1 /* 2 Copyright (C) 2014-2016 Quinten Lansu 3 4 Permission is hereby granted, free of charge, to any person 5 obtaining a copy of this software and associated documentation 6 files (the "Software"), to deal in the Software without 7 restriction, including without limitation the rights to use, 8 copy, modify, merge, publish, distribute, sublicense, and/or 9 sell copies of the Software, and to permit persons to whom the 10 Software is furnished to do so, subject to the following 11 conditions: 12 13 The above copyright notice and this permission notice shall be 14 included in all copies or substantial portions of the Software. 15 16 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 17 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES 18 OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND 19 NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT 20 HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, 21 WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 22 FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR 23 OTHER DEALINGS IN THE SOFTWARE. 24 */ 25 26 /* This is the concatenation of 27 28 base.h casemapping.h codepoint.h database.h streaming.h 29 composition.h decomposition.h unicodedatabase.h utf8rewind.h 30 (order is important) 31 32 with some modifications to simplify 33 */ 34 35 #ifndef U8_H 36 #define U8_H 1 37 38 #ifndef _UTF8REWIND_H_ 39 #define _UTF8REWIND_H_ 40 41 42 43 44 #define UTF8_VERSION_MAKE(_major, _minor, _bugfix) \ 45 ((_major) * 10000) + ((_minor) * 100) + (_bugfix) 46 47 #define UTF8_VERSION_MAJOR 1 48 49 #define UTF8_VERSION_MINOR 5 50 51 #define UTF8_VERSION_BUGFIX 1 52 53 #define UTF8_VERSION \ 54 UTF8_VERSION_MAKE(UTF8_VERSION_MAJOR, UTF8_VERSION_MINOR, UTF8_VERSION_BUGFIX) 55 56 #define UTF8_VERSION_STRING "1.5.1" 57 58 #define UTF8_VERSION_GUARD(_major, _minor, _bugfix) \ 59 (UTF8_VERSION >= UTF8_VERSION_MAKE(_major, _minor, _bugfix)) 60 61 62 63 #define UTF8_ERR_NONE (0) 64 65 #define UTF8_ERR_INVALID_DATA (-1) 66 67 #define UTF8_ERR_INVALID_FLAG (-2) 68 69 #define UTF8_ERR_NOT_ENOUGH_SPACE (-3) 70 71 #define UTF8_ERR_OVERLAPPING_PARAMETERS (-4) 72 73 #define UTF8_ERR_INVALID_LOCALE (-5) 74 75 76 77 #define UTF8_LOCALE_DEFAULT 0 78 79 #define UTF8_LOCALE_LITHUANIAN 1 80 81 #define UTF8_LOCALE_TURKISH_AND_AZERI_LATIN 2 82 83 #define UTF8_LOCALE_MAXIMUM 3 84 85 86 87 #define UTF8_NORMALIZE_COMPOSE 0x00000001 88 89 #define UTF8_NORMALIZE_DECOMPOSE 0x00000002 90 91 #define UTF8_NORMALIZE_COMPATIBILITY 0x00000004 92 93 #define UTF8_NORMALIZATION_RESULT_YES (0) 94 95 #define UTF8_NORMALIZATION_RESULT_MAYBE (1) 96 97 #define UTF8_NORMALIZATION_RESULT_NO (2) 98 99 100 101 #define UTF8_CATEGORY_LETTER_UPPERCASE 0x00000001 102 103 #define UTF8_CATEGORY_LETTER_LOWERCASE 0x00000002 104 105 #define UTF8_CATEGORY_LETTER_TITLECASE 0x00000004 106 107 #define UTF8_CATEGORY_LETTER_MODIFIER 0x00000008 108 109 #define UTF8_CATEGORY_LETTER_OTHER 0x00000010 110 111 #define UTF8_CATEGORY_LETTER \ 112 (UTF8_CATEGORY_LETTER_UPPERCASE | UTF8_CATEGORY_LETTER_LOWERCASE | \ 113 UTF8_CATEGORY_LETTER_TITLECASE | UTF8_CATEGORY_LETTER_MODIFIER | \ 114 UTF8_CATEGORY_LETTER_OTHER) 115 116 #define UTF8_CATEGORY_CASE_MAPPED \ 117 (UTF8_CATEGORY_LETTER_UPPERCASE | UTF8_CATEGORY_LETTER_LOWERCASE | \ 118 UTF8_CATEGORY_LETTER_TITLECASE) 119 120 #define UTF8_CATEGORY_MARK_NON_SPACING 0x00000020 121 122 #define UTF8_CATEGORY_MARK_SPACING 0x00000040 123 124 #define UTF8_CATEGORY_MARK_ENCLOSING 0x00000080 125 126 #define UTF8_CATEGORY_MARK \ 127 (UTF8_CATEGORY_MARK_NON_SPACING | UTF8_CATEGORY_MARK_SPACING | \ 128 UTF8_CATEGORY_MARK_ENCLOSING) 129 130 #define UTF8_CATEGORY_NUMBER_DECIMAL 0x00000100 131 132 #define UTF8_CATEGORY_NUMBER_LETTER 0x00000200 133 134 #define UTF8_CATEGORY_NUMBER_OTHER 0x00000400 135 136 #define UTF8_CATEGORY_NUMBER \ 137 (UTF8_CATEGORY_NUMBER_DECIMAL | UTF8_CATEGORY_NUMBER_LETTER | \ 138 UTF8_CATEGORY_NUMBER_OTHER) 139 140 #define UTF8_CATEGORY_PUNCTUATION_CONNECTOR 0x00000800 141 142 #define UTF8_CATEGORY_PUNCTUATION_DASH 0x00001000 143 144 #define UTF8_CATEGORY_PUNCTUATION_OPEN 0x00002000 145 146 #define UTF8_CATEGORY_PUNCTUATION_CLOSE 0x00004000 147 148 #define UTF8_CATEGORY_PUNCTUATION_INITIAL 0x00008000 149 150 #define UTF8_CATEGORY_PUNCTUATION_FINAL 0x00010000 151 152 #define UTF8_CATEGORY_PUNCTUATION_OTHER 0x00020000 153 154 #define UTF8_CATEGORY_PUNCTUATION \ 155 (UTF8_CATEGORY_PUNCTUATION_CONNECTOR | UTF8_CATEGORY_PUNCTUATION_DASH | \ 156 UTF8_CATEGORY_PUNCTUATION_OPEN | UTF8_CATEGORY_PUNCTUATION_CLOSE | \ 157 UTF8_CATEGORY_PUNCTUATION_INITIAL | UTF8_CATEGORY_PUNCTUATION_FINAL | \ 158 UTF8_CATEGORY_PUNCTUATION_OTHER) 159 160 #define UTF8_CATEGORY_SYMBOL_MATH 0x00040000 161 162 #define UTF8_CATEGORY_SYMBOL_CURRENCY 0x00080000 163 164 #define UTF8_CATEGORY_SYMBOL_MODIFIER 0x00100000 165 166 #define UTF8_CATEGORY_SYMBOL_OTHER 0x00200000 167 168 #define UTF8_CATEGORY_SYMBOL \ 169 (UTF8_CATEGORY_SYMBOL_MATH | UTF8_CATEGORY_SYMBOL_CURRENCY | \ 170 UTF8_CATEGORY_SYMBOL_MODIFIER | UTF8_CATEGORY_SYMBOL_OTHER) 171 172 #define UTF8_CATEGORY_SEPARATOR_SPACE 0x00400000 173 174 #define UTF8_CATEGORY_SEPARATOR_LINE 0x00800000 175 176 #define UTF8_CATEGORY_SEPARATOR_PARAGRAPH 0x01000000 177 178 #define UTF8_CATEGORY_SEPARATOR \ 179 (UTF8_CATEGORY_SEPARATOR_SPACE | UTF8_CATEGORY_SEPARATOR_LINE | \ 180 UTF8_CATEGORY_SEPARATOR_PARAGRAPH) 181 182 #define UTF8_CATEGORY_CONTROL 0x02000000 183 184 #define UTF8_CATEGORY_FORMAT 0x04000000 185 186 #define UTF8_CATEGORY_SURROGATE 0x08000000 187 188 #define UTF8_CATEGORY_PRIVATE_USE 0x10000000 189 190 #define UTF8_CATEGORY_UNASSIGNED 0x20000000 191 192 #define UTF8_CATEGORY_COMPATIBILITY 0x40000000 193 194 #define UTF8_CATEGORY_IGNORE_GRAPHEME_CLUSTER 0x80000000 195 196 #define UTF8_CATEGORY_ISCNTRL \ 197 (UTF8_CATEGORY_COMPATIBILITY | \ 198 UTF8_CATEGORY_CONTROL) 199 200 #define UTF8_CATEGORY_ISPRINT \ 201 (UTF8_CATEGORY_COMPATIBILITY | \ 202 UTF8_CATEGORY_LETTER | UTF8_CATEGORY_NUMBER | \ 203 UTF8_CATEGORY_PUNCTUATION | UTF8_CATEGORY_SYMBOL | \ 204 UTF8_CATEGORY_SEPARATOR) 205 206 #define UTF8_CATEGORY_ISSPACE \ 207 (UTF8_CATEGORY_COMPATIBILITY | \ 208 UTF8_CATEGORY_SEPARATOR_SPACE) 209 210 #define UTF8_CATEGORY_ISBLANK \ 211 (UTF8_CATEGORY_COMPATIBILITY | \ 212 UTF8_CATEGORY_SEPARATOR_SPACE | UTF8_CATEGORY_PRIVATE_USE) 213 214 #define UTF8_CATEGORY_ISGRAPH \ 215 (UTF8_CATEGORY_COMPATIBILITY | \ 216 UTF8_CATEGORY_LETTER | UTF8_CATEGORY_NUMBER | \ 217 UTF8_CATEGORY_PUNCTUATION | UTF8_CATEGORY_SYMBOL) 218 219 #define UTF8_CATEGORY_ISPUNCT \ 220 (UTF8_CATEGORY_COMPATIBILITY | \ 221 UTF8_CATEGORY_PUNCTUATION | UTF8_CATEGORY_SYMBOL) 222 223 #define UTF8_CATEGORY_ISALNUM \ 224 (UTF8_CATEGORY_COMPATIBILITY | \ 225 UTF8_CATEGORY_LETTER | UTF8_CATEGORY_NUMBER) 226 227 #define UTF8_CATEGORY_ISALPHA \ 228 (UTF8_CATEGORY_COMPATIBILITY | \ 229 UTF8_CATEGORY_LETTER) 230 231 #define UTF8_CATEGORY_ISUPPER \ 232 (UTF8_CATEGORY_COMPATIBILITY | \ 233 UTF8_CATEGORY_LETTER_UPPERCASE) 234 235 #define UTF8_CATEGORY_ISLOWER \ 236 (UTF8_CATEGORY_COMPATIBILITY | \ 237 UTF8_CATEGORY_LETTER_LOWERCASE) 238 239 #define UTF8_CATEGORY_ISDIGIT \ 240 (UTF8_CATEGORY_COMPATIBILITY | \ 241 UTF8_CATEGORY_NUMBER) 242 243 #define UTF8_CATEGORY_ISXDIGIT \ 244 (UTF8_CATEGORY_COMPATIBILITY | \ 245 UTF8_CATEGORY_NUMBER | UTF8_CATEGORY_PRIVATE_USE) 246 247 248 249 250 #ifndef UTF8_WCHAR_SIZE 251 #if (__SIZEOF_WCHAR_T__ == 4) || (WCHAR_MAX > UINT16_MAX) || (__WCHAR_MAX__ > UINT16_MAX) 252 #define UTF8_WCHAR_SIZE (4) 253 #else 254 #define UTF8_WCHAR_SIZE (2) 255 #endif 256 #endif 257 258 #if (UTF8_WCHAR_SIZE == 4) 259 260 #define UTF8_WCHAR_UTF32 (1) 261 #elif (UTF8_WCHAR_SIZE == 2) 262 263 #define UTF8_WCHAR_UTF16 (1) 264 #else 265 #error Invalid size for wchar_t type. 266 #endif 267 268 #ifndef UTF8_API 269 #ifdef __cplusplus 270 #define UTF8_API extern "C" 271 #else 272 #define UTF8_API 273 #endif 274 #endif 275 276 typedef int int32_t; 277 typedef unsigned char uint8_t; 278 typedef unsigned short uint16_t; 279 typedef unsigned int uint32_t; 280 typedef unsigned long long uint64_t; 281 282 typedef uint16_t utf16_t; 283 typedef uint32_t unicode_t; 284 285 #endif /* _UTF8REWIND_H_ */ 286 287 288 #ifndef _UTF8REWIND_INTERNAL_BASE_H_ 289 #define _UTF8REWIND_INTERNAL_BASE_H_ 290 291 292 293 294 #if defined(__GNUC__) && !defined(COMPILER_ICC) 295 #define UTF8_UNUSED(_parameter) _parameter __attribute__ ((unused)) 296 #else 297 #define UTF8_UNUSED(_parameter) _parameter 298 #endif 299 300 #define UTF8_SET_ERROR(_error) \ 301 if (errors != 0) { *errors = UTF8_ERR_ ## _error; } 302 303 /* Validates input before transforming */ 304 /* Check for parameter overlap using the separating axis theorem */ 305 306 #define UTF8_VALIDATE_PARAMETERS_CHAR(_inputType, _result) \ 307 if (input == 0) { \ 308 UTF8_SET_ERROR(INVALID_DATA); \ 309 return _result; \ 310 } \ 311 else if (inputSize < sizeof(_inputType)) { \ 312 if (target != 0) { \ 313 if (targetSize < 3) { \ 314 UTF8_SET_ERROR(NOT_ENOUGH_SPACE); \ 315 return _result; \ 316 } \ 317 memcpy(target, REPLACEMENT_CHARACTER_STRING, REPLACEMENT_CHARACTER_STRING_LENGTH); \ 318 } \ 319 UTF8_SET_ERROR(INVALID_DATA); \ 320 return _result + REPLACEMENT_CHARACTER_STRING_LENGTH; \ 321 } \ 322 if (target != 0 && targetSize == 0) { \ 323 UTF8_SET_ERROR(NOT_ENOUGH_SPACE); \ 324 return _result; \ 325 } \ 326 if ((char*)input == target) { \ 327 UTF8_SET_ERROR(OVERLAPPING_PARAMETERS); \ 328 return _result; \ 329 } \ 330 { \ 331 char* input_center = (char*)input + (inputSize / 2); \ 332 char* target_center = target + (targetSize / 2); \ 333 size_t delta = (size_t)((input_center > target_center) ? (input_center - target_center) : (target_center - input_center)); \ 334 if (delta < (inputSize + targetSize) / 2) { \ 335 UTF8_SET_ERROR(OVERLAPPING_PARAMETERS); \ 336 return _result; \ 337 } \ 338 } 339 340 #define UTF8_VALIDATE_PARAMETERS(_inputType, _outputType, _result) \ 341 if (input == 0) { \ 342 UTF8_SET_ERROR(INVALID_DATA); \ 343 return _result; \ 344 } \ 345 else if (inputSize < sizeof(_inputType)) { \ 346 if (target != 0) { \ 347 if (targetSize < sizeof(_outputType)) { \ 348 UTF8_SET_ERROR(NOT_ENOUGH_SPACE); \ 349 return _result; \ 350 } \ 351 *target = REPLACEMENT_CHARACTER; \ 352 } \ 353 UTF8_SET_ERROR(INVALID_DATA); \ 354 return _result + sizeof(_outputType); \ 355 } \ 356 if (target != 0 && targetSize < sizeof(_outputType)) { \ 357 UTF8_SET_ERROR(NOT_ENOUGH_SPACE); \ 358 return _result; \ 359 } \ 360 if ((char*)input == (char*)target) { \ 361 UTF8_SET_ERROR(OVERLAPPING_PARAMETERS); \ 362 return _result; \ 363 } \ 364 { \ 365 char* input_center = (char*)input + (inputSize / 2); \ 366 char* target_center = (char*)target + (targetSize / 2); \ 367 size_t delta = (size_t)((input_center > target_center) ? (input_center - target_center) : (target_center - input_center)); \ 368 if (delta < (inputSize + targetSize) / 2) { \ 369 UTF8_SET_ERROR(OVERLAPPING_PARAMETERS); \ 370 return _result; \ 371 } \ 372 } 373 374 375 376 #endif /* _UTF8REWIND_INTERNAL_BASE_H_ */ 377 378 #ifndef _UTF8REWIND_INTERNAL_CASEMAPPING_H_ 379 #define _UTF8REWIND_INTERNAL_CASEMAPPING_H_ 380 381 382 383 384 typedef struct { 385 const char* src; 386 char* dst; 387 size_t src_size; 388 size_t dst_size; 389 size_t total_bytes_needed; 390 unicode_t last_code_point; 391 size_t locale; 392 const uint32_t* property_index1; 393 const uint32_t* property_index2; 394 const uint32_t* property_data; 395 uint32_t last_general_category; 396 uint8_t last_code_point_size; 397 uint8_t last_canonical_combining_class; 398 uint8_t quickcheck_flags; 399 } CaseMappingState; 400 401 uint8_t casemapping_initialize( 402 CaseMappingState* state, 403 const char* input, size_t inputSize, 404 char* target, size_t targetSize, 405 const uint32_t* propertyIndex1, const uint32_t* propertyIndex2, const uint32_t* propertyData, 406 uint8_t quickCheck, size_t locale, 407 int32_t* errors); 408 409 size_t casemapping_execute(CaseMappingState* state, int32_t* errors); 410 411 412 413 #endif /* _UTF8REWIND_INTERNAL_CASEMAPPING_H_ */ 414 #ifndef _UTF8REWIND_INTERNAL_CODEPOINT_H_ 415 #define _UTF8REWIND_INTERNAL_CODEPOINT_H_ 416 417 418 419 420 421 422 423 #define MAX_BASIC_LATIN 0x007F 424 425 426 #define MAX_LATIN_1 0x00FF 427 428 429 #define MAX_BASIC_MULTILINGUAL_PLANE 0xFFFF 430 431 432 #define MAX_LEGAL_UNICODE 0x10FFFF 433 434 435 #define REPLACEMENT_CHARACTER 0xFFFD 436 437 438 #define REPLACEMENT_CHARACTER_STRING "\xEF\xBF\xBD" 439 440 441 #define REPLACEMENT_CHARACTER_STRING_LENGTH 3 442 443 444 #define SURROGATE_HIGH_START 0xD800 445 446 447 #define SURROGATE_HIGH_END 0xDBFF 448 449 450 #define SURROGATE_LOW_START 0xDC00 451 452 453 #define SURROGATE_LOW_END 0xDFFF 454 455 456 #define HANGUL_JAMO_FIRST 0x1100 457 458 459 #define HANGUL_JAMO_LAST 0x11FF 460 461 462 #define HANGUL_L_FIRST 0x1100 463 464 465 #define HANGUL_L_LAST 0x1112 466 467 468 #define HANGUL_L_COUNT 19 469 470 471 #define HANGUL_V_FIRST 0x1161 472 473 474 #define HANGUL_V_LAST 0x1175 475 476 477 #define HANGUL_V_COUNT 21 478 479 480 #define HANGUL_T_FIRST 0x11A7 481 482 483 #define HANGUL_T_LAST 0x11C2 484 485 486 #define HANGUL_T_COUNT 28 487 488 489 #define HANGUL_N_COUNT 588 /* VCount * TCount */ 490 491 492 #define HANGUL_S_FIRST 0xAC00 493 494 495 #define HANGUL_S_LAST 0xD7A3 496 497 498 #define HANGUL_S_COUNT 11172 /* LCount * NCount */ 499 500 #define CP_LATIN_CAPITAL_LETTER_I 0x0049 501 #define CP_LATIN_CAPITAL_LETTER_J 0x004A 502 #define CP_LATIN_SMALL_LETTER_I 0x0069 503 #define CP_LATIN_SMALL_LETTER_J 0x006A 504 #define CP_LATIN_CAPITAL_LETTER_I_WITH_GRAVE 0x00CC 505 #define CP_LATIN_CAPITAL_LETTER_I_WITH_ACUTE 0x00CD 506 #define CP_LATIN_CAPITAL_LETTER_I_WITH_TILDE 0x0128 507 #define CP_LATIN_CAPITAL_LETTER_I_WITH_OGONEK 0x012E 508 #define CP_LATIN_SMALL_LETTER_I_WITH_OGONEK 0x012F 509 #define CP_LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE 0x0130 510 #define CP_LATIN_SMALL_LETTER_DOTLESS_I 0x0131 511 #define CP_COMBINING_GRAVE_ACCENT 0x0300 512 #define CP_COMBINING_ACUTE_ACCENT 0x0301 513 #define CP_COMBINING_TILDE_ACCENT 0x0303 514 #define CP_COMBINING_DOT_ABOVE 0x0307 515 #define CP_COMBINING_GREEK_YPOGEGRAMMENI 0x0345 516 #define CP_COMBINING_GRAPHEME_JOINER 0x034F 517 #define CP_GREEK_CAPITAL_LETTER_SIGMA 0x03A3 518 519 #define CCC_NOT_REORDERED 0 520 #define CCC_OVERLAY 1 521 #define CCC_NUKTA 7 522 #define CCC_KANA_VOICING 8 523 #define CCC_VIRAMA 9 524 #define CCC_FIXED_POSITION_START 10 525 #define CCC_FIXED_POSITION_END 199 526 #define CCC_ATTACHED_BELOW_LEFT 200 527 #define CCC_ATTACHED_BELOW 202 528 #define CCC_ATTACHED_BOTTOM_RIGHT 204 529 #define CCC_ATTACHED_LEFT 208 530 #define CCC_ATTACHED_RIGHT 210 531 #define CCC_ATTACHED_TOP_LEFT 212 532 #define CCC_ATTACHED_ABOVE 214 533 #define CCC_ATTACHED_ABOVE_RIGHT 216 534 #define CCC_BELOW_LEFT 218 535 #define CCC_BELOW 220 536 #define CCC_BELOW_RIGHT 222 537 #define CCC_LEFT 224 538 #define CCC_RIGHT 226 539 #define CCC_ABOVE_LEFT 228 540 #define CCC_ABOVE 230 541 #define CCC_ABOVE_RIGHT 232 542 #define CCC_DOUBLE_BELOW 233 543 #define CCC_DOUBLE_ABOVE 234 544 #define CCC_IOTA_SUBSCRIPT 240 545 #define CCC_INVALID 255 546 547 548 549 550 551 #endif /* _UTF8REWIND_INTERNAL_CODEPOINT_H_ */ 552 553 #ifndef _UTF8REWIND_INTERNAL_DATABASE_H_ 554 #define _UTF8REWIND_INTERNAL_DATABASE_H_ 555 556 557 558 559 typedef enum QuickCheckCaseMapped 560 { 561 QuickCheckCaseMapped_Uppercase = 0x01, 562 QuickCheckCaseMapped_Lowercase = 0x02, 563 QuickCheckCaseMapped_Titlecase = 0x04, 564 QuickCheckCaseMapped_Casefolded = 0x08, 565 } QuickCheckCaseMapped; 566 567 typedef enum QuickCheckResult 568 { 569 QuickCheckResult_Yes, 570 QuickCheckResult_Maybe, 571 QuickCheckResult_No, 572 } QuickCheckResult; 573 574 #define PROPERTY_INDEX_SHIFT (5) 575 576 static const unicode_t PROPERTY_DATA_MASK = (1 << PROPERTY_INDEX_SHIFT) - 1; 577 578 #define PROPERTY_GET(_indexArray, _dataArray, _cp) \ 579 (_dataArray)[ \ 580 (_indexArray)[(_cp) >> PROPERTY_INDEX_SHIFT] + \ 581 ((_cp) & PROPERTY_DATA_MASK)] 582 583 #define PROPERTY_GET_GC(_cp) \ 584 PROPERTY_GET(GeneralCategoryIndexPtr, GeneralCategoryDataPtr, _cp) 585 586 #define PROPERTY_GET_CCC(_cp) \ 587 PROPERTY_GET(CanonicalCombiningClassIndexPtr, CanonicalCombiningClassDataPtr, _cp) 588 589 #define PROPERTY_GET_CM(_cp) \ 590 PROPERTY_GET(QuickCheckCaseMappedIndexPtr, QuickCheckCaseMappedDataPtr, _cp) 591 592 #define PROPERTY_GET_NFC(_cp) \ 593 PROPERTY_GET(QuickCheckNFCIndexPtr, QuickCheckNFCDataPtr, _cp) 594 595 #define PROPERTY_GET_NFD(_cp) \ 596 PROPERTY_GET(QuickCheckNFDIndexPtr, QuickCheckNFDDataPtr, _cp) 597 598 #define PROPERTY_GET_NFKC(_cp) \ 599 PROPERTY_GET(QuickCheckNFKCIndexPtr, QuickCheckNFKCDataPtr, _cp) 600 601 #define PROPERTY_GET_NFKD(_cp) \ 602 PROPERTY_GET(QuickCheckNFKDIndexPtr, QuickCheckNFKDDataPtr, _cp) 603 604 605 606 #endif /* _UTF8REWIND_INTERNAL_DATABASE_H_ */ 607 608 609 #ifndef _UTF8REWIND_INTERNAL_STREAMING_H_ 610 #define _UTF8REWIND_INTERNAL_STREAMING_H_ 611 612 613 614 615 /* 616 UAX15-D4. Stream-Safe Text Process 617 618 This is the process of producing a Unicode string in Stream-Safe Text Format by processing that string 619 from start to finish, inserting U+034F COMBINING GRAPHEME JOINER (CGJ) within long sequences of 620 non-starters. The exact position of the inserted CGJs are determined according to the following algorithm, 621 which describes the generation of an output string from an input string: 622 623 * If the input string is empty, return an empty output string. 624 * Set nonStarterCount to zero. 625 * For each code point C in the input string: 626 * Produce the NFKD decomposition S. 627 * If nonStarterCount plus the number of initial non-starters in S is greater than 30, append a CGJ to 628 the output string and set the nonStarterCount to zero. 629 * Append C to the output string. 630 * If there are no starters in S, increment nonStarterCount by the number of code points in S; otherwise, 631 set nonStarterCount to the number of trailing non-starters in S (which may be zero). 632 * Return the output string. 633 */ 634 635 #define STREAM_SAFE_MAX 30 636 #define STREAM_BUFFER_MAX 32 637 638 typedef struct { 639 const char* src; 640 size_t src_size; 641 uint8_t index; 642 uint8_t current; 643 uint8_t filled; 644 uint8_t stable; 645 uint8_t last_length; 646 unicode_t codepoint[STREAM_BUFFER_MAX]; 647 uint8_t quick_check[STREAM_BUFFER_MAX]; 648 uint8_t canonical_combining_class[STREAM_BUFFER_MAX]; 649 } StreamState; 650 651 652 653 654 #endif /* _UTF8REWIND_INTERNAL_STREAMING_H_ */ 655 656 #ifndef _UTF8REWIND_INTERNAL_COMPOSITION_H_ 657 #define _UTF8REWIND_INTERNAL_COMPOSITION_H_ 658 659 660 661 662 typedef struct { 663 StreamState* input; 664 StreamState* output; 665 const size_t* qc_index; 666 const uint8_t* qc_data; 667 } ComposeState; 668 669 670 671 #endif /* _UTF8REWIND_INTERNAL_COMPOSITION_H_ */ 672 673 #ifndef _UTF8REWIND_INTERNAL_DECOMPOSITION_H_ 674 #define _UTF8REWIND_INTERNAL_DECOMPOSITION_H_ 675 676 677 678 679 typedef struct { 680 StreamState* input; 681 StreamState* output; 682 const size_t* qc_index; 683 const uint8_t* qc_data; 684 const uint32_t* property_index1; 685 const uint32_t* property_index2; 686 const uint32_t* property_data; 687 unicode_t cache_codepoint[STREAM_BUFFER_MAX]; 688 uint8_t cache_canonical_combining_class[STREAM_BUFFER_MAX]; 689 uint8_t cache_current; 690 uint8_t cache_filled; 691 } DecomposeState; 692 693 694 695 #endif /* _UTF8REWIND_INTERNAL_DECOMPOSITION_H_ */ 696 697 #ifndef _UTF8REWIND_UNICODEDATABASE_H_ 698 #define _UTF8REWIND_UNICODEDATABASE_H_ 699 700 701 702 703 typedef struct { 704 unicode_t codepoint; 705 uint32_t length_and_offset; 706 } DecompositionRecord; 707 708 typedef struct { 709 uint64_t key; 710 unicode_t value; 711 } CompositionRecord; 712 713 714 715 #endif /* _UTF8REWIND_UNICODEDATABASE_H_ */ 716 717 718 #endif /*U8_H*/ 719