Overview
Comment: | OFString: Add methods for UTF-32. |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA3-256: |
7cddd5f891be8c029dfd7bc5f3c08b0f |
User & Date: | js on 2013-01-08 12:33:53 |
Other Links: | manifest | tags |
Context
2013-01-09
| ||
22:10 | OFTCPSocket: Set ai_flags. check-in: 541b33d978 user: js tags: trunk | |
2013-01-08
| ||
12:33 | OFString: Add methods for UTF-32. check-in: 7cddd5f891 user: js tags: trunk | |
03:41 | OFProcess: Kill the process in -[close]. check-in: 382e89a033 user: js tags: trunk | |
Changes
Modified src/OFString.h from [31ec44e41b] to [4892881708].
︙ | |||
201 202 203 204 205 206 207 208 209 210 211 212 213 214 | 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 | + + + + + + + + + + + + + + + + + + + | * @param byteOrder The byte order to assume if there is no BOM * @return A new autoreleased OFString */ + (instancetype)stringWithUTF16String: (const uint16_t*)string length: (size_t)length byteOrder: (of_byte_order_t)byteOrder; /*! * @brief Creates a new OFString from a UTF-32 encoded string. * * @param string The UTF-32 string * @return A new autoreleased OFString */ + (instancetype)stringWithUTF32String: (const uint32_t*)string; /*! * @brief Creates a new OFString from a UTF-32 encoded string, assuming the * specified byte order if no BOM is found. * * @param string The UTF-32 string * @param byteOrder The byte order to assume if there is no BOM * @return A new autoreleased OFString */ + (instancetype)stringWithUTF32String: (const uint32_t*)string byteOrder: (of_byte_order_t)byteOrder; /*! * @brief Creates a new OFString from a format string. * * See printf for the format syntax. As an addition, %@ is available as format * specifier for objects. * * @param format A string used as format to initialize the OFString |
︙ | |||
400 401 402 403 404 405 406 407 408 409 410 411 412 413 | 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 | + + + + + + + + + + + + + + + + + + + | * @param byteOrder The byte order to assume if there is no BOM * @return An initialized OFString */ - initWithUTF16String: (const uint16_t*)string length: (size_t)length byteOrder: (of_byte_order_t)byteOrder; /*! * @brief Initializes an already allocated OFString with a UTF-32 string. * * @param string The UTF-32 string * @return An initialized OFString */ - initWithUTF32String: (const uint32_t*)string; /*! * @brief Initializes an already allocated OFString with a UTF-32 string, * assuming the specified byte order if no BOM is found. * * @param string The UTF-32 string * @param byteOrder The byte order to assume if there is no BOM * @return An initialized OFString */ - initWithUTF32String: (const uint32_t*)string byteOrder: (of_byte_order_t)byteOrder; /*! * @brief Initializes an already allocated OFString with a format string. * * See printf for the format syntax. As an addition, %@ is available as format * specifier for objects. * * @param format A string used as format to initialize the OFString |
︙ | |||
900 901 902 903 904 905 906 907 908 909 910 911 912 913 | 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 | + + + + + + + + + + + + + + + + + + + + + + + + | /*! * @brief Returns the length of the string in UTF-16 characters. * * @return The length of string in UTF-16 characters */ - (size_t)UTF16StringLength; /*! * @brief Returns the string in UTF-32 encoding with native byte order. * * The result is valid until the autorelease pool is released. If you want to * use the result outside the scope of the current autorelease pool, you have to * copy it. * * @return The string in UTF-32 encoding with native byte order */ - (const of_unichar_t*)UTF32String OF_RETURNS_INNER_POINTER; /*! * @brief Returns the string in UTF-32 encoding with the specified byte order. * * The result is valid until the autorelease pool is released. If you want to * use the result outside the scope of the current autorelease pool, you have to * copy it. * * @param byteOrder The byte order for the UTF-32 encoding * @return The string in UTF-32 encoding with the specified byte order */ - (const of_unichar_t*)UTF32StringWithByteOrder: (of_byte_order_t)byteOrder OF_RETURNS_INNER_POINTER; /*! * @brief Writes the string into the specified file using UTF-8 encoding. * * @param path The path of the file to write to */ - (void)writeToFile: (OFString*)path; |
︙ | |||
937 938 939 940 941 942 943 944 945 946 | 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 | + | #ifdef __cplusplus extern "C" { #endif extern size_t of_string_utf8_encode(of_unichar_t, char*); extern size_t of_string_utf8_decode(const char*, size_t, of_unichar_t*); extern size_t of_string_utf16_length(const uint16_t*); extern size_t of_string_utf32_length(const uint32_t*); #ifdef __cplusplus } #endif |
Modified src/OFString.m from [6044846057] to [2ad39db524].
︙ | |||
148 149 150 151 152 153 154 155 156 157 158 159 160 161 | 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | + + + + + + + + + + + | size_t length = 0; while (*string++ != 0) length++; return length; } size_t of_string_utf32_length(const uint32_t *string) { size_t length = 0; while (*string++ != 0) length++; return length; } static OFString* standardize_path(OFArray *components, OFString *currentDirectory, OFString *parentDirectory, OFString *joinString) { void *pool = objc_autoreleasePoolPush(); OFMutableArray *array; |
︙ | |||
335 336 337 338 339 340 341 342 343 344 345 346 347 348 | 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 | + + + + + + + + + + + + | length: (size_t)length byteOrder: (of_byte_order_t)byteOrder { return (id)[[OFString_UTF8 alloc] initWithUTF16String: string length: length byteOrder: byteOrder]; } - initWithUTF32String: (const uint32_t*)string { return (id)[[OFString_UTF8 alloc] initWithUTF32String: string]; } - initWithUTF32String: (const uint32_t*)string byteOrder: (of_byte_order_t)byteOrder { return (id)[[OFString_UTF8 alloc] initWithUTF32String: string byteOrder: byteOrder]; } - initWithFormat: (OFConstantString*)format, ... { id ret; va_list arguments; va_start(arguments, format); |
︙ | |||
534 535 536 537 538 539 540 541 542 543 544 545 546 547 | 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 | + + + + + + + + + + + + | length: (size_t)length byteOrder: (of_byte_order_t)byteOrder { return [[[self alloc] initWithUTF16String: string length: length byteOrder: byteOrder] autorelease]; } + (instancetype)stringWithUTF32String: (const uint32_t*)string { return [[[self alloc] initWithUTF32String: string] autorelease]; } + (instancetype)stringWithUTF32String: (const uint32_t*)string byteOrder: (of_byte_order_t)byteOrder { return [[[self alloc] initWithUTF32String: string byteOrder: byteOrder] autorelease]; } + (instancetype)stringWithFormat: (OFConstantString*)format, ... { id ret; va_list arguments; va_start(arguments, format); |
︙ | |||
709 710 711 712 713 714 715 716 717 718 719 720 721 722 | 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 | + + + + + + + + + + + + + + + | [self doesNotRecognizeSelector: _cmd]; abort(); } @catch (id e) { [self release]; @throw e; } } - initWithUTF32String: (const uint32_t*)string { return [self initWithCharacters: string length: of_string_utf32_length(string) byteOrder: OF_BYTE_ORDER_NATIVE]; } - initWithUTF32String: (const uint32_t*)string byteOrder: (of_byte_order_t)byteOrder { return [self initWithCharacters: string length: of_string_utf32_length(string) byteOrder: byteOrder]; } - initWithFormat: (OFConstantString*)format, ... { id ret; va_list arguments; va_start(arguments, format); |
︙ | |||
2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 | 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 | + + + + + + + + + + + + + + + + + + + + + + + + + + + | for (i = 0; i < length; i++) if (characters[i] > 0xFFFF) UTF16StringLength++; return UTF16StringLength; } - (const of_unichar_t*)UTF32String { return [self UTF32StringWithByteOrder: OF_BYTE_ORDER_NATIVE]; } - (const of_unichar_t*)UTF32StringWithByteOrder: (of_byte_order_t)byteOrder { OFObject *object = [[[OFObject alloc] init] autorelease]; size_t length = [self length]; of_unichar_t *ret; ret = [object allocMemoryWithSize: sizeof(of_unichar_t) count: length + 1]; [self getCharacters: ret inRange: of_range(0, length)]; ret[length] = 0; if (byteOrder != OF_BYTE_ORDER_NATIVE) { size_t i; for (i = 0; i < length; i++) ret[i] = OF_BSWAP32(ret[i]); } return ret; } - (void)writeToFile: (OFString*)path { void *pool = objc_autoreleasePoolPush(); OFFile *file; file = [OFFile fileWithPath: path |
︙ |
Modified src/OFString_UTF8.m from [0ddb5e507a] to [c7327619e7].
︙ | |||
527 528 529 530 531 532 533 534 535 536 537 538 539 540 | 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 | + + + + + | if (length <= i + 1) @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; nextCharacter = (swap ? OF_BSWAP16(string[i + 1]) : string[i + 1]); if ((nextCharacter & 0xFC00) != 0xDC00) @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; character = (((character & 0x3FF) << 10) | (nextCharacter & 0x3FF)) + 0x10000; i++; s->cStringLength--; s->length--; } |
︙ | |||
1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 | 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 | + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + | if (cLen == 0 || c > 0x10FFFF) @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; ret[j++] = c; i += cLen; } return ret; } - (const of_unichar_t*)UTF32StringWithByteOrder: (of_byte_order_t)byteOrder { OFObject *object = [[[OFObject alloc] init] autorelease]; of_unichar_t *ret; size_t i, j; ret = [object allocMemoryWithSize: sizeof(of_unichar_t) count: s->length + 1]; i = j = 0; while (i < s->cStringLength) { 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 exceptionWithClass: [self class]]; if (byteOrder != OF_BYTE_ORDER_NATIVE) ret[j++] = OF_BSWAP32(c); else ret[j++] = c; i += cLen; } ret[j] = 0; return ret; } #ifdef OF_HAVE_BLOCKS - (void)enumerateLinesUsingBlock: (of_string_line_enumeration_block_t)block { |
︙ |
Modified tests/OFStringTests.m from [7f9159fd57] to [1701ed672c].
︙ | |||
36 37 38 39 40 41 42 | 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | - + - + | static OFString *module = @"OFString"; static OFString* whitespace[] = { @" \r \t\n\t \tasd \t \t\t\r\n", @" \t\t \t\t \t \t" }; static of_unichar_t ucstr[] = { |
︙ | |||
153 154 155 156 157 158 159 | 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | - - - - - - - - - - + + + + + + | TEST(@"+[stringWithUTF8String:length:]", (s[0] = [OFMutableString stringWithUTF8String: "\xEF\xBB\xBF" "foobar" length: 6]) && [s[0] isEqual: @"foo"]) |
︙ | |||
404 405 406 407 408 409 410 | 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 | - + - + - - + - + + + + + + + + + + + | EXPECT_EXCEPTION(@"Detect out of range in -[hexadecimalValue]", OFOutOfRangeException, [@"0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF" @"0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF" hexadecimalValue]) TEST(@"-[characters]", (ua = [@"fööbär🀺" characters]) && |
︙ |