Differences From Artifact [3ce37a1895]:
- File
src/OFString_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: 31231) [annotate] [blame] [check-ins using]
To Artifact [3a479b89af]:
- File
src/OFString_UTF8.m
— part of check-in
[3d16a30f41]
at
2013-06-22 12:12:36
on branch trunk
— Rework exceptions.
This mostly removes the argument for the class in which the exception
occurred. As backtraces were recently added for all platforms, the
passed class does not give any extra information on where the exception
occurred anymore.This also removes a few other arguments which were not too helpful. In
the past, the idea was to pass as many arguments as possible so that it
is easier to find the origin of the exception. However, as backtraces
are a much better way to find the origin, those are not useful anymore
and just make the exception more cumbersome to use. The rule is now to
only pass arguments that might help in recovering from the exception or
provide information that is otherwise not easily accessible. (user: js, size: 30279) [annotate] [blame] [check-ins using]
︙ | ︙ | |||
187 188 189 190 191 192 193 | switch (of_string_utf8_check(UTF8String, UTF8StringLength, &_s->length)) { case 1: _s->isUTF8 = true; break; case -1: | | < | 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 | switch (of_string_utf8_check(UTF8String, UTF8StringLength, &_s->length)) { case 1: _s->isUTF8 = true; break; case -1: @throw [OFInvalidEncodingException exception]; } memcpy(_s->cString, UTF8String, UTF8StringLength); _s->cString[UTF8StringLength] = 0; } @catch (id e) { [self release]; @throw e; |
︙ | ︙ | |||
229 230 231 232 233 234 235 | if (encoding == OF_STRING_ENCODING_UTF_8 || encoding == OF_STRING_ENCODING_ASCII) { switch (of_string_utf8_check(cString, cStringLength, &_s->length)) { case 1: if (encoding == OF_STRING_ENCODING_ASCII) @throw [OFInvalidEncodingException | | | < | 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | if (encoding == OF_STRING_ENCODING_UTF_8 || encoding == OF_STRING_ENCODING_ASCII) { switch (of_string_utf8_check(cString, cStringLength, &_s->length)) { case 1: if (encoding == OF_STRING_ENCODING_ASCII) @throw [OFInvalidEncodingException exception]; _s->isUTF8 = true; break; case -1: @throw [OFInvalidEncodingException exception]; } memcpy(_s->cString, cString, cStringLength); _s->cString[cStringLength] = 0; return self; } |
︙ | ︙ | |||
263 264 265 266 267 268 269 | _s->isUTF8 = true; bytes = of_string_utf8_encode( (uint8_t)cString[i], buffer); if (bytes == 0) @throw [OFInvalidEncodingException | | | 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 | _s->isUTF8 = true; bytes = of_string_utf8_encode( (uint8_t)cString[i], buffer); if (bytes == 0) @throw [OFInvalidEncodingException exception]; _s->cStringLength += bytes - 1; _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + 1]; memcpy(_s->cString + j, buffer, bytes); |
︙ | ︙ | |||
287 288 289 290 291 292 293 | case OF_STRING_ENCODING_ISO_8859_15: table = of_iso_8859_15; break; case OF_STRING_ENCODING_WINDOWS_1252: table = of_windows_1252; break; default: | | < | < | < | 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 | case OF_STRING_ENCODING_ISO_8859_15: table = of_iso_8859_15; break; case OF_STRING_ENCODING_WINDOWS_1252: table = of_windows_1252; break; default: @throw [OFInvalidEncodingException exception]; } for (i = j = 0; i < cStringLength; i++) { char buffer[4]; of_unichar_t character; size_t characterBytes; if (!(cString[i] & 0x80)) { _s->cString[j++] = cString[i]; continue; } character = table[(uint8_t)cString[i]]; if (character == 0xFFFD) @throw [OFInvalidEncodingException exception]; _s->isUTF8 = true; characterBytes = of_string_utf8_encode(character, buffer); if (characterBytes == 0) @throw [OFInvalidEncodingException exception]; _s->cStringLength += characterBytes - 1; _s->cString = [self resizeMemory: _s->cString size: _s->cStringLength + 1]; memcpy(_s->cString + j, buffer, characterBytes); |
︙ | ︙ | |||
361 362 363 364 365 366 367 | switch (of_string_utf8_check(UTF8String, UTF8StringLength, &_s->length)) { case 1: _s->isUTF8 = true; break; case -1: | | < | 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 | switch (of_string_utf8_check(UTF8String, UTF8StringLength, &_s->length)) { case 1: _s->isUTF8 = true; break; case -1: @throw [OFInvalidEncodingException exception]; } } @catch (id e) { [self release]; @throw e; } return self; |
︙ | ︙ | |||
431 432 433 434 435 436 437 | _s->isUTF8 = true; memcpy(_s->cString + j, buffer, len); j += len; break; default: | | < | 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 | _s->isUTF8 = true; memcpy(_s->cString + j, buffer, len); j += len; break; default: @throw [OFInvalidEncodingException exception]; } } _s->cString[j] = '\0'; _s->cStringLength = j; @try { |
︙ | ︙ | |||
486 487 488 489 490 491 492 | char buffer[4]; of_unichar_t character = (swap ? OF_BSWAP16(string[i]) : string[i]); size_t len; /* Missing high surrogate */ if ((character & 0xFC00) == 0xDC00) | | < | | | 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 | char buffer[4]; of_unichar_t character = (swap ? OF_BSWAP16(string[i]) : string[i]); size_t len; /* Missing high surrogate */ if ((character & 0xFC00) == 0xDC00) @throw [OFInvalidEncodingException exception]; if ((character & 0xFC00) == 0xD800) { of_char16_t nextCharacter; if (length <= i + 1) @throw [OFInvalidEncodingException exception]; nextCharacter = (swap ? OF_BSWAP16(string[i + 1]) : string[i + 1]); if ((nextCharacter & 0xFC00) != 0xDC00) @throw [OFInvalidEncodingException exception]; character = (((character & 0x3FF) << 10) | (nextCharacter & 0x3FF)) + 0x10000; i++; _s->length--; } |
︙ | ︙ | |||
527 528 529 530 531 532 533 | _s->isUTF8 = true; memcpy(_s->cString + j, buffer, len); j += len; break; default: | | < | 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | _s->isUTF8 = true; memcpy(_s->cString + j, buffer, len); j += len; break; default: @throw [OFInvalidEncodingException exception]; } } _s->cString[j] = '\0'; _s->cStringLength = j; @try { |
︙ | ︙ | |||
594 595 596 597 598 599 600 | _s->isUTF8 = true; memcpy(_s->cString + j, buffer, len); j += len; break; default: | | < | 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 | _s->isUTF8 = true; memcpy(_s->cString + j, buffer, len); j += len; break; default: @throw [OFInvalidEncodingException exception]; } } _s->cString[j] = '\0'; _s->cStringLength = j; @try { |
︙ | ︙ | |||
626 627 628 629 630 631 632 | self = [super init]; @try { char *tmp; int cStringLength; if (format == nil) | | < < | < | < | 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 | self = [super init]; @try { char *tmp; int cStringLength; if (format == nil) @throw [OFInvalidArgumentException exception]; _s = &_storage; if ((cStringLength = of_vasprintf(&tmp, [format UTF8String], arguments)) == -1) @throw [OFInvalidFormatException exception]; _s->cStringLength = cStringLength; @try { switch (of_string_utf8_check(tmp, cStringLength, &_s->length)) { case 1: _s->isUTF8 = true; break; case -1: @throw [OFInvalidEncodingException exception]; } _s->cString = [self allocMemoryWithSize: cStringLength + 1]; memcpy(_s->cString, tmp, cStringLength + 1); } @finally { free(tmp); |
︙ | ︙ | |||
743 744 745 746 747 748 749 | - (size_t)getCString: (char*)cString maxLength: (size_t)maxLength encoding: (of_string_encoding_t)encoding { switch (encoding) { case OF_STRING_ENCODING_ASCII: if (_s->isUTF8) | | < | < | < | 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 | - (size_t)getCString: (char*)cString maxLength: (size_t)maxLength encoding: (of_string_encoding_t)encoding { switch (encoding) { case OF_STRING_ENCODING_ASCII: if (_s->isUTF8) @throw [OFInvalidEncodingException exception]; /* intentional fall-through */ case OF_STRING_ENCODING_UTF_8: if (_s->cStringLength + 1 > maxLength) @throw [OFOutOfRangeException exception]; memcpy(cString, _s->cString, _s->cStringLength + 1); return _s->cStringLength; default: return [super getCString: cString maxLength: maxLength encoding: encoding]; } } - (const char*)cStringWithEncoding: (of_string_encoding_t)encoding { switch (encoding) { case OF_STRING_ENCODING_ASCII: if (_s->isUTF8) @throw [OFInvalidEncodingException exception]; /* intentional fall-through */ case OF_STRING_ENCODING_UTF_8: return _s->cString; default: return [super cStringWithEncoding: encoding]; } } |
︙ | ︙ | |||
840 841 842 843 844 845 846 | size_t otherCStringLength, minimumCStringLength; int compare; if (object == self) return OF_ORDERED_SAME; if (![object isKindOfClass: [OFString class]]) | | < < | 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 | size_t otherCStringLength, minimumCStringLength; int compare; if (object == self) return OF_ORDERED_SAME; if (![object isKindOfClass: [OFString class]]) @throw [OFInvalidArgumentException exception]; otherString = (OFString*)object; otherCStringLength = [otherString UTF8StringLength]; minimumCStringLength = (_s->cStringLength > otherCStringLength ? otherCStringLength : _s->cStringLength); if ((compare = memcmp(_s->cString, [otherString UTF8String], |
︙ | ︙ | |||
874 875 876 877 878 879 880 | size_t i, j, otherCStringLength, minimumCStringLength; int compare; if (otherString == self) return OF_ORDERED_SAME; if (![otherString isKindOfClass: [OFString class]]) | | < < | 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 | size_t i, j, otherCStringLength, minimumCStringLength; int compare; if (otherString == self) return OF_ORDERED_SAME; if (![otherString isKindOfClass: [OFString class]]) @throw [OFInvalidArgumentException exception]; otherCString = [otherString UTF8String]; otherCStringLength = [otherString UTF8StringLength]; if (!_s->isUTF8) { minimumCStringLength = (_s->cStringLength > otherCStringLength ? otherCStringLength : _s->cStringLength); |
︙ | ︙ | |||
912 913 914 915 916 917 918 | l1 = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c1); l2 = of_string_utf8_decode(otherCString + j, otherCStringLength - j, &c2); if (l1 == 0 || l2 == 0 || c1 > 0x10FFFF || c2 > 0x10FFFF) | | < | 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 | l1 = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c1); l2 = of_string_utf8_decode(otherCString + j, otherCStringLength - j, &c2); if (l1 == 0 || l2 == 0 || c1 > 0x10FFFF || c2 > 0x10FFFF) @throw [OFInvalidEncodingException exception]; if (c1 >> 8 < OF_UNICODE_CASEFOLDING_TABLE_SIZE) { of_unichar_t tc = of_unicode_casefolding_table[c1 >> 8][c1 & 0xFF]; if (tc) c1 = tc; |
︙ | ︙ | |||
964 965 966 967 968 969 970 | for (i = 0; i < _s->cStringLength; i++) { of_unichar_t c; size_t length; if ((length = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c)) == 0) | | < | 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 | for (i = 0; i < _s->cStringLength; i++) { of_unichar_t c; size_t length; if ((length = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c)) == 0) @throw [OFInvalidEncodingException exception]; OF_HASH_ADD(hash, (c & 0xFF0000) >> 16); OF_HASH_ADD(hash, (c & 0x00FF00) >> 8); OF_HASH_ADD(hash, c & 0x0000FF); i += length - 1; } |
︙ | ︙ | |||
987 988 989 990 991 992 993 | } - (of_unichar_t)characterAtIndex: (size_t)index { of_unichar_t character; if (index >= _s->length) | | | < | | | 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 | } - (of_unichar_t)characterAtIndex: (size_t)index { of_unichar_t character; if (index >= _s->length) @throw [OFOutOfRangeException exception]; if (!_s->isUTF8) return _s->cString[index]; index = of_string_utf8_get_position(_s->cString, index, _s->cStringLength); if (!of_string_utf8_decode(_s->cString + index, _s->cStringLength - index, &character)) @throw [OFInvalidEncodingException exception]; return character; } - (void)getCharacters: (of_unichar_t*)buffer inRange: (of_range_t)range { /* TODO: Could be slightly optimized */ void *pool = objc_autoreleasePoolPush(); const of_unichar_t *characters = [self characters]; if (range.length > SIZE_MAX - range.location || range.location + range.length > _s->length) @throw [OFOutOfRangeException exception]; memcpy(buffer, characters + range.location, range.length * sizeof(of_unichar_t)); objc_autoreleasePoolPop(pool); } - (of_range_t)rangeOfString: (OFString*)string options: (int)options range: (of_range_t)range { const char *cString = [string UTF8String]; size_t i, cStringLength = [string UTF8StringLength]; size_t rangeLocation, rangeLength; if (range.length > SIZE_MAX - range.location || range.location + range.length > _s->length) @throw [OFOutOfRangeException exception]; if (_s->isUTF8) { rangeLocation = of_string_utf8_get_position( _s->cString, range.location, _s->cStringLength); rangeLength = of_string_utf8_get_position( _s->cString + rangeLocation, range.length, _s->cStringLength - rangeLocation); |
︙ | ︙ | |||
1104 1105 1106 1107 1108 1109 1110 | - (OFString*)substringWithRange: (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) | | | 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 | - (OFString*)substringWithRange: (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 exception]; 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); } |
︙ | ︙ | |||
1322 1323 1324 1325 1326 1327 1328 | of_unichar_t c; size_t cLen; cLen = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c); if (cLen == 0 || c > 0x10FFFF) | | < | 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 | of_unichar_t c; size_t cLen; cLen = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c); if (cLen == 0 || c > 0x10FFFF) @throw [OFInvalidEncodingException exception]; ret[j++] = c; i += cLen; } return ret; } |
︙ | ︙ | |||
1351 1352 1353 1354 1355 1356 1357 | of_unichar_t c; size_t cLen; cLen = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c); if (cLen == 0 || c > 0x10FFFF) | | < | 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 | of_unichar_t c; size_t cLen; cLen = of_string_utf8_decode(_s->cString + i, _s->cStringLength - i, &c); if (cLen == 0 || c > 0x10FFFF) @throw [OFInvalidEncodingException exception]; if (byteOrder != OF_BYTE_ORDER_NATIVE) ret[j++] = OF_BSWAP32(c); else ret[j++] = c; i += cLen; |
︙ | ︙ |