
| 15 | * accompanied this code). | ||
| 16 | * | ||
| 17 | * You should have received a copy of the GNU General Public License version | ||
| 18 | * 2 along with this work; if not, write to the Free Software Foundation, | ||
| 19 | * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. | ||
| 20 | * | ||
| 21 | * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA | ||
| 22 | * or visit www.oracle.com if you need additional information or have any | ||
| 23 | * questions. | ||
| 24 | */ | ||
| 25 | /* | ||
| 26 | ******************************************************************************* | ||
| 27 | * (C) Copyright IBM Corp. and others, 1996-2009 - All Rights Reserved * | ||
| 28 | * * | ||
| 29 | * The original version of this source code and documentation is copyrighted * | ||
| 30 | * and owned by IBM, These materials are provided under terms of a License * | ||
| 31 | * Agreement between IBM and Sun. This technology is protected by multiple * | ||
| 32 | * US and International patents. This notice and attribution to IBM may not * | ||
| 33 | * to removed. * | ||
| 34 | ******************************************************************************* | ||
| 35 | */ | ||
| 36 | |||
| 37 | package sun.text.normalizer; | ||
| 38 | |||
| 39 | import java.text.CharacterIterator; | ||
| 40 | import java.text.Normalizer; | ||
| 41 | |||
| 42 | /** | ||
| 43 | * Unicode Normalization | ||
| 44 | * | ||
| 45 | * <h2>Unicode normalization API</h2> | ||
| 46 | * | ||
| 47 | * <code>normalize</code> transforms Unicode text into an equivalent composed or | ||
| 48 | * decomposed form, allowing for easier sorting and searching of text. | ||
| 49 | * <code>normalize</code> supports the standard normalization forms described in | ||
| 50 | * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> | ||
| 51 | * Unicode Standard Annex #15 — Unicode Normalization Forms</a>. | ||
| 52 | * | ||
| 53 | * Characters with accents or other adornments can be encoded in | ||
| 54 | * several different ways in Unicode. For example, take the character A-acute. | ||
| 55 | * In Unicode, this can be encoded as a single character (the | ||
| 56 | * "composed" form): | ||
| 57 | * | ||
| 58 | * <p> | ||
| 59 | * 00C1 LATIN CAPITAL LETTER A WITH ACUTE | ||
| 60 | * </p> | ||
| 61 | * | ||
| 62 | * or as two separate characters (the "decomposed" form): | ||
| 63 | * | ||
| 64 | * <p> | ||
| 65 | * 0041 LATIN CAPITAL LETTER A | ||
| 66 | * 0301 COMBINING ACUTE ACCENT | ||
| 67 | * </p> | ||
| 68 | * | ||
| 69 | * To a user of your program, however, both of these sequences should be | ||
| 70 | * treated as the same "user-level" character "A with acute accent". When you | ||
| 71 | * are searching or comparing text, you must ensure that these two sequences are | ||
| 72 | * treated equivalently. In addition, you must handle characters with more than | ||
| 73 | * one accent. Sometimes the order of a character's combining accents is | ||
| 74 | * significant, while in other cases accent sequences in different orders are | ||
| 75 | * really equivalent. | ||
| 76 | * | ||
| 77 | * Similarly, the string "ffi" can be encoded as three separate letters: | ||
| 78 | * | ||
| 79 | * <p> | ||
| 80 | * 0066 LATIN SMALL LETTER F | ||
| 81 | * 0066 LATIN SMALL LETTER F | ||
| 82 | * 0069 LATIN SMALL LETTER I | ||
| 83 | * </p> | ||
| 84 | * | ||
| 85 | * or as the single character | ||
| 86 | * | ||
| 87 | * <p> | ||
| 88 | * FB03 LATIN SMALL LIGATURE FFI | ||
| 89 | * </p> | ||
| 90 | * | ||
| 91 | * The ffi ligature is not a distinct semantic character, and strictly speaking | ||
| 92 | * it shouldn't be in Unicode at all, but it was included for compatibility | ||
| 93 | * with existing character sets that already provided it. The Unicode standard | ||
| 94 | * identifies such characters by giving them "compatibility" decompositions | ||
| 95 | * into the corresponding semantic characters. When sorting and searching, you | ||
| 96 | * will often want to use these mappings. | ||
| 97 | * | ||
| 98 | * <code>normalize</code> helps solve these problems by transforming text into | ||
| 99 | * the canonical composed and decomposed forms as shown in the first example | ||
| 100 | * above. In addition, you can have it perform compatibility decompositions so | ||
| 101 | * that you can treat compatibility characters the same as their equivalents. | ||
| 102 | * Finally, <code>normalize</code> rearranges accents into the proper canonical | ||
| 103 | * order, so that you do not have to worry about accent rearrangement on your | ||
| 104 | * own. | ||
| 105 | * | ||
| 106 | * Form FCD, "Fast C or D", is also designed for collation. | ||
| 107 | * It allows to work on strings that are not necessarily normalized | ||
| 108 | * with an algorithm (like in collation) that works under "canonical closure", | ||
| 109 | * i.e., it treats precomposed characters and their decomposed equivalents the | ||
| 110 | * same. | ||
| 111 | * | ||
| 112 | * It is not a normalization form because it does not provide for uniqueness of | ||
| 113 | * representation. Multiple strings may be canonically equivalent (their NFDs | ||
| 114 | * are identical) and may all conform to FCD without being identical themselves. | ||
| 115 | * | ||
| 116 | * The form is defined such that the "raw decomposition", the recursive | ||
| 117 | * canonical decomposition of each character, results in a string that is | ||
| 118 | * canonically ordered. This means that precomposed characters are allowed for | ||
| 119 | * as long as their decompositions do not need canonical reordering. | ||
| 120 | * | ||
| 121 | * Its advantage for a process like collation is that all NFD and most NFC texts | ||
| 122 | * - and many unnormalized texts - already conform to FCD and do not need to be | ||
| 123 | * normalized (NFD) for such a process. The FCD quick check will return YES for | ||
| 124 | * most strings in practice. | ||
| 125 | * | ||
| 126 | * normalize(FCD) may be implemented with NFD. | ||
| 127 | * | ||
| 128 | * For more details on FCD see the collation design document: | ||
| 129 | * http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm | ||
| 130 | * | ||
| 131 | * ICU collation performs either NFD or FCD normalization automatically if | ||
| 132 | * normalization is turned on for the collator object. Beyond collation and | ||
| 133 | * string search, normalized strings may be useful for string equivalence | ||
| 134 | * comparisons, transliteration/transcription, unique representations, etc. | ||
| 135 | * | ||
| 136 | * The W3C generally recommends to exchange texts in NFC. | ||
| 137 | * Note also that most legacy character encodings use only precomposed forms and | ||
| 138 | * often do not encode any combining marks by themselves. For conversion to such | ||
| 139 | * character encodings the Unicode text needs to be normalized to NFC. | ||
| 140 | * For more usage examples, see the Unicode Standard Annex. | ||
| 141 | * @stable ICU 2.8 | ||
| 142 | */ | ||
| 143 | |||
| 144 | public final class NormalizerBase implements Cloneable { | ||
| 145 | |||
| 146 | //------------------------------------------------------------------------- | ||
| 147 | // Private data | ||
| 148 | //------------------------------------------------------------------------- | ||
| 149 | private char[] buffer = new char[100]; | ||
| 150 | private int bufferStart = 0; | ||
| 151 | private int bufferPos = 0; | ||
| 152 | private int bufferLimit = 0; | ||
| 153 | |||
| 154 | // The input text and our position in it | ||
| 155 | private UCharacterIterator text; | ||
| 156 | private Mode mode = NFC; | ||
| 157 | private int options = 0; | ||
| 158 | private int currentIndex; | ||
| 159 | private int nextIndex; | ||
| 160 | |||
| 161 | /** | ||
| 162 | * Options bit set value to select Unicode 3.2 normalization | ||
| 163 | * (except NormalizationCorrections). | ||
| 164 | * At most one Unicode version can be selected at a time. | ||
| 165 | * @stable ICU 2.6 | ||
| 166 | */ | ||
| 167 | public static final int UNICODE_3_2=0x20; | ||
| 168 | |||
| 169 | /** | ||
| 170 | * Constant indicating that the end of the iteration has been reached. | ||
| 171 | * This is guaranteed to have the same value as {@link UCharacterIterator#DONE}. | ||
| 172 | * @stable ICU 2.8 | ||
| 173 | */ | ||
| 174 | public static final int DONE = UCharacterIterator.DONE; | ||
| 175 | |||
| 176 | /** | ||
| 177 | * Constants for normalization modes. | ||
| 178 | * @stable ICU 2.8 | ||
| 179 | */ | ||
| 180 | public static class Mode { | ||
| 181 | private int modeValue; | ||
| 182 | private Mode(int value) { | ||
| 183 | modeValue = value; | ||
| 184 | } | ||
| 185 | |||
| 186 | /** | ||
| 187 | * This method is used for method dispatch | ||
| 188 | * @stable ICU 2.6 | ||
| 189 | */ | ||
| 190 | protected int normalize(char[] src, int srcStart, int srcLimit, | ||
| 191 | char[] dest,int destStart,int destLimit, | ||
| 192 | UnicodeSet nx) { | ||
| 193 | int srcLen = (srcLimit - srcStart); | ||
| 194 | int destLen = (destLimit - destStart); | ||
| 195 | if( srcLen > destLen ) { | ||
| 196 | return srcLen; | ||
| 197 | } | ||
| 198 | System.arraycopy(src,srcStart,dest,destStart,srcLen); | ||
| 199 | return srcLen; | ||
| 200 | } | ||
| 201 | |||
| 202 | /** | ||
| 203 | * This method is used for method dispatch | ||
| 204 | * @stable ICU 2.6 | ||
| 205 | */ | ||
| 206 | protected int normalize(char[] src, int srcStart, int srcLimit, | ||
| 207 | char[] dest,int destStart,int destLimit, | ||
| 208 | int options) { | ||
| 209 | return normalize( src, srcStart, srcLimit, | ||
| 210 | dest,destStart,destLimit, | ||
| 211 | NormalizerImpl.getNX(options) | ||
| 212 | ); | ||
| 213 | } | ||
| 214 | |||
| 215 | /** | ||
| 216 | * This method is used for method dispatch | ||
| 217 | * @stable ICU 2.6 | ||
| 218 | */ | ||
| 219 | protected String normalize(String src, int options) { | ||
| 220 | return src; | ||
| 221 | } | ||
| 222 | |||
| 223 | /** | ||
| 224 | * This method is used for method dispatch | ||
| 225 | * @stable ICU 2.8 | ||
| 226 | */ | ||
| 227 | protected int getMinC() { | ||
| 228 | return -1; | ||
| 229 | } | ||
| 230 | |||
| 231 | /** | ||
| 232 | * This method is used for method dispatch | ||
| 233 | * @stable ICU 2.8 | ||
| 234 | */ | ||
| 235 | protected int getMask() { | ||
| 236 | return -1; | ||
| 237 | } | ||
| 238 | |||
| 239 | /** | ||
| 240 | * This method is used for method dispatch | ||
| 241 | * @stable ICU 2.8 | ||
| 242 | */ | ||
| 243 | protected IsPrevBoundary getPrevBoundary() { | ||
| 244 | return null; | ||
| 245 | } | ||
| 246 | |||
| 247 | /** | ||
| 248 | * This method is used for method dispatch | ||
| 249 | * @stable ICU 2.8 | ||
| 250 | */ | ||
| 251 | protected IsNextBoundary getNextBoundary() { | ||
| 252 | return null; | ||
| 253 | } | ||
| 254 | |||
| 255 | /** | ||
| 256 | * This method is used for method dispatch | ||
| 257 | * @stable ICU 2.6 | ||
| 258 | */ | ||
| 259 | protected QuickCheckResult quickCheck(char[] src,int start, int limit, | ||
| 260 | boolean allowMaybe,UnicodeSet nx) { | ||
| 261 | if(allowMaybe) { | ||
| 262 | return MAYBE; | ||
| 263 | } | ||
| 264 | return NO; | ||
| 265 | } | ||
| 266 | |||
| 267 | /** | ||
| 268 | * This method is used for method dispatch | ||
| 269 | * @stable ICU 2.8 | ||
| 270 | */ | ||
| 271 | protected boolean isNFSkippable(int c) { | ||
| 272 | return true; | ||
| 273 | } | ||
| 274 | } | ||
| 275 | |||
| 276 | /** | ||
| 277 | * No decomposition/composition. | ||
| 278 | * @stable ICU 2.8 | ||
| 279 | */ | ||
| 280 | public static final Mode NONE = new Mode(1); | ||
| 281 | |||
| 282 | /** | ||
| 283 | * Canonical decomposition. | ||
| 284 | * @stable ICU 2.8 | ||
| 285 | */ | ||
| 286 | public static final Mode NFD = new NFDMode(2); | ||
| 287 | |||
| 288 | private static final class NFDMode extends Mode { | ||
| 289 | private NFDMode(int value) { | ||
| 290 | super(value); | ||
| 291 | } | ||
| 292 | |||
| 293 | protected int normalize(char[] src, int srcStart, int srcLimit, | ||
| 294 | char[] dest,int destStart,int destLimit, | ||
| 295 | UnicodeSet nx) { | ||
| 296 | int[] trailCC = new int[1]; | ||
| 297 | return NormalizerImpl.decompose(src, srcStart,srcLimit, | ||
| 298 | dest, destStart,destLimit, | ||
| 299 | false, trailCC,nx); | ||
| 300 | } | ||
| 301 | |||
| 302 | protected String normalize( String src, int options) { | ||
| 303 | return decompose(src,false,options); | ||
| 304 | } | ||
| 305 | |||
| 306 | protected int getMinC() { | ||
| 307 | return NormalizerImpl.MIN_WITH_LEAD_CC; | ||
| 308 | } | ||
| 309 | |||
| 310 | protected IsPrevBoundary getPrevBoundary() { | ||
| 311 | return new IsPrevNFDSafe(); | ||
| 312 | } | ||
| 313 | |||
| 314 | protected IsNextBoundary getNextBoundary() { | ||
| 315 | return new IsNextNFDSafe(); | ||
| 316 | } | ||
| 317 | |||
| 318 | protected int getMask() { | ||
| 319 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFD); | ||
| 320 | } | ||
| 321 | |||
| 322 | protected QuickCheckResult quickCheck(char[] src,int start, | ||
| 323 | int limit,boolean allowMaybe, | ||
| 324 | UnicodeSet nx) { | ||
| 325 | return NormalizerImpl.quickCheck( | ||
| 326 | src, start,limit, | ||
| 327 | NormalizerImpl.getFromIndexesArr( | ||
| 328 | NormalizerImpl.INDEX_MIN_NFD_NO_MAYBE | ||
| 329 | ), | ||
| 330 | NormalizerImpl.QC_NFD, | ||
| 331 | 0, | ||
| 332 | allowMaybe, | ||
| 333 | nx | ||
| 334 | ); | ||
| 335 | } | ||
| 336 | |||
| 337 | protected boolean isNFSkippable(int c) { | ||
| 338 | return NormalizerImpl.isNFSkippable(c,this, | ||
| 339 | (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFD) | ||
| 340 | ); | ||
| 341 | } | ||
| 342 | } | ||
| 343 | |||
| 344 | /** | ||
| 345 | * Compatibility decomposition. | ||
| 346 | * @stable ICU 2.8 | ||
| 347 | */ | ||
| 348 | public static final Mode NFKD = new NFKDMode(3); | ||
| 349 | |||
| 350 | private static final class NFKDMode extends Mode { | ||
| 351 | private NFKDMode(int value) { | ||
| 352 | super(value); | ||
| 353 | } | ||
| 354 | |||
| 355 | protected int normalize(char[] src, int srcStart, int srcLimit, | ||
| 356 | char[] dest,int destStart,int destLimit, | ||
| 357 | UnicodeSet nx) { | ||
| 358 | int[] trailCC = new int[1]; | ||
| 359 | return NormalizerImpl.decompose(src, srcStart,srcLimit, | ||
| 360 | dest, destStart,destLimit, | ||
| 361 | true, trailCC, nx); | ||
| 362 | } | ||
| 363 | |||
| 364 | protected String normalize( String src, int options) { | ||
| 365 | return decompose(src,true,options); | ||
| 366 | } | ||
| 367 | |||
| 368 | protected int getMinC() { | ||
| 369 | return NormalizerImpl.MIN_WITH_LEAD_CC; | ||
| 370 | } | ||
| 371 | |||
| 372 | protected IsPrevBoundary getPrevBoundary() { | ||
| 373 | return new IsPrevNFDSafe(); | ||
| 374 | } | ||
| 375 | |||
| 376 | protected IsNextBoundary getNextBoundary() { | ||
| 377 | return new IsNextNFDSafe(); | ||
| 378 | } | ||
| 379 | |||
| 380 | protected int getMask() { | ||
| 381 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFKD); | ||
| 382 | } | ||
| 383 | |||
| 384 | protected QuickCheckResult quickCheck(char[] src,int start, | ||
| 385 | int limit,boolean allowMaybe, | ||
| 386 | UnicodeSet nx) { | ||
| 387 | return NormalizerImpl.quickCheck( | ||
| 388 | src,start,limit, | ||
| 389 | NormalizerImpl.getFromIndexesArr( | ||
| 390 | NormalizerImpl.INDEX_MIN_NFKD_NO_MAYBE | ||
| 391 | ), | ||
| 392 | NormalizerImpl.QC_NFKD, | ||
| 393 | NormalizerImpl.OPTIONS_COMPAT, | ||
| 394 | allowMaybe, | ||
| 395 | nx | ||
| 396 | ); | ||
| 397 | } | ||
| 398 | |||
| 399 | protected boolean isNFSkippable(int c) { | ||
| 400 | return NormalizerImpl.isNFSkippable(c, this, | ||
| 401 | (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFKD) | ||
| 402 | ); | ||
| 403 | } | ||
| 404 | } | ||
| 405 | |||
| 406 | /** | ||
| 407 | * Canonical decomposition followed by canonical composition. | ||
| 408 | * @stable ICU 2.8 | ||
| 409 | */ | ||
| 410 | public static final Mode NFC = new NFCMode(4); | ||
| 411 | |||
| 412 | private static final class NFCMode extends Mode{ | ||
| 413 | private NFCMode(int value) { | ||
| 414 | super(value); | ||
| 415 | } | ||
| 416 | protected int normalize(char[] src, int srcStart, int srcLimit, | ||
| 417 | char[] dest,int destStart,int destLimit, | ||
| 418 | UnicodeSet nx) { | ||
| 419 | return NormalizerImpl.compose( src, srcStart, srcLimit, | ||
| 420 | dest,destStart,destLimit, | ||
| 421 | 0, nx); | ||
| 422 | } | ||
| 423 | |||
| 424 | protected String normalize( String src, int options) { | ||
| 425 | return compose(src, false, options); | ||
| 426 | } | ||
| 427 | |||
| 428 | protected int getMinC() { | ||
| 429 | return NormalizerImpl.getFromIndexesArr( | ||
| 430 | NormalizerImpl.INDEX_MIN_NFC_NO_MAYBE | ||
| 431 | ); | ||
| 432 | } | ||
| 433 | protected IsPrevBoundary getPrevBoundary() { | ||
| 434 | return new IsPrevTrueStarter(); | ||
| 435 | } | ||
| 436 | protected IsNextBoundary getNextBoundary() { | ||
| 437 | return new IsNextTrueStarter(); | ||
| 438 | } | ||
| 439 | protected int getMask() { | ||
| 440 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFC); | ||
| 441 | } | ||
| 442 | protected QuickCheckResult quickCheck(char[] src,int start, | ||
| 443 | int limit,boolean allowMaybe, | ||
| 444 | UnicodeSet nx) { | ||
| 445 | return NormalizerImpl.quickCheck( | ||
| 446 | src,start,limit, | ||
| 447 | NormalizerImpl.getFromIndexesArr( | ||
| 448 | NormalizerImpl.INDEX_MIN_NFC_NO_MAYBE | ||
| 449 | ), | ||
| 450 | NormalizerImpl.QC_NFC, | ||
| 451 | 0, | ||
| 452 | allowMaybe, | ||
| 453 | nx | ||
| 454 | ); | ||
| 455 | } | ||
| 456 | protected boolean isNFSkippable(int c) { | ||
| 457 | return NormalizerImpl.isNFSkippable(c,this, | ||
| 458 | ( NormalizerImpl.CC_MASK|NormalizerImpl.COMBINES_ANY| | ||
| 459 | (NormalizerImpl.QC_NFC & NormalizerImpl.QC_ANY_NO) | ||
| 460 | ) | ||
| 461 | ); | ||
| 462 | } | ||
| 463 | }; | ||
| 464 | |||
| 465 | /** | ||
| 466 | * Compatibility decomposition followed by canonical composition. | ||
| 467 | * @stable ICU 2.8 | ||
| 468 | */ | ||
| 469 | public static final Mode NFKC =new NFKCMode(5); | ||
| 470 | |||
| 471 | private static final class NFKCMode extends Mode{ | ||
| 472 | private NFKCMode(int value) { | ||
| 473 | super(value); | ||
| 474 | } | ||
| 475 | protected int normalize(char[] src, int srcStart, int srcLimit, | ||
| 476 | char[] dest,int destStart,int destLimit, | ||
| 477 | UnicodeSet nx) { | ||
| 478 | return NormalizerImpl.compose(src, srcStart,srcLimit, | ||
| 479 | dest, destStart,destLimit, | ||
| 480 | NormalizerImpl.OPTIONS_COMPAT, nx); | ||
| 481 | } | ||
| 482 | |||
| 483 | protected String normalize( String src, int options) { | ||
| 484 | return compose(src, true, options); | ||
| 485 | } | ||
| 486 | protected int getMinC() { | ||
| 487 | return NormalizerImpl.getFromIndexesArr( | ||
| 488 | NormalizerImpl.INDEX_MIN_NFKC_NO_MAYBE | ||
| 489 | ); | ||
| 490 | } | ||
| 491 | protected IsPrevBoundary getPrevBoundary() { | ||
| 492 | return new IsPrevTrueStarter(); | ||
| 493 | } | ||
| 494 | protected IsNextBoundary getNextBoundary() { | ||
| 495 | return new IsNextTrueStarter(); | ||
| 496 | } | ||
| 497 | protected int getMask() { | ||
| 498 | return (NormalizerImpl.CC_MASK|NormalizerImpl.QC_NFKC); | ||
| 499 | } | ||
| 500 | protected QuickCheckResult quickCheck(char[] src,int start, | ||
| 501 | int limit,boolean allowMaybe, | ||
| 502 | UnicodeSet nx) { | ||
| 503 | return NormalizerImpl.quickCheck( | ||
| 504 | src,start,limit, | ||
| 505 | NormalizerImpl.getFromIndexesArr( | ||
| 506 | NormalizerImpl.INDEX_MIN_NFKC_NO_MAYBE | ||
| 507 | ), | ||
| 508 | NormalizerImpl.QC_NFKC, | ||
| 509 | NormalizerImpl.OPTIONS_COMPAT, | ||
| 510 | allowMaybe, | ||
| 511 | nx | ||
| 512 | ); | ||
| 513 | } | ||
| 514 | protected boolean isNFSkippable(int c) { | ||
| 515 | return NormalizerImpl.isNFSkippable(c, this, | ||
| 516 | ( NormalizerImpl.CC_MASK|NormalizerImpl.COMBINES_ANY| | ||
| 517 | (NormalizerImpl.QC_NFKC & NormalizerImpl.QC_ANY_NO) | ||
| 518 | ) | ||
| 519 | ); | ||
| 520 | } | ||
| 521 | }; | ||
| 522 | |||
| 523 | /** | ||
| 524 | * Result values for quickCheck(). | ||
| 525 | * For details see Unicode Technical Report 15. | ||
| 526 | * @stable ICU 2.8 | ||
| 527 | */ | ||
| 528 | public static final class QuickCheckResult{ | ||
| 529 | private int resultValue; | ||
| 530 | private QuickCheckResult(int value) { | ||
| 531 | resultValue=value; | ||
| 532 | } | ||
| 533 | } | ||
| 534 | /** | ||
| 535 | * Indicates that string is not in the normalized format | ||
| 536 | * @stable ICU 2.8 | ||
| 537 | */ | ||
| 538 | public static final QuickCheckResult NO = new QuickCheckResult(0); | ||
| 539 | |||
| 540 | /** | ||
| 541 | * Indicates that string is in the normalized format | ||
| 542 | * @stable ICU 2.8 | ||
| 543 | */ | ||
| 544 | public static final QuickCheckResult YES = new QuickCheckResult(1); | ||
| 545 | |||
| 546 | /** | ||
| 547 | * Indicates it cannot be determined if string is in the normalized | ||
| 548 | * format without further thorough checks. | ||
| 549 | * @stable ICU 2.8 | ||
| 550 | */ | ||
| 551 | public static final QuickCheckResult MAYBE = new QuickCheckResult(2); | ||
| 552 | |||
| 553 | //------------------------------------------------------------------------- | ||
| 554 | // Constructors | ||
| 555 | //------------------------------------------------------------------------- | ||
| 556 | |||
| 557 | /** | ||
| 558 | * Creates a new <tt>Normalizer</tt> object for iterating over the | ||
| 559 | * normalized form of a given string. | ||
| 560 | * <p> | ||
| 561 | * The <tt>options</tt> parameter specifies which optional | ||
| 562 | * <tt>Normalizer</tt> features are to be enabled for this object. | ||
| 563 | * <p> | ||
| 564 | * @param str The string to be normalized. The normalization | ||
| 565 | * will start at the beginning of the string. | ||
| 566 | * | ||
| 567 | * @param mode The normalization mode. | ||
| 568 | * | ||
| 569 | * @param opt Any optional features to be enabled. | ||
| 570 | * Currently the only available option is {@link #UNICODE_3_2}. | ||
| 571 | * If you want the default behavior corresponding to one of the | ||
| 572 | * standard Unicode Normalization Forms, use 0 for this argument. | ||
| 573 | * @stable ICU 2.6 | ||
| 574 | */ | ||
| 575 | public NormalizerBase(String str, Mode mode, int opt) { | ||
| 576 | this.text = UCharacterIterator.getInstance(str); | ||
| 577 | this.mode = mode; | ||
| 578 | this.options=opt; | ||
| 579 | } | ||
| 580 | |||
| 581 | /** | ||
| 582 | * Creates a new <tt>Normalizer</tt> object for iterating over the | ||
| 583 | * normalized form of the given text. | ||
| 584 | * <p> | ||
| 585 | * @param iter The input text to be normalized. The normalization | ||
| 586 | * will start at the beginning of the string. | ||
| 587 | * | ||
| 588 | * @param mode The normalization mode. | ||
| 589 | */ | ||
| 590 | public NormalizerBase(CharacterIterator iter, Mode mode) { | ||
| 591 | this(iter, mode, UNICODE_LATEST); | ||
| 592 | } | ||
| 593 | |||
| 594 | /** | ||
| 595 | * Creates a new <tt>Normalizer</tt> object for iterating over the | ||
| 596 | * normalized form of the given text. | ||
| 597 | * <p> | ||
| 598 | * @param iter The input text to be normalized. The normalization | ||
| 599 | * will start at the beginning of the string. | ||
| 600 | * | ||
| 601 | * @param mode The normalization mode. | ||
| 602 | * | ||
| 603 | * @param opt Any optional features to be enabled. | ||
| 604 | * Currently the only available option is {@link #UNICODE_3_2}. | ||
| 605 | * If you want the default behavior corresponding to one of the | ||
| 606 | * standard Unicode Normalization Forms, use 0 for this argument. | ||
| 607 | * @stable ICU 2.6 | ||
| 608 | */ | ||
| 609 | public NormalizerBase(CharacterIterator iter, Mode mode, int opt) { | ||
| 610 | this.text = UCharacterIterator.getInstance( | ||
| 611 | (CharacterIterator)iter.clone() | ||
| 612 | ); | ||
| 613 | this.mode = mode; | ||
| 614 | this.options = opt; | ||
| 615 | } | ||
| 616 | |||
| 617 | /** | ||
| 618 | * Clones this <tt>Normalizer</tt> object. All properties of this | ||
| 619 | * object are duplicated in the new object, including the cloning of any | ||
| 620 | * {@link CharacterIterator} that was passed in to the constructor | ||
| 621 | * or to {@link #setText(CharacterIterator) setText}. | ||
| 622 | * However, the text storage underlying | ||
| 623 | * the <tt>CharacterIterator</tt> is not duplicated unless the | ||
| 624 | * iterator's <tt>clone</tt> method does so. | ||
| 625 | * @stable ICU 2.8 | ||
| 626 | */ | ||
| 627 | public Object clone() { | ||
| 628 | try { | ||
| 629 | NormalizerBase copy = (NormalizerBase) super.clone(); | ||
| 630 | copy.text = (UCharacterIterator) text.clone(); | ||
| 631 | //clone the internal buffer | ||
| 632 | if (buffer != null) { | ||
| 633 | copy.buffer = new char[buffer.length]; | ||
| 634 | System.arraycopy(buffer,0,copy.buffer,0,buffer.length); | ||
| 635 | } | ||
| 636 | return copy; | ||
| 637 | } | ||
| 638 | catch (CloneNotSupportedException e) { | ||
| 639 | throw new InternalError(e.toString()); | ||
| 640 | } | ||
| 641 | } | ||
| 642 | |||
| 643 | //-------------------------------------------------------------------------- | ||
| 644 | // Static Utility methods | ||
| 645 | //-------------------------------------------------------------------------- | ||
| 646 | |||
| 647 | /** | ||
| 648 | * Compose a string. | ||
| 649 | * The string will be composed to according the the specified mode. | ||
| 650 | * @param str The string to compose. | ||
| 651 | * @param compat If true the string will be composed accoding to | ||
| 652 | * NFKC rules and if false will be composed according to | ||
| 653 | * NFC rules. | ||
| 654 | * @param options The only recognized option is UNICODE_3_2 | ||
| 655 | * @return String The composed string | ||
| 656 | * @stable ICU 2.6 | ||
| 657 | */ | ||
| 658 | public static String compose(String str, boolean compat, int options) { | ||
| 659 | |||
| 660 | char[] dest, src; | ||
| 661 | if (options == UNICODE_3_2_0_ORIGINAL) { | ||
| 662 | String mappedStr = NormalizerImpl.convert(str); | ||
| 663 | dest = new char[mappedStr.length()*MAX_BUF_SIZE_COMPOSE]; | ||
| 664 | src = mappedStr.toCharArray(); | ||
| 665 | } else { | ||
| 666 | dest = new char[str.length()*MAX_BUF_SIZE_COMPOSE]; | ||
| 667 | src = str.toCharArray(); | ||
| 668 | } | ||
| 669 | int destSize=0; | ||
| 670 | |||
| 671 | UnicodeSet nx = NormalizerImpl.getNX(options); | ||
| 672 | |||
| 673 | /* reset options bits that should only be set here or inside compose() */ | ||
| 674 | options&=~(NormalizerImpl.OPTIONS_SETS_MASK|NormalizerImpl.OPTIONS_COMPAT|NormalizerImpl.OPTIONS_COMPOSE_CONTIGUOUS); | ||
| 675 | |||
| 676 | if(compat) { | ||
| 677 | options|=NormalizerImpl.OPTIONS_COMPAT; | ||
| 678 | } | ||
| 679 | |||
| 680 | for(;;) { | ||
| 681 | destSize=NormalizerImpl.compose(src,0,src.length, | ||
| 682 | dest,0,dest.length,options, | ||
| 683 | nx); | ||
| 684 | if(destSize<=dest.length) { | ||
| 685 | return new String(dest,0,destSize); | ||
| 686 | } else { | ||
| 687 | dest = new char[destSize]; | ||
| 688 | } | ||
| 689 | } | ||
| 690 | } | ||
| 691 | |||
| 692 | private static final int MAX_BUF_SIZE_COMPOSE = 2; | ||
| 693 | private static final int MAX_BUF_SIZE_DECOMPOSE = 3; | ||
| 694 | |||
| 695 | /** | ||
| 696 | * Decompose a string. | ||
| 697 | * The string will be decomposed to according the the specified mode. | ||
| 698 | * @param str The string to decompose. | ||
| 699 | * @param compat If true the string will be decomposed accoding to NFKD | ||
| 700 | * rules and if false will be decomposed according to NFD | ||
| 701 | * rules. | ||
| 702 | * @return String The decomposed string | ||
| 703 | * @stable ICU 2.8 | ||
| 704 | */ | ||
| 705 | public static String decompose(String str, boolean compat) { | ||
| 706 | return decompose(str,compat,UNICODE_LATEST); | ||
| 707 | } | ||
| 708 | |||
| 709 | /** | ||
| 710 | * Decompose a string. | ||
| 711 | * The string will be decomposed to according the the specified mode. | ||
| 712 | * @param str The string to decompose. | ||
| 713 | * @param compat If true the string will be decomposed accoding to NFKD | ||
| 714 | * rules and if false will be decomposed according to NFD | ||
| 715 | * rules. | ||
| 716 | * @param options The normalization options, ORed together (0 for no options). | ||
| 717 | * @return String The decomposed string | ||
| 718 | * @stable ICU 2.6 | ||
| 719 | */ | ||
| 720 | public static String decompose(String str, boolean compat, int options) { | ||
| 721 | |||
| 722 | int[] trailCC = new int[1]; | ||
| 723 | int destSize=0; | ||
| 724 | UnicodeSet nx = NormalizerImpl.getNX(options); | ||
| 725 | char[] dest; | ||
| 726 | |||
| 727 | if (options == UNICODE_3_2_0_ORIGINAL) { | ||
| 728 | String mappedStr = NormalizerImpl.convert(str); | ||
| 729 | dest = new char[mappedStr.length()*MAX_BUF_SIZE_DECOMPOSE]; | ||
| 730 | |||
| 731 | for(;;) { | ||
| 732 | destSize=NormalizerImpl.decompose(mappedStr.toCharArray(),0,mappedStr.length(), | ||
| 733 | dest,0,dest.length, | ||
| 734 | compat,trailCC, nx); | ||
| 735 | if(destSize<=dest.length) { | ||
| 736 | return new String(dest,0,destSize); | ||
| 737 | } else { | ||
| 738 | dest = new char[destSize]; | ||
| 739 | } | ||
| 740 | } | ||
| 741 | } else { | ||
| 742 | dest = new char[str.length()*MAX_BUF_SIZE_DECOMPOSE]; | ||
| 743 | |||
| 744 | for(;;) { | ||
| 745 | destSize=NormalizerImpl.decompose(str.toCharArray(),0,str.length(), | ||
| 746 | dest,0,dest.length, | ||
| 747 | compat,trailCC, nx); | ||
| 748 | if(destSize<=dest.length) { | ||
| 749 | return new String(dest,0,destSize); | ||
| 750 | } else { | ||
| 751 | dest = new char[destSize]; | ||
| 752 | } | ||
| 753 | } | ||
| 754 | } | ||
| 755 | } | ||
| 756 | |||
| 757 | /** | ||
| 758 | * Normalize a string. | ||
| 759 | * The string will be normalized according the the specified normalization | ||
| 760 | * mode and options. | ||
| 761 | * @param src The char array to compose. | ||
| 762 | * @param srcStart Start index of the source | ||
| 763 | * @param srcLimit Limit index of the source | ||
| 764 | * @param dest The char buffer to fill in | ||
| 765 | * @param destStart Start index of the destination buffer | ||
| 766 | * @param destLimit End index of the destination buffer | ||
| 767 | * @param mode The normalization mode; one of Normalizer.NONE, | ||
| 768 | * Normalizer.NFD, Normalizer.NFC, Normalizer.NFKC, | ||
| 769 | * Normalizer.NFKD, Normalizer.DEFAULT | ||
| 770 | * @param options The normalization options, ORed together (0 for no options). | ||
| 771 | * @return int The total buffer size needed;if greater than length of | ||
| 772 | * result, the output was truncated. | ||
| 773 | * @exception IndexOutOfBoundsException if the target capacity is | ||
| 774 | * less than the required length | ||
| 775 | * @stable ICU 2.6 | ||
| 776 | */ | ||
| 777 | public static int normalize(char[] src,int srcStart, int srcLimit, | ||
| 778 | char[] dest,int destStart, int destLimit, | ||
| 779 | Mode mode, int options) { | ||
| 780 | int length = mode.normalize(src,srcStart,srcLimit,dest,destStart,destLimit, options); | ||
| 781 | |||
| 782 | if(length<=(destLimit-destStart)) { | ||
| 783 | return length; | ||
| 784 | } else { | ||
| 785 | throw new IndexOutOfBoundsException(Integer.toString(length)); | ||
| 786 | } | ||
| 787 | } | ||
| 788 | |||
| 789 | //------------------------------------------------------------------------- | ||
| 790 | // Iteration API | ||
| 791 | //------------------------------------------------------------------------- | ||
| 792 | |||
| 793 | /** | ||
| 794 | * Return the current character in the normalized text-> | ||
| 795 | * @return The codepoint as an int | ||
| 796 | * @stable ICU 2.8 | ||
| 797 | */ | ||
| 798 | public int current() { | ||
| 799 | if(bufferPos<bufferLimit || nextNormalize()) { | ||
| 800 | return getCodePointAt(bufferPos); | ||
| 801 | } else { | ||
| 802 | return DONE; | ||
| 803 | } | ||
| 804 | } | ||
| 805 | |||
| 806 | /** | ||
| 807 | * Return the next character in the normalized text and advance | ||
| 808 | * the iteration position by one. If the end | ||
| 809 | * of the text has already been reached, {@link #DONE} is returned. | ||
| 810 | * @return The codepoint as an int | ||
| 811 | * @stable ICU 2.8 | ||
| 812 | */ | ||
| 813 | public int next() { | ||
| 814 | if(bufferPos<bufferLimit || nextNormalize()) { | ||
| 815 | int c=getCodePointAt(bufferPos); | ||
| 816 | bufferPos+=(c>0xFFFF) ? 2 : 1; | ||
| 817 | return c; | ||
| 818 | } else { | ||
| 819 | return DONE; | ||
| 820 | } | ||
| 821 | } | ||
| 822 | |||
| 823 | |||
| 824 | /** | ||
| 825 | * Return the previous character in the normalized text and decrement | ||
| 826 | * the iteration position by one. If the beginning | ||
| 827 | * of the text has already been reached, {@link #DONE} is returned. | ||
| 828 | * @return The codepoint as an int | ||
| 829 | * @stable ICU 2.8 | ||
| 830 | */ | ||
| 831 | public int previous() { | ||
| 832 | if(bufferPos>0 || previousNormalize()) { | ||
| 833 | int c=getCodePointAt(bufferPos-1); | ||
| 834 | bufferPos-=(c>0xFFFF) ? 2 : 1; | ||
| 835 | return c; | ||
| 836 | } else { | ||
| 837 | return DONE; | ||
| 838 | } | ||
| 839 | } | ||
| 840 | |||
| 841 | /** | ||
| 842 | * Reset the index to the beginning of the text. | ||
| 843 | * This is equivalent to setIndexOnly(startIndex)). | ||
| 844 | * @stable ICU 2.8 | ||
| 845 | */ | ||
| 846 | public void reset() { | ||
| 847 | text.setIndex(0); | ||
| 848 | currentIndex=nextIndex=0; | ||
| 849 | clearBuffer(); | ||
| 850 | } | ||
| 851 | |||
| 852 | /** | ||
| 853 | * Set the iteration position in the input text that is being normalized, | ||
| 854 | * without any immediate normalization. | ||
| 855 | * After setIndexOnly(), getIndex() will return the same index that is | ||
| 856 | * specified here. | ||
| 857 | * | ||
| 858 | * @param index the desired index in the input text. | ||
| 859 | * @stable ICU 2.8 | ||
| 860 | */ | ||
| 861 | public void setIndexOnly(int index) { | ||
| 862 | text.setIndex(index); | ||
| 863 | currentIndex=nextIndex=index; // validates index | ||
| 864 | clearBuffer(); | ||
| 865 | } | ||
| 866 | |||
| 867 | /** | ||
| 868 | * Set the iteration position in the input text that is being normalized | ||
| 869 | * and return the first normalized character at that position. | ||
| 870 | * <p> | ||
| 871 | * <b>Note:</b> This method sets the position in the <em>input</em> text, | ||
| 872 | * while {@link #next} and {@link #previous} iterate through characters | ||
| 873 | * in the normalized <em>output</em>. This means that there is not | ||
| 874 | * necessarily a one-to-one correspondence between characters returned | ||
| 875 | * by <tt>next</tt> and <tt>previous</tt> and the indices passed to and | ||
| 876 | * returned from <tt>setIndex</tt> and {@link #getIndex}. | ||
| 877 | * <p> | ||
| 878 | * @param index the desired index in the input text-> | ||
| 879 | * | ||
| 880 | * @return the first normalized character that is the result of iterating | ||
| 881 | * forward starting at the given index. | ||
| 882 | * | ||
| 883 | * @throws IllegalArgumentException if the given index is less than | ||
| 884 | * {@link #getBeginIndex} or greater than {@link #getEndIndex}. | ||
| 885 | * @return The codepoint as an int | ||
| 886 | * @deprecated ICU 3.2 | ||
| 887 | * @obsolete ICU 3.2 | ||
| 888 | */ | ||
| 889 | public int setIndex(int index) { | ||
| 890 | setIndexOnly(index); | ||
| 891 | return current(); | ||
| 892 | } | ||
| 893 | |||
| 894 | /** | ||
| 895 | * Retrieve the index of the start of the input text. This is the begin | ||
| 896 | * index of the <tt>CharacterIterator</tt> or the start (i.e. 0) of the | ||
| 897 | * <tt>String</tt> over which this <tt>Normalizer</tt> is iterating | ||
| 898 | * @deprecated ICU 2.2. Use startIndex() instead. | ||
| 899 | * @return The codepoint as an int | ||
| 900 | * @see #startIndex | ||
| 901 | */ | ||
| 902 | public int getBeginIndex() { | ||
| 903 | return 0; | ||
| 904 | } | ||
| 905 | |||
| 906 | /** | ||
| 907 | * Retrieve the index of the end of the input text. This is the end index | ||
| 908 | * of the <tt>CharacterIterator</tt> or the length of the <tt>String</tt> | ||
| 909 | * over which this <tt>Normalizer</tt> is iterating | ||
| 910 | * @deprecated ICU 2.2. Use endIndex() instead. | ||
| 911 | * @return The codepoint as an int | ||
| 912 | * @see #endIndex | ||
| 913 | */ | ||
| 914 | public int getEndIndex() { | ||
| 915 | return endIndex(); | ||
| 916 | } | ||
| 917 | |||
| 918 | /** | ||
| 919 | * Retrieve the current iteration position in the input text that is | ||
| 920 | * being normalized. This method is useful in applications such as | ||
| 921 | * searching, where you need to be able to determine the position in | ||
| 922 | * the input text that corresponds to a given normalized output character. | ||
| 923 | * <p> | ||
| 924 | * <b>Note:</b> This method sets the position in the <em>input</em>, while | ||
| 925 | * {@link #next} and {@link #previous} iterate through characters in the | ||
| 926 | * <em>output</em>. This means that there is not necessarily a one-to-one | ||
| 927 | * correspondence between characters returned by <tt>next</tt> and | ||
| 928 | * <tt>previous</tt> and the indices passed to and returned from | ||
| 929 | * <tt>setIndex</tt> and {@link #getIndex}. | ||
| 930 | * @return The current iteration position | ||
| 931 | * @stable ICU 2.8 | ||
| 932 | */ | ||
| 933 | public int getIndex() { | ||
| 934 | if(bufferPos<bufferLimit) { | ||
| 935 | return currentIndex; | ||
| 936 | } else { | ||
| 937 | return nextIndex; | ||
| 938 | } | ||
| 939 | } | ||
| 940 | |||
| 941 | /** | ||
| 942 | * Retrieve the index of the end of the input text-> This is the end index | ||
| 943 | * of the <tt>CharacterIterator</tt> or the length of the <tt>String</tt> | ||
| 944 | * over which this <tt>Normalizer</tt> is iterating | ||
| 945 | * @return The current iteration position | ||
| 946 | * @stable ICU 2.8 | ||
| 947 | */ | ||
| 948 | public int endIndex() { | ||
| 949 | return text.getLength(); | ||
| 950 | } | ||
| 951 | |||
| 952 | //------------------------------------------------------------------------- | ||
| 953 | // Property access methods | ||
| 954 | //------------------------------------------------------------------------- | ||
| 955 | /** | ||
| 956 | * Set the normalization mode for this object. | ||
| 957 | * <p> | ||
| 958 | * <b>Note:</b>If the normalization mode is changed while iterating | ||
| 959 | * over a string, calls to {@link #next} and {@link #previous} may | ||
| 960 | * return previously buffers characters in the old normalization mode | ||
| 961 | * until the iteration is able to re-sync at the next base character. | ||
| 962 | * It is safest to call {@link #setText setText()}, {@link #first}, | ||
| 963 | * {@link #last}, etc. after calling <tt>setMode</tt>. | ||
| 964 | * <p> | ||
| 965 | * @param newMode the new mode for this <tt>Normalizer</tt>. | ||
| 966 | * The supported modes are: | ||
| 967 | * <ul> | ||
| 968 | * <li>{@link #COMPOSE} - Unicode canonical decompositiion | ||
| 969 | * followed by canonical composition. | ||
| 970 | * <li>{@link #COMPOSE_COMPAT} - Unicode compatibility decompositiion | ||
| 971 | * follwed by canonical composition. | ||
| 972 | * <li>{@link #DECOMP} - Unicode canonical decomposition | ||
| 973 | * <li>{@link #DECOMP_COMPAT} - Unicode compatibility decomposition. | ||
| 974 | * <li>{@link #NO_OP} - Do nothing but return characters | ||
| 975 | * from the underlying input text. | ||
| 976 | * </ul> | ||
| 977 | * | ||
| 978 | * @see #getMode | ||
| 979 | * @stable ICU 2.8 | ||
| 980 | */ | ||
| 981 | public void setMode(Mode newMode) { | ||
| 982 | mode = newMode; | ||
| 983 | } | ||
| 984 | /** | ||
| 985 | * Return the basic operation performed by this <tt>Normalizer</tt> | ||
| 986 | * | ||
| 987 | * @see #setMode | ||
| 988 | * @stable ICU 2.8 | ||
| 989 | */ | ||
| 990 | public Mode getMode() { | ||
| 991 | return mode; | ||
| 992 | } | ||
| 993 | |||
| 994 | /** | ||
| 995 | * Set the input text over which this <tt>Normalizer</tt> will iterate. | ||
| 996 | * The iteration position is set to the beginning of the input text-> | ||
| 997 | * @param newText The new string to be normalized. | ||
| 998 | * @stable ICU 2.8 | ||
| 999 | */ | ||
| 1000 | public void setText(String newText) { | ||
| 1001 | |||
| 1002 | UCharacterIterator newIter = UCharacterIterator.getInstance(newText); | ||
| 1003 | if (newIter == null) { | ||
| 1004 | throw new InternalError("Could not create a new UCharacterIterator"); | ||
| 1005 | } | ||
| 1006 | text = newIter; | ||
| 1007 | reset(); | ||
| 1008 | } | ||
| 1009 | |||
| 1010 | /** | ||
| 1011 | * Set the input text over which this <tt>Normalizer</tt> will iterate. | ||
| 1012 | * The iteration position is set to the beginning of the input text-> | ||
| 1013 | * @param newText The new string to be normalized. | ||
| 1014 | * @stable ICU 2.8 | ||
| 1015 | */ | ||
| 1016 | public void setText(CharacterIterator newText) { | ||
| 1017 | |||
| 1018 | UCharacterIterator newIter = UCharacterIterator.getInstance(newText); | ||
| 1019 | if (newIter == null) { | ||
| 1020 | throw new InternalError("Could not create a new UCharacterIterator"); | ||
| 1021 | } | ||
| 1022 | text = newIter; | ||
| 1023 | currentIndex=nextIndex=0; | ||
| 1024 | clearBuffer(); | ||
| 1025 | } | ||
| 1026 | |||
| 1027 | //------------------------------------------------------------------------- | ||
| 1028 | // Private utility methods | ||
| 1029 | //------------------------------------------------------------------------- | ||
| 1030 | |||
| 1031 | |||
| 1032 | /* backward iteration --------------------------------------------------- */ | ||
| 1033 | |||
| 1034 | /* | ||
| 1035 | * read backwards and get norm32 | ||
| 1036 | * return 0 if the character is <minC | ||
| 1037 | * if c2!=0 then (c2, c) is a surrogate pair (reversed - c2 is first | ||
| 1038 | * surrogate but read second!) | ||
| 1039 | */ | ||
| 1040 | |||
| 1041 | private static long getPrevNorm32(UCharacterIterator src, | ||
| 1042 | int/*unsigned*/ minC, | ||
| 1043 | int/*unsigned*/ mask, | ||
| 1044 | char[] chars) { | ||
| 1045 | long norm32; | ||
| 1046 | int ch=0; | ||
| 1047 | /* need src.hasPrevious() */ | ||
| 1048 | if((ch=src.previous()) == UCharacterIterator.DONE) { | ||
| 1049 | return 0; | ||
| 1050 | } | ||
| 1051 | chars[0]=(char)ch; | ||
| 1052 | chars[1]=0; | ||
| 1053 | |||
| 1054 | /* check for a surrogate before getting norm32 to see if we need to | ||
| 1055 | * predecrement further */ | ||
| 1056 | if(chars[0]<minC) { | ||
| 1057 | return 0; | ||
| 1058 | } else if(!UTF16.isSurrogate(chars[0])) { | ||
| 1059 | return NormalizerImpl.getNorm32(chars[0]); | ||
| 1060 | } else if(UTF16.isLeadSurrogate(chars[0]) || (src.getIndex()==0)) { | ||
| 1061 | /* unpaired surrogate */ | ||
| 1062 | chars[1]=(char)src.current(); | ||
| 1063 | return 0; | ||
| 1064 | } else if(UTF16.isLeadSurrogate(chars[1]=(char)src.previous())) { | ||
| 1065 | norm32=NormalizerImpl.getNorm32(chars[1]); | ||
| 1066 | if((norm32&mask)==0) { | ||
| 1067 | /* all surrogate pairs with this lead surrogate have irrelevant | ||
| 1068 | * data */ | ||
| 1069 | return 0; | ||
| 1070 | } else { | ||
| 1071 | /* norm32 must be a surrogate special */ | ||
| 1072 | return NormalizerImpl.getNorm32FromSurrogatePair(norm32,chars[0]); | ||
| 1073 | } | ||
| 1074 | } else { | ||
| 1075 | /* unpaired second surrogate, undo the c2=src.previous() movement */ | ||
| 1076 | src.moveIndex( 1); | ||
| 1077 | return 0; | ||
| 1078 | } | ||
| 1079 | } | ||
| 1080 | |||
| 1081 | private interface IsPrevBoundary{ | ||
| 1082 | public boolean isPrevBoundary(UCharacterIterator src, | ||
| 1083 | int/*unsigned*/ minC, | ||
| 1084 | int/*unsigned*/ mask, | ||
| 1085 | char[] chars); | ||
| 1086 | } | ||
| 1087 | private static final class IsPrevNFDSafe implements IsPrevBoundary{ | ||
| 1088 | /* | ||
| 1089 | * for NF*D: | ||
| 1090 | * read backwards and check if the lead combining class is 0 | ||
| 1091 | * if c2!=0 then (c2, c) is a surrogate pair (reversed - c2 is first | ||
| 1092 | * surrogate but read second!) | ||
| 1093 | */ | ||
| 1094 | public boolean isPrevBoundary(UCharacterIterator src, | ||
| 1095 | int/*unsigned*/ minC, | ||
| 1096 | int/*unsigned*/ ccOrQCMask, | ||
| 1097 | char[] chars) { | ||
| 1098 | |||
| 1099 | return NormalizerImpl.isNFDSafe(getPrevNorm32(src, minC, | ||
| 1100 | ccOrQCMask, chars), | ||
| 1101 | ccOrQCMask, | ||
| 1102 | ccOrQCMask& NormalizerImpl.QC_MASK); | ||
| 1103 | } | ||
| 1104 | } | ||
| 1105 | |||
| 1106 | private static final class IsPrevTrueStarter implements IsPrevBoundary{ | ||
| 1107 | /* | ||
| 1108 | * read backwards and check if the character is (or its decomposition | ||
| 1109 | * begins with) a "true starter" (cc==0 and NF*C_YES) | ||
| 1110 | * if c2!=0 then (c2, c) is a surrogate pair (reversed - c2 is first | ||
| 1111 | * surrogate but read second!) | ||
| 1112 | */ | ||
| 1113 | public boolean isPrevBoundary(UCharacterIterator src, | ||
| 1114 | int/*unsigned*/ minC, | ||
| 1115 | int/*unsigned*/ ccOrQCMask, | ||
| 1116 | char[] chars) { | ||
| 1117 | long norm32; | ||
| 1118 | int/*unsigned*/ decompQCMask; | ||
| 1119 | |||
| 1120 | decompQCMask=(ccOrQCMask<<2)&0xf; /*decomposition quick check mask*/ | ||
| 1121 | norm32=getPrevNorm32(src, minC, ccOrQCMask|decompQCMask, chars); | ||
| 1122 | return NormalizerImpl.isTrueStarter(norm32,ccOrQCMask,decompQCMask); | ||
| 1123 | } | ||
| 1124 | } | ||
| 1125 | |||
| 1126 | private static int findPreviousIterationBoundary(UCharacterIterator src, | ||
| 1127 | IsPrevBoundary obj, | ||
| 1128 | int/*unsigned*/ minC, | ||
| 1129 | int/*mask*/ mask, | ||
| 1130 | char[] buffer, | ||
| 1131 | int[] startIndex) { | ||
| 1132 | char[] chars=new char[2]; | ||
| 1133 | boolean isBoundary; | ||
| 1134 | |||
| 1135 | /* fill the buffer from the end backwards */ | ||
| 1136 | startIndex[0] = buffer.length; | ||
| 1137 | chars[0]=0; | ||
| 1138 | while(src.getIndex()>0 && chars[0]!=UCharacterIterator.DONE) { | ||
| 1139 | isBoundary=obj.isPrevBoundary(src, minC, mask, chars); | ||
| 1140 | |||
| 1141 | /* always write this character to the front of the buffer */ | ||
| 1142 | /* make sure there is enough space in the buffer */ | ||
| 1143 | if(startIndex[0] < (chars[1]==0 ? 1 : 2)) { | ||
| 1144 | |||
| 1145 | // grow the buffer | ||
| 1146 | char[] newBuf = new char[buffer.length*2]; | ||
| 1147 | /* move the current buffer contents up */ | ||
| 1148 | System.arraycopy(buffer,startIndex[0],newBuf, | ||
| 1149 | newBuf.length-(buffer.length-startIndex[0]), | ||
| 1150 | buffer.length-startIndex[0]); | ||
| 1151 | //adjust the startIndex | ||
| 1152 | startIndex[0]+=newBuf.length-buffer.length; | ||
| 1153 | |||
| 1154 | buffer=newBuf; | ||
| 1155 | newBuf=null; | ||
| 1156 | |||
| 1157 | } | ||
| 1158 | |||
| 1159 | buffer[--startIndex[0]]=chars[0]; | ||
| 1160 | if(chars[1]!=0) { | ||
| 1161 | buffer[--startIndex[0]]=chars[1]; | ||
| 1162 | } | ||
| 1163 | |||
| 1164 | /* stop if this just-copied character is a boundary */ | ||
| 1165 | if(isBoundary) { | ||
| 1166 | break; | ||
| 1167 | } | ||
| 1168 | } | ||
| 1169 | |||
| 1170 | /* return the length of the buffer contents */ | ||
| 1171 | return buffer.length-startIndex[0]; | ||
| 1172 | } | ||
| 1173 | |||
| 1174 | private static int previous(UCharacterIterator src, | ||
| 1175 | char[] dest, int destStart, int destLimit, | ||
| 1176 | Mode mode, | ||
| 1177 | boolean doNormalize, | ||
| 1178 | boolean[] pNeededToNormalize, | ||
| 1179 | int options) { | ||
| 1180 | |||
| 1181 | IsPrevBoundary isPreviousBoundary; | ||
| 1182 | int destLength, bufferLength; | ||
| 1183 | int/*unsigned*/ mask; | ||
| 1184 | int c,c2; | ||
| 1185 | |||
| 1186 | char minC; | ||
| 1187 | int destCapacity = destLimit-destStart; | ||
| 1188 | destLength=0; | ||
| 1189 | |||
| 1190 | if(pNeededToNormalize!=null) { | ||
| 1191 | pNeededToNormalize[0]=false; | ||
| 1192 | } | ||
| 1193 | minC = (char)mode.getMinC(); | ||
| 1194 | mask = mode.getMask(); | ||
| 1195 | isPreviousBoundary = mode.getPrevBoundary(); | ||
| 1196 | |||
| 1197 | if(isPreviousBoundary==null) { | ||
| 1198 | destLength=0; | ||
| 1199 | if((c=src.previous())>=0) { | ||
| 1200 | destLength=1; | ||
| 1201 | if(UTF16.isTrailSurrogate((char)c)) { | ||
| 1202 | c2= src.previous(); | ||
| 1203 | if(c2!= UCharacterIterator.DONE) { | ||
| 1204 | if(UTF16.isLeadSurrogate((char)c2)) { | ||
| 1205 | if(destCapacity>=2) { | ||
| 1206 | dest[1]=(char)c; // trail surrogate | ||
| 1207 | destLength=2; | ||
| 1208 | } | ||
| 1209 | // lead surrogate to be written below | ||
| 1210 | c=c2; | ||
| 1211 | } else { | ||
| 1212 | src.moveIndex(1); | ||
| 1213 | } | ||
| 1214 | } | ||
| 1215 | } | ||
| 1216 | |||
| 1217 | if(destCapacity>0) { | ||
| 1218 | dest[0]=(char)c; | ||
| 1219 | } | ||
| 1220 | } | ||
| 1221 | return destLength; | ||
| 1222 | } | ||
| 1223 | |||
| 1224 | char[] buffer = new char[100]; | ||
| 1225 | int[] startIndex= new int[1]; | ||
| 1226 | bufferLength=findPreviousIterationBoundary(src, | ||
| 1227 | isPreviousBoundary, | ||
| 1228 | minC, mask,buffer, | ||
| 1229 | startIndex); | ||
| 1230 | if(bufferLength>0) { | ||
| 1231 | if(doNormalize) { | ||
| 1232 | destLength=NormalizerBase.normalize(buffer,startIndex[0], | ||
| 1233 | startIndex[0]+bufferLength, | ||
| 1234 | dest, destStart,destLimit, | ||
| 1235 | mode, options); | ||
| 1236 | |||
| 1237 | if(pNeededToNormalize!=null) { | ||
| 1238 | pNeededToNormalize[0]=(boolean)(destLength!=bufferLength || | ||
| 1239 | Utility.arrayRegionMatches( | ||
| 1240 | buffer,0,dest, | ||
| 1241 | destStart,destLimit | ||
| 1242 | )); | ||
| 1243 | } | ||
| 1244 | } else { | ||
| 1245 | /* just copy the source characters */ | ||
| 1246 | if(destCapacity>0) { | ||
| 1247 | System.arraycopy(buffer,startIndex[0],dest,0, | ||
| 1248 | (bufferLength<destCapacity) ? | ||
| 1249 | bufferLength : destCapacity | ||
| 1250 | ); | ||
| 1251 | } | ||
| 1252 | } | ||
| 1253 | } | ||
| 1254 | |||
| 1255 | |||
| 1256 | return destLength; | ||
| 1257 | } | ||
| 1258 | |||
| 1259 | |||
| 1260 | |||
| 1261 | /* forward iteration ---------------------------------------------------- */ | ||
| 1262 | /* | ||
| 1263 | * read forward and check if the character is a next-iteration boundary | ||
| 1264 | * if c2!=0 then (c, c2) is a surrogate pair | ||
| 1265 | */ | ||
| 1266 | private interface IsNextBoundary{ | ||
| 1267 | boolean isNextBoundary(UCharacterIterator src, | ||
| 1268 | int/*unsigned*/ minC, | ||
| 1269 | int/*unsigned*/ mask, | ||
| 1270 | int[] chars); | ||
| 1271 | } | ||
| 1272 | /* | ||
| 1273 | * read forward and get norm32 | ||
| 1274 | * return 0 if the character is <minC | ||
| 1275 | * if c2!=0 then (c2, c) is a surrogate pair | ||
| 1276 | * always reads complete characters | ||
| 1277 | */ | ||
| 1278 | private static long /*unsigned*/ getNextNorm32(UCharacterIterator src, | ||
| 1279 | int/*unsigned*/ minC, | ||
| 1280 | int/*unsigned*/ mask, | ||
| 1281 | int[] chars) { | ||
| 1282 | long norm32; | ||
| 1283 | |||
| 1284 | /* need src.hasNext() to be true */ | ||
| 1285 | chars[0]=src.next(); | ||
| 1286 | chars[1]=0; | ||
| 1287 | |||
| 1288 | if(chars[0]<minC) { | ||
| 1289 | return 0; | ||
| 1290 | } | ||
| 1291 | |||
| 1292 | norm32=NormalizerImpl.getNorm32((char)chars[0]); | ||
| 1293 | if(UTF16.isLeadSurrogate((char)chars[0])) { | ||
| 1294 | if(src.current()!=UCharacterIterator.DONE && | ||
| 1295 | UTF16.isTrailSurrogate((char)(chars[1]=src.current()))) { | ||
| 1296 | src.moveIndex(1); /* skip the c2 surrogate */ | ||
| 1297 | if((norm32&mask)==0) { | ||
| 1298 | /* irrelevant data */ | ||
| 1299 | return 0; | ||
| 1300 | } else { | ||
| 1301 | /* norm32 must be a surrogate special */ | ||
| 1302 | return NormalizerImpl.getNorm32FromSurrogatePair(norm32,(char)chars[1]); | ||
| 1303 | } | ||
| 1304 | } else { | ||
| 1305 | /* unmatched surrogate */ | ||
| 1306 | return 0; | ||
| 1307 | } | ||
| 1308 | } | ||
| 1309 | return norm32; | ||
| 1310 | } | ||
| 1311 | |||
| 1312 | |||
| 1313 | /* | ||
| 1314 | * for NF*D: | ||
| 1315 | * read forward and check if the lead combining class is 0 | ||
| 1316 | * if c2!=0 then (c, c2) is a surrogate pair | ||
| 1317 | */ | ||
| 1318 | private static final class IsNextNFDSafe implements IsNextBoundary{ | ||
| 1319 | public boolean isNextBoundary(UCharacterIterator src, | ||
| 1320 | int/*unsigned*/ minC, | ||
| 1321 | int/*unsigned*/ ccOrQCMask, | ||
| 1322 | int[] chars) { | ||
| 1323 | return NormalizerImpl.isNFDSafe(getNextNorm32(src,minC,ccOrQCMask,chars), | ||
| 1324 | ccOrQCMask, ccOrQCMask&NormalizerImpl.QC_MASK); | ||
| 1325 | } | ||
| 1326 | } | ||
| 1327 | |||
| 1328 | /* | ||
| 1329 | * for NF*C: | ||
| 1330 | * read forward and check if the character is (or its decomposition begins | ||
| 1331 | * with) a "true starter" (cc==0 and NF*C_YES) | ||
| 1332 | * if c2!=0 then (c, c2) is a surrogate pair | ||
| 1333 | */ | ||
| 1334 | private static final class IsNextTrueStarter implements IsNextBoundary{ | ||
| 1335 | public boolean isNextBoundary(UCharacterIterator src, | ||
| 1336 | int/*unsigned*/ minC, | ||
| 1337 | int/*unsigned*/ ccOrQCMask, | ||
| 1338 | int[] chars) { | ||
| 1339 | long norm32; | ||
| 1340 | int/*unsigned*/ decompQCMask; | ||
| 1341 | |||
| 1342 | decompQCMask=(ccOrQCMask<<2)&0xf; /*decomposition quick check mask*/ | ||
| 1343 | norm32=getNextNorm32(src, minC, ccOrQCMask|decompQCMask, chars); | ||
| 1344 | return NormalizerImpl.isTrueStarter(norm32, ccOrQCMask, decompQCMask); | ||
| 1345 | } | ||
| 1346 | } | ||
| 1347 | |||
| 1348 | private static int findNextIterationBoundary(UCharacterIterator src, | ||
| 1349 | IsNextBoundary obj, | ||
| 1350 | int/*unsigned*/ minC, | ||
| 1351 | int/*unsigned*/ mask, | ||
| 1352 | char[] buffer) { | ||
| 1353 | if(src.current()==UCharacterIterator.DONE) { | ||
| 1354 | return 0; | ||
| 1355 | } | ||
| 1356 | |||
| 1357 | /* get one character and ignore its properties */ | ||
| 1358 | int[] chars = new int[2]; | ||
| 1359 | chars[0]=src.next(); | ||
| 1360 | buffer[0]=(char)chars[0]; | ||
| 1361 | int bufferIndex = 1; | ||
| 1362 | |||
| 1363 | if(UTF16.isLeadSurrogate((char)chars[0])&& | ||
| 1364 | src.current()!=UCharacterIterator.DONE) { | ||
| 1365 | if(UTF16.isTrailSurrogate((char)(chars[1]=src.next()))) { | ||
| 1366 | buffer[bufferIndex++]=(char)chars[1]; | ||
| 1367 | } else { | ||
| 1368 | src.moveIndex(-1); /* back out the non-trail-surrogate */ | ||
| 1369 | } | ||
| 1370 | } | ||
| 1371 | |||
| 1372 | /* get all following characters until we see a boundary */ | ||
| 1373 | /* checking hasNext() instead of c!=DONE on the off-chance that U+ffff | ||
| 1374 | * is part of the string */ | ||
| 1375 | while( src.current()!=UCharacterIterator.DONE) { | ||
| 1376 | if(obj.isNextBoundary(src, minC, mask, chars)) { | ||
| 1377 | /* back out the latest movement to stop at the boundary */ | ||
| 1378 | src.moveIndex(chars[1]==0 ? -1 : -2); | ||
| 1379 | break; | ||
| 1380 | } else { | ||
| 1381 | if(bufferIndex+(chars[1]==0 ? 1 : 2)<=buffer.length) { | ||
| 1382 | buffer[bufferIndex++]=(char)chars[0]; | ||
| 1383 | if(chars[1]!=0) { | ||
| 1384 | buffer[bufferIndex++]=(char)chars[1]; | ||
| 1385 | } | ||
| 1386 | } else { | ||
| 1387 | char[] newBuf = new char[buffer.length*2]; | ||
| 1388 | System.arraycopy(buffer,0,newBuf,0,bufferIndex); | ||
| 1389 | buffer = newBuf; | ||
| 1390 | buffer[bufferIndex++]=(char)chars[0]; | ||
| 1391 | if(chars[1]!=0) { | ||
| 1392 | buffer[bufferIndex++]=(char)chars[1]; | ||
| 1393 | } | ||
| 1394 | } | ||
| 1395 | } | ||
| 1396 | } | ||
| 1397 | |||
| 1398 | /* return the length of the buffer contents */ | ||
| 1399 | return bufferIndex; | ||
| 1400 | } | ||
| 1401 | |||
| 1402 | private static int next(UCharacterIterator src, | ||
| 1403 | char[] dest, int destStart, int destLimit, | ||
| 1404 | NormalizerBase.Mode mode, | ||
| 1405 | boolean doNormalize, | ||
| 1406 | boolean[] pNeededToNormalize, | ||
| 1407 | int options) { | ||
| 1408 | |||
| 1409 | IsNextBoundary isNextBoundary; | ||
| 1410 | int /*unsigned*/ mask; | ||
| 1411 | int /*unsigned*/ bufferLength; | ||
| 1412 | int c,c2; | ||
| 1413 | char minC; | ||
| 1414 | int destCapacity = destLimit - destStart; | ||
| 1415 | int destLength = 0; | ||
| 1416 | if(pNeededToNormalize!=null) { | ||
| 1417 | pNeededToNormalize[0]=false; | ||
| 1418 | } | ||
| 1419 | |||
| 1420 | minC = (char)mode.getMinC(); | ||
| 1421 | mask = mode.getMask(); | ||
| 1422 | isNextBoundary = mode.getNextBoundary(); | ||
| 1423 | |||
| 1424 | if(isNextBoundary==null) { | ||
| 1425 | destLength=0; | ||
| 1426 | c=src.next(); | ||
| 1427 | if(c!=UCharacterIterator.DONE) { | ||
| 1428 | destLength=1; | ||
| 1429 | if(UTF16.isLeadSurrogate((char)c)) { | ||
| 1430 | c2= src.next(); | ||
| 1431 | if(c2!= UCharacterIterator.DONE) { | ||
| 1432 | if(UTF16.isTrailSurrogate((char)c2)) { | ||
| 1433 | if(destCapacity>=2) { | ||
| 1434 | dest[1]=(char)c2; // trail surrogate | ||
| 1435 | destLength=2; | ||
| 1436 | } | ||
| 1437 | // lead surrogate to be written below | ||
| 1438 | } else { | ||
| 1439 | src.moveIndex(-1); | ||
| 1440 | } | ||
| 1441 | } | ||
| 1442 | } | ||
| 1443 | |||
| 1444 | if(destCapacity>0) { | ||
| 1445 | dest[0]=(char)c; | ||
| 1446 | } | ||
| 1447 | } | ||
| 1448 | return destLength; | ||
| 1449 | } | ||
| 1450 | |||
| 1451 | char[] buffer=new char[100]; | ||
| 1452 | int[] startIndex = new int[1]; | ||
| 1453 | bufferLength=findNextIterationBoundary(src,isNextBoundary, minC, mask, | ||
| 1454 | buffer); | ||
| 1455 | if(bufferLength>0) { | ||
| 1456 | if(doNormalize) { | ||
| 1457 | destLength=mode.normalize(buffer,startIndex[0],bufferLength, | ||
| 1458 | dest,destStart,destLimit, options); | ||
| 1459 | |||
| 1460 | if(pNeededToNormalize!=null) { | ||
| 1461 | pNeededToNormalize[0]=(boolean)(destLength!=bufferLength || | ||
| 1462 | Utility.arrayRegionMatches(buffer,startIndex[0], | ||
| 1463 | dest,destStart, | ||
| 1464 | destLength)); | ||
| 1465 | } | ||
| 1466 | } else { | ||
| 1467 | /* just copy the source characters */ | ||
| 1468 | if(destCapacity>0) { | ||
| 1469 | System.arraycopy(buffer,0,dest,destStart, | ||
| 1470 | Math.min(bufferLength,destCapacity) | ||
| 1471 | ); | ||
| 1472 | } | ||
| 1473 | |||
| 1474 | |||
| 1475 | } | ||
| 1476 | } | ||
| 1477 | return destLength; | ||
| 1478 | } | ||
| 1479 | |||
| 1480 | private void clearBuffer() { | ||
| 1481 | bufferLimit=bufferStart=bufferPos=0; | ||
| 1482 | } | ||
| 1483 | |||
| 1484 | private boolean nextNormalize() { | ||
| 1485 | |||
| 1486 | clearBuffer(); | ||
| 1487 | currentIndex=nextIndex; | ||
| 1488 | text.setIndex(nextIndex); | ||
| 1489 | |||
| 1490 | bufferLimit=next(text,buffer,bufferStart,buffer.length,mode,true,null,options); | ||
| 1491 | |||
| 1492 | nextIndex=text.getIndex(); | ||
| 1493 | return (bufferLimit>0); | ||
| 1494 | } | ||
| 1495 | |||
| 1496 | private boolean previousNormalize() { | ||
| 1497 | |||
| 1498 | clearBuffer(); | ||
| 1499 | nextIndex=currentIndex; | ||
| 1500 | text.setIndex(currentIndex); | ||
| 1501 | bufferLimit=previous(text,buffer,bufferStart,buffer.length,mode,true,null,options); | ||
| 1502 | |||
| 1503 | currentIndex=text.getIndex(); | ||
| 1504 | bufferPos = bufferLimit; | ||
| 1505 | return bufferLimit>0; | ||
| 1506 | } | ||
| 1507 | |||
| 1508 | private int getCodePointAt(int index) { | ||
| 1509 | if( UTF16.isSurrogate(buffer[index])) { | ||
| 1510 | if(UTF16.isLeadSurrogate(buffer[index])) { | ||
| 1511 | if((index+1)<bufferLimit && | ||
| 1512 | UTF16.isTrailSurrogate(buffer[index+1])) { | ||
| 1513 | return UCharacterProperty.getRawSupplementary( | ||
| 1514 | buffer[index], | ||
| 1515 | buffer[index+1] | ||
| 1516 | ); | ||
| 1517 | } | ||
| 1518 | }else if(UTF16.isTrailSurrogate(buffer[index])) { | ||
| 1519 | if(index>0 && UTF16.isLeadSurrogate(buffer[index-1])) { | ||
| 1520 | return UCharacterProperty.getRawSupplementary( | ||
| 1521 | buffer[index-1], | ||
| 1522 | buffer[index] | ||
| 1523 | ); | ||
| 1524 | } | ||
| 1525 | } | ||
| 1526 | } | ||
| 1527 | return buffer[index]; | ||
| 1528 | |||
| 1529 | } | ||
| 1530 | |||
| 1531 | /** | ||
| 1532 | * Internal API | ||
| 1533 | * @internal | ||
| 1534 | */ | ||
| 1535 | public static boolean isNFSkippable(int c, Mode mode) { | ||
| 1536 | return mode.isNFSkippable(c); | ||
| 1537 | } | ||
| 1538 | |||
| 1539 | // | ||
| 1540 | // Options | ||
| 1541 | // | ||
| 1542 | |||
| 1543 | /* | ||
| 1544 | * Default option for Unicode 3.2.0 normalization. | ||
| 1545 | * Corrigendum 4 was fixed in Unicode 3.2.0 but isn't supported in | ||
| 1546 | * IDNA/StringPrep. | ||
| 1547 | * The public review issue #29 was fixed in Unicode 4.1.0. Corrigendum 5 | ||
| 1548 | * allowed Unicode 3.2 to 4.0.1 to apply the fix for PRI #29, but it isn't | ||
| 1549 | * supported by IDNA/StringPrep as well as Corrigendum 4. | ||
| 1550 | */ | ||
| 1551 | public static final int UNICODE_3_2_0_ORIGINAL = | ||
| 1552 | UNICODE_3_2 | | ||
| 1553 | NormalizerImpl.WITHOUT_CORRIGENDUM4_CORRECTIONS | | ||
| 1554 | NormalizerImpl.BEFORE_PRI_29; | ||
| 1555 | |||
| 1556 | /* | ||
| 1557 | * Default option for the latest Unicode normalization. This option is | ||
| 1558 | * provided mainly for testing. | ||
| 1559 | * The value zero means that normalization is done with the fixes for | ||
| 1560 | * - Corrigendum 4 (Five CJK Canonical Mapping Errors) | ||
| 1561 | * - Corrigendum 5 (Normalization Idempotency) | ||
| 1562 | */ | ||
| 1563 | public static final int UNICODE_LATEST = 0x00; | ||
| 1564 | |||
| 1565 | // | ||
| 1566 | // public constructor and methods for java.text.Normalizer and | ||
| 1567 | // sun.text.Normalizer | ||
| 1568 | // | ||
| 1569 | |||
| 1570 | /** | ||
| 1571 | * Creates a new <tt>Normalizer</tt> object for iterating over the | ||
| 1572 | * normalized form of a given string. | ||
| 1573 | * | ||
| 1574 | * @param str The string to be normalized. The normalization | ||
| 1575 | * will start at the beginning of the string. | ||
| 1576 | * | ||
| 1577 | * @param mode The normalization mode. | ||
| 1578 | */ | ||
| 1579 | public NormalizerBase(String str, Mode mode) { | ||
| 1580 | this(str, mode, UNICODE_LATEST); | ||
| 1581 | } | ||
| 1582 | |||
| 1583 | /** | ||
| 1584 | * Normalizes a <code>String</code> using the given normalization form. | ||
| 1585 | * | ||
| 1586 | * @param str the input string to be normalized. | ||
| 1587 | * @param form the normalization form | ||
| 1588 | */ | ||
| 1589 | public static String normalize(String str, Normalizer.Form form) { | ||
| 1590 | return normalize(str, form, UNICODE_LATEST); | ||
| 1591 | } | ||
| 1592 | |||
| 1593 | /** | ||
| 1594 | * Normalizes a <code>String</code> using the given normalization form. | ||
| 1595 | * | ||
| 1596 | * @param str the input string to be normalized. | ||
| 1597 | * @param form the normalization form | ||
| 1598 | * @param options the optional features to be enabled. | ||
| 1599 | */ | ||
| 1600 | public static String normalize(String str, Normalizer.Form form, int options) { | ||
| 1601 | int len = str.length(); | ||
| 1602 | boolean asciiOnly = true; | ||
| 1603 | if (len < 80) { | ||
| 1604 | for (int i = 0; i < len; i++) { | ||
| 1605 | if (str.charAt(i) > 127) { | ||
| 1606 | asciiOnly = false; | ||
| 1607 | break; | ||
| 1608 | } | ||
| 1609 | } | ||
| 1610 | } else { | ||
| 1611 | char[] a = str.toCharArray(); | ||
| 1612 | for (int i = 0; i < len; i++) { | ||
| 1613 | if (a[i] > 127) { | ||
| 1614 | asciiOnly = false; | ||
| 1615 | break; | ||
| 1616 | } | ||
| 1617 | } | ||
| 1618 | } | ||
| 1619 | |||
| 1620 | switch (form) { | ||
| 1621 | case NFC : | ||
| 1622 | return asciiOnly ? str : NFC.normalize(str, options); | ||
| 1623 | case NFD : | ||
| 1624 | return asciiOnly ? str : NFD.normalize(str, options); | ||
| 1625 | case NFKC : | ||
| 1626 | return asciiOnly ? str : NFKC.normalize(str, options); | ||
| 1627 | case NFKD : | ||
| 1628 | return asciiOnly ? str : NFKD.normalize(str, options); | ||
| 1629 | } | ||
| 1630 | |||
| 1631 | throw new IllegalArgumentException("Unexpected normalization form: " + | ||
| 1632 | form); | ||
| 1633 | } | ||
| 1634 | |||
| 1635 | /** | ||
| 1636 | * Test if a string is in a given normalization form. | ||
| 1637 | * This is semantically equivalent to source.equals(normalize(source, mode)). | ||
| 1638 | * | ||
| 1639 | * Unlike quickCheck(), this function returns a definitive result, | ||
| 1640 | * never a "maybe". | ||
| 1641 | * For NFD, NFKD, and FCD, both functions work exactly the same. | ||
| 1642 | * For NFC and NFKC where quickCheck may return "maybe", this function will | ||
| 1643 | * perform further tests to arrive at a true/false result. | ||
| 1644 | * @param str the input string to be checked to see if it is normalized | ||
| 1645 | * @param form the normalization form | ||
| 1646 | * @param options the optional features to be enabled. | ||
| 1647 | */ | ||
| 1648 | public static boolean isNormalized(String str, Normalizer.Form form) { | ||
| 1649 | return isNormalized(str, form, UNICODE_LATEST); | ||
| 1650 | } | ||
| 1651 | |||
| 1652 | /** | ||
| 1653 | * Test if a string is in a given normalization form. | ||
| 1654 | * This is semantically equivalent to source.equals(normalize(source, mode)). | ||
| 1655 | * | ||
| 1656 | * Unlike quickCheck(), this function returns a definitive result, | ||
| 1657 | * never a "maybe". | ||
| 1658 | * For NFD, NFKD, and FCD, both functions work exactly the same. | ||
| 1659 | * For NFC and NFKC where quickCheck may return "maybe", this function will | ||
| 1660 | * perform further tests to arrive at a true/false result. | ||
| 1661 | * @param str the input string to be checked to see if it is normalized | ||
| 1662 | * @param form the normalization form | ||
| 1663 | * @param options the optional features to be enabled. | ||
| 1664 | */ | ||
| 1665 | public static boolean isNormalized(String str, Normalizer.Form form, int options) { | ||
| 1666 | switch (form) { | ||
| 1667 | case NFC: | ||
| 1668 | return (NFC.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); | ||
| 1669 | case NFD: | ||
| 1670 | return (NFD.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); | ||
| 1671 | case NFKC: | ||
| 1672 | return (NFKC.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); | ||
| 1673 | case NFKD: | ||
| 1674 | return (NFKD.quickCheck(str.toCharArray(),0,str.length(),false,NormalizerImpl.getNX(options))==YES); | ||
| 1675 | } | ||
| 1676 | |||
| 1677 | throw new IllegalArgumentException("Unexpected normalization form: " + | ||
| 1678 | form); | ||
| 1679 | } | ||
| 1680 | } | ||