Index: src/OFString.h ================================================================== --- src/OFString.h +++ src/OFString.h @@ -15,11 +15,12 @@ #import "OFObject.h" #import "OFArray.h" enum of_string_encoding { OF_STRING_ENCODING_UTF_8, - OF_STRING_ENCODING_ISO_8859_1 + OF_STRING_ENCODING_ISO_8859_1, + OF_STRING_ENCODING_ISO_8859_15, }; extern int of_string_check_utf8(const char*, size_t); extern size_t of_string_unicode_to_utf8(uint32_t, char*); Index: src/OFString.m ================================================================== --- src/OFString.m +++ src/OFString.m @@ -26,10 +26,12 @@ #import "OFAutoreleasePool.h" #import "OFExceptions.h" #import "OFMacros.h" #import "asprintf.h" + +#import "encodings/iso_8859_15.h" /* References for static linking */ void _references_to_categories_of_OFString() { _OFHashing_reference = 1; @@ -247,42 +249,72 @@ switch (of_string_check_utf8(str, length)) { case 1: is_utf8 = YES; break; case -1: + /* + * We can't use [super dealloc] on OS X here. + * Compiler bug? Anyway, [self dealloc] will do here as + * we don't reimplement dealloc. + */ c = isa; - [super dealloc]; + [self dealloc]; @throw [OFInvalidEncodingException newWithClass: c]; } memcpy(string, str, length); string[length] = 0; break; case OF_STRING_ENCODING_ISO_8859_1: - for (i = j = 0; i < length; i++) { + case OF_STRING_ENCODING_ISO_8859_15: + for (i = j = 0; i < len; i++) { if ((uint8_t)str[i] < 0x80) string[j++] = str[i]; else { - /* - * ISO 8859-1 can only have 2 bytes when encoded - * as UTF-8, nevertheless, let's be on the safe - * side. - */ char buf[4]; + uint32_t chr; + size_t chr_bytes; + + switch (encoding) { + case OF_STRING_ENCODING_ISO_8859_1: + chr = (uint8_t)str[i]; + break; + case OF_STRING_ENCODING_ISO_8859_15: + chr = iso_8859_15_to_unicode[ + (uint8_t)str[i]]; + break; + default: + /* + * We can't use [super dealloc] on OS X + * here. Compiler bug? Anyway, + * [self dealloc] will do here as we + * don't reimplement dealloc. + */ + c = isa; + [self dealloc]; + @throw [OFInvalidEncodingException + newWithClass: c]; + } is_utf8 = YES; + chr_bytes = of_string_unicode_to_utf8(chr, buf); - if (of_string_unicode_to_utf8( - (uint8_t)str[i], buf) == 0) { + if (chr_bytes == 0) { + /* + * We can't use [super dealloc] on OS X + * here. Compiler bug? Anyway, + * [self dealloc] will do here as we + * don't reimplement dealloc. + */ c = isa; - [super dealloc]; + [self dealloc]; @throw [OFInvalidEncodingException newWithClass: c]; } - length++; + length += chr_bytes - 1; @try { string = [self resizeMemory: string toSize: length + 1]; } @catch (OFException *e) { @@ -294,21 +326,26 @@ */ [self dealloc]; @throw e; } - string[j++] = buf[0]; - string[j++] = buf[1]; + memcpy(string + j, buf, chr_bytes); + j += chr_bytes; } } string[length] = 0; break; default: + /* + * We can't use [super dealloc] on OS X here. + * Compiler bug? Anyway, [self dealloc] will do here as we + * don't reimplement dealloc. + */ c = isa; - [super dealloc]; + [self dealloc]; @throw [OFInvalidEncodingException newWithClass: c]; } return self; } ADDED src/encodings/iso_8859_15.h Index: src/encodings/iso_8859_15.h ================================================================== --- /dev/null +++ src/encodings/iso_8859_15.h @@ -0,0 +1,34 @@ +static uint32_t iso_8859_15_to_unicode[256] = { + 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000A, 0x000B, 0x000C, 0x000D, 0x000E, 0x000F, + 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001A, 0x001B, 0x001C, 0x001D, 0x001E, 0x001F, + 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002A, 0x002B, 0x002C, 0x002D, 0x002E, 0x002F, + 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003A, 0x003B, 0x003C, 0x003D, 0x003E, 0x003F, + 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004A, 0x004B, 0x004C, 0x004D, 0x004E, 0x004F, + 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005A, 0x005B, 0x005C, 0x005D, 0x005E, 0x005F, + 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006A, 0x006B, 0x006C, 0x006D, 0x006E, 0x006F, + 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007A, 0x007B, 0x007C, 0x007D, 0x007E, 0x007F, + 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, + 0x0088, 0x0089, 0x008A, 0x008B, 0x008C, 0x008D, 0x008E, 0x008F, + 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, + 0x0098, 0x0099, 0x009A, 0x009B, 0x009C, 0x009D, 0x009E, 0x009F, + 0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x20AC, 0x00A5, 0x0160, 0x00A7, + 0x0161, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF, + 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x017D, 0x00B5, 0x00B6, 0x00B7, + 0x017E, 0x00B9, 0x00BA, 0x00BB, 0x0152, 0x0153, 0x0178, 0x00BF, + 0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7, + 0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF, + 0x00D0, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7, + 0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF, + 0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7, + 0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF, + 0x00F0, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7, + 0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x00FF +}; Index: tests/OFString/OFString.m ================================================================== --- tests/OFString/OFString.m +++ tests/OFString/OFString.m @@ -22,11 +22,11 @@ #define ZD "%zd" #else #define ZD "%u" #endif -#define NUM_TESTS 69 +#define NUM_TESTS 70 #define SUCCESS \ printf("\r\033[1;%dmTests successful: " ZD "/%d\033[0m", \ (i == NUM_TESTS - 1 ? 32 : 33), i + 1, NUM_TESTS); \ fflush(stdout); #define FAIL \ @@ -117,10 +117,14 @@ /* ISO-8859-1 tests */ CHECK([[OFString stringWithCString: "\xE4\xF6\xFC" encoding: OF_STRING_ENCODING_ISO_8859_1] isEqual: @"äöü"]) + + CHECK([[OFString stringWithCString: "\xA4\xA6\xA8\xB4\xB8\xBC\xBD\xBE" + encoding: OF_STRING_ENCODING_ISO_8859_15] + isEqual: @"€ŠšŽžŒœŸ"]) /* Format tests */ s1 = [OFMutableString stringWithFormat: @"%s: %d", "test", 123]; CHECK([s1 isEqual: @"test: 123"])