Differences From Artifact [8a8377795b]:
- File src/OFMutableString_UTF8.m — part of check-in [e40729d406] at 2013-02-12 18:22:15 on branch trunk — Prefix all ivars with an underscore. (user: js, size: 20136) [annotate] [blame] [check-ins using]
To Artifact [50da202bb8]:
- File
src/OFMutableString_UTF8.m
— part of check-in
[c5ef582958]
at
2013-03-04 17:20:15
on branch trunk
— Replace BOOL with bool.
The only places where BOOL is left are those where they are required by
the ABI. (user: js, size: 20207) [annotate] [blame] [check-ins using]
︙ | ︙ | |||
41 42 43 44 45 46 47 | + (void)initialize { if (self == [OFMutableString_UTF8 class]) [self inheritMethodsFromClass: [OFString_UTF8 class]]; } - initWithUTF8StringNoCopy: (char*)UTF8String | | | | | | | 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | + (void)initialize { if (self == [OFMutableString_UTF8 class]) [self inheritMethodsFromClass: [OFString_UTF8 class]]; } - initWithUTF8StringNoCopy: (char*)UTF8String freeWhenDone: (bool)freeWhenDone { @try { self = [self initWithUTF8String: UTF8String]; } @finally { if (freeWhenDone) free(UTF8String); } return self; } - (void)OF_convertWithWordStartTable: (const of_unichar_t *const[])startTable wordMiddleTable: (const of_unichar_t *const[])middleTable wordStartTableSize: (size_t)startTableSize wordMiddleTableSize: (size_t)middleTableSize { of_unichar_t *unicodeString; size_t unicodeLen, newCStringLength; size_t i, j; char *newCString; bool isStart = true; if (!_s->isUTF8) { uint8_t t; const of_unichar_t *const *table; assert(startTableSize >= 1 && middleTableSize >= 1); _s->hashed = false; for (i = 0; i < _s->cStringLength; i++) { if (isStart) table = startTable; else table = middleTable; switch (_s->cString[i]) { case ' ': case '\t': case '\n': case '\r': isStart = true; break; default: isStart = false; break; } if ((t = table[0][(uint8_t)_s->cString[i]]) != 0) _s->cString[i] = t; } |
︙ | ︙ | |||
132 133 134 135 136 137 138 | } switch (c) { case ' ': case '\t': case '\n': case '\r': | | | | 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | } switch (c) { case ' ': case '\t': case '\n': case '\r': isStart = true; break; default: isStart = false; break; } if (c >> 8 < tableSize) { of_unichar_t tc = table[c >> 8][c & 0xFF]; if (tc) |
︙ | ︙ | |||
191 192 193 194 195 196 197 | } assert(j == newCStringLength); newCString[j] = 0; [self freeMemory: unicodeString]; [self freeMemory: _s->cString]; | | | 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 | } assert(j == newCStringLength); newCString[j] = 0; [self freeMemory: unicodeString]; [self freeMemory: _s->cString]; _s->hashed = false; _s->cString = newCString; _s->cStringLength = newCStringLength; /* * Even though cStringLength can change, length cannot, therefore no * need to change it. */ |
︙ | ︙ | |||
217 218 219 220 221 222 223 | _s->cStringLength); if (index > _s->cStringLength) @throw [OFOutOfRangeException exceptionWithClass: [self class]]; /* Shortcut if old and new character both are ASCII */ if (!(character & 0x80) && !(_s->cString[index] & 0x80)) { | | | | | 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | _s->cStringLength); if (index > _s->cStringLength) @throw [OFOutOfRangeException exceptionWithClass: [self class]]; /* Shortcut if old and new character both are ASCII */ if (!(character & 0x80) && !(_s->cString[index] & 0x80)) { _s->hashed = false; _s->cString[index] = character; return; } if ((lenNew = of_string_utf8_encode(character, buffer)) == 0) @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; if ((lenOld = of_string_utf8_decode(_s->cString + index, _s->cStringLength - index, &c)) == 0) @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; _s->hashed = false; if (lenNew == lenOld) memcpy(_s->cString + index, buffer, lenNew); else if (lenNew > lenOld) { _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength - lenOld + lenNew + 1]; memmove(_s->cString + index + lenNew, _s->cString + index + lenOld, _s->cStringLength - index - lenOld); memcpy(_s->cString + index, buffer, lenNew); _s->cStringLength -= lenOld; _s->cStringLength += lenNew; _s->cString[_s->cStringLength] = '\0'; if (character & 0x80) _s->isUTF8 = true; } else if (lenNew < lenOld) { memmove(_s->cString + index + lenNew, _s->cString + index + lenOld, _s->cStringLength - index - lenOld); memcpy(_s->cString + index, buffer, lenNew); _s->cStringLength -= lenOld; |
︙ | ︙ | |||
284 285 286 287 288 289 290 | if (UTF8StringLength >= 3 && !memcmp(UTF8String, "\xEF\xBB\xBF", 3)) { UTF8String += 3; UTF8StringLength -= 3; } switch (of_string_utf8_check(UTF8String, UTF8StringLength, &length)) { case 1: | | | | 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 | if (UTF8StringLength >= 3 && !memcmp(UTF8String, "\xEF\xBB\xBF", 3)) { UTF8String += 3; UTF8StringLength -= 3; } switch (of_string_utf8_check(UTF8String, UTF8StringLength, &length)) { case 1: _s->isUTF8 = true; break; case -1: @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; } _s->hashed = false; _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + UTF8StringLength + 1]; memcpy(_s->cString + _s->cStringLength, UTF8String, UTF8StringLength + 1); _s->cStringLength += UTF8StringLength; |
︙ | ︙ | |||
314 315 316 317 318 319 320 | if (UTF8StringLength >= 3 && !memcmp(UTF8String, "\xEF\xBB\xBF", 3)) { UTF8String += 3; UTF8StringLength -= 3; } switch (of_string_utf8_check(UTF8String, UTF8StringLength, &length)) { case 1: | | | | 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 | if (UTF8StringLength >= 3 && !memcmp(UTF8String, "\xEF\xBB\xBF", 3)) { UTF8String += 3; UTF8StringLength -= 3; } switch (of_string_utf8_check(UTF8String, UTF8StringLength, &length)) { case 1: _s->isUTF8 = true; break; case -1: @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; } _s->hashed = false; _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + UTF8StringLength + 1]; memcpy(_s->cString + _s->cStringLength, UTF8String, UTF8StringLength); _s->cStringLength += UTF8StringLength; _s->length += length; |
︙ | ︙ | |||
369 370 371 372 373 374 375 | if (string == nil) @throw [OFInvalidArgumentException exceptionWithClass: [self class] selector: _cmd]; UTF8StringLength = [string UTF8StringLength]; | | | | | | | | | | | 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 | if (string == nil) @throw [OFInvalidArgumentException exceptionWithClass: [self class] selector: _cmd]; UTF8StringLength = [string UTF8StringLength]; _s->hashed = false; _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + UTF8StringLength + 1]; memcpy(_s->cString + _s->cStringLength, [string UTF8String], UTF8StringLength); _s->cStringLength += UTF8StringLength; _s->length += [string length]; _s->cString[_s->cStringLength] = 0; if ([string isKindOfClass: [OFString_UTF8 class]] || [string isKindOfClass: [OFMutableString_UTF8 class]]) { if (((OFString_UTF8*)string)->_s->isUTF8) _s->isUTF8 = true; } else _s->isUTF8 = true; } - (void)appendCharacters: (of_unichar_t*)characters length: (size_t)length { char *tmp; tmp = [self allocMemoryWithSize: (length * 4) + 1]; @try { size_t i, j = 0; bool isUTF8 = false; for (i = 0; i < length; i++) { char buffer[4]; switch (of_string_utf8_encode(characters[i], buffer)) { case 1: tmp[j++] = buffer[0]; break; case 2: isUTF8 = true; memcpy(tmp + j, buffer, 2); j += 2; break; case 3: isUTF8 = true; memcpy(tmp + j, buffer, 3); j += 3; break; case 4: isUTF8 = true; memcpy(tmp + j, buffer, 4); j += 4; break; default: @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; } } tmp[j] = '\0'; _s->hashed = false; _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + j + 1]; memcpy(_s->cString + _s->cStringLength, tmp, j + 1); _s->cStringLength += j; _s->length += length; if (isUTF8) _s->isUTF8 = true; } @finally { [self freeMemory: tmp]; } } - (void)appendFormat: (OFConstantString*)format arguments: (va_list)arguments |
︙ | ︙ | |||
478 479 480 481 482 483 484 | } } - (void)reverse { size_t i, j; | | | 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 | } } - (void)reverse { size_t i, j; _s->hashed = false; /* We reverse all bytes and restore UTF-8 later, if necessary */ for (i = 0, j = _s->cStringLength - 1; i < _s->cStringLength / 2; i++, j--) { _s->cString[i] ^= _s->cString[j]; _s->cString[j] ^= _s->cString[i]; _s->cString[i] ^= _s->cString[j]; |
︙ | ︙ | |||
573 574 575 576 577 578 579 | exceptionWithClass: [self class]]; if (_s->isUTF8) index = of_string_utf8_get_position(_s->cString, index, _s->cStringLength); newCStringLength = _s->cStringLength + [string UTF8StringLength]; | | | | | | 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 | exceptionWithClass: [self class]]; if (_s->isUTF8) index = of_string_utf8_get_position(_s->cString, index, _s->cStringLength); newCStringLength = _s->cStringLength + [string UTF8StringLength]; _s->hashed = false; _s->cString = [self resizeMemory: _s->cString size: newCStringLength + 1]; memmove(_s->cString + index + [string UTF8StringLength], _s->cString + index, _s->cStringLength - index); memcpy(_s->cString + index, [string UTF8String], [string UTF8StringLength]); _s->cString[newCStringLength] = '\0'; _s->cStringLength = newCStringLength; _s->length += [string length]; if ([string isKindOfClass: [OFString_UTF8 class]] || [string isKindOfClass: [OFMutableString_UTF8 class]]) { if (((OFString_UTF8*)string)->_s->isUTF8) _s->isUTF8 = true; } else _s->isUTF8 = true; } - (void)deleteCharactersInRange: (of_range_t)range { size_t start = range.location; size_t end = range.location + range.length; if (range.length > SIZE_MAX - range.location || end > _s->length) @throw [OFOutOfRangeException exceptionWithClass: [self class]]; if (_s->isUTF8) { start = of_string_utf8_get_position(_s->cString, start, _s->cStringLength); end = of_string_utf8_get_position(_s->cString, end, _s->cStringLength); } memmove(_s->cString + start, _s->cString + end, _s->cStringLength - end); _s->hashed = false; _s->length -= range.length; _s->cStringLength -= end - start; _s->cString[_s->cStringLength] = 0; @try { _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + 1]; |
︙ | ︙ | |||
645 646 647 648 649 650 651 | _s->cStringLength); end = of_string_utf8_get_position(_s->cString, end, _s->cStringLength); } newCStringLength = _s->cStringLength - (end - start) + [replacement UTF8StringLength]; | | | 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 | _s->cStringLength); end = of_string_utf8_get_position(_s->cString, end, _s->cStringLength); } newCStringLength = _s->cStringLength - (end - start) + [replacement UTF8StringLength]; _s->hashed = false; _s->cString = [self resizeMemory: _s->cString size: newCStringLength + 1]; memmove(_s->cString + start + [replacement UTF8StringLength], _s->cString + end, _s->cStringLength - end); memcpy(_s->cString + start, [replacement UTF8String], [replacement UTF8StringLength]); |
︙ | ︙ | |||
730 731 732 733 734 735 736 | } memcpy(newCString + newCStringLength, _s->cString + last, _s->cStringLength - last); newCStringLength += _s->cStringLength - last; newCString[newCStringLength] = 0; [self freeMemory: _s->cString]; | | | | | 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 | } memcpy(newCString + newCStringLength, _s->cString + last, _s->cStringLength - last); newCStringLength += _s->cStringLength - last; newCString[newCStringLength] = 0; [self freeMemory: _s->cString]; _s->hashed = false; _s->cString = newCString; _s->cStringLength = newCStringLength; _s->length = newLength; } - (void)deleteLeadingWhitespaces { size_t i; for (i = 0; i < _s->cStringLength; i++) if (_s->cString[i] != ' ' && _s->cString[i] != '\t' && _s->cString[i] != '\n' && _s->cString[i] != '\r' && _s->cString[i] != '\f') break; _s->hashed = false; _s->cStringLength -= i; _s->length -= i; memmove(_s->cString, _s->cString + i, _s->cStringLength); _s->cString[_s->cStringLength] = '\0'; @try { _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + 1]; } @catch (OFOutOfMemoryException *e) { /* We don't really care, as we only made it smaller */ } } - (void)deleteTrailingWhitespaces { size_t d; char *p; _s->hashed = false; d = 0; for (p = _s->cString + _s->cStringLength - 1; p >= _s->cString; p--) { if (*p != ' ' && *p != '\t' && *p != '\n' && *p != '\r' && *p != '\f') break; |
︙ | ︙ | |||
794 795 796 797 798 799 800 | } - (void)deleteEnclosingWhitespaces { size_t d, i; char *p; | | | 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 | } - (void)deleteEnclosingWhitespaces { size_t d, i; char *p; _s->hashed = false; d = 0; for (p = _s->cString + _s->cStringLength - 1; p >= _s->cString; p--) { if (*p != ' ' && *p != '\t' && *p != '\n' && *p != '\r' && *p != '\f') break; |
︙ | ︙ |