mirrors/serenity
1
0
Fork 0
mirror of https://github.com/SerenityOS/serenity.git synced 2025-01-23 18:02:05 -05:00
Code Issues Projects Releases Packages Wiki Activity

LibTextCodec: Implement table based decoders as SingleByteDecoder

Browse source 
Instead of copy-pasting the implementation, let's use a single class.
This "Single Byte Decoder" concept even exists in the Encoding Spec :^)
This commit is contained in:
Simon Wanner 2024-05-27 17:57:12 +02:00 • committed by Andreas Kling
parent 3029406c4b
commit 96b3c35358
2 changed files with 95 additions and 132 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

209
Userland/Libraries/LibTextCodec/Decoder.cpp
View file

@ -2,6 +2,7 @@
* Copyright (c) 2020, Andreas Kling <kling@serenityos.org>
* Copyright (c) 2022, Jelle Raaijmakers <jelle@gmta.nl>
* Copyright (c) 2023, Sam Atkins <atkinssj@serenityos.org>
* Copyright (c) 2024, Simon Wanner <simon@skyrising.xyz>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
@ -21,15 +22,69 @@ UTF8Decoder s_utf8_decoder;
UTF16BEDecoder s_utf16be_decoder;
UTF16LEDecoder s_utf16le_decoder;
Latin2Decoder s_latin2_decoder;
CentralEuropeDecoder s_centraleurope_decoder;
HebrewDecoder s_hebrew_decoder;
CyrillicDecoder s_cyrillic_decoder;
Koi8RDecoder s_koi8r_decoder;
Latin9Decoder s_latin9_decoder;
MacRomanDecoder s_mac_roman_decoder;
PDFDocEncodingDecoder s_pdf_doc_encoding_decoder;
TurkishDecoder s_turkish_decoder;
XUserDefinedDecoder s_x_user_defined_decoder;
// clang-format off
// https://encoding.spec.whatwg.org/index-windows-1250.txt
SingleByteDecoder s_centraleurope_decoder {{
0x20AC, 0x0081, 0x201A, 0x0083, 0x201E, 0x2026, 0x2020, 0x2021, 0x0088, 0x2030, 0x0160, 0x2039, 0x015A, 0x0164, 0x017D, 0x0179,
0x0090, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x0098, 0x2122, 0x0161, 0x203A, 0x015B, 0x0165, 0x017E, 0x017A,
0x00A0, 0x02C7, 0x02D8, 0x0141, 0x00A4, 0x0104, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x015E, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x017B,
0x00B0, 0x00B1, 0x02DB, 0x0142, 0x00B4, 0x00B5, 0x00B6, 0x00B7, 0x00B8, 0x0105, 0x015F, 0x00BB, 0x013D, 0x02DD, 0x013E, 0x017C,
0x0154, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0139, 0x0106, 0x00C7, 0x010C, 0x00C9, 0x0118, 0x00CB, 0x011A, 0x00CD, 0x00CE, 0x010E,
0x0110, 0x0143, 0x0147, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x00D7, 0x0158, 0x016E, 0x00DA, 0x0170, 0x00DC, 0x00DD, 0x0162, 0x00DF,
0x0155, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x013A, 0x0107, 0x00E7, 0x010D, 0x00E9, 0x0119, 0x00EB, 0x011B, 0x00ED, 0x00EE, 0x010F,
0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7, 0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD, 0x0163, 0x02D9,
}};
// https://encoding.spec.whatwg.org/index-windows-1251.txt
SingleByteDecoder s_cyrillic_decoder {{
0x0402, 0x0403, 0x201A, 0x0453, 0x201E, 0x2026, 0x2020, 0x2021, 0x20AC, 0x2030, 0x0409, 0x2039, 0x040A, 0x040C, 0x040B, 0x040F,
0x0452, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x0098, 0x2122, 0x0459, 0x203A, 0x045A, 0x045C, 0x045B, 0x045F,
0x00A0, 0x040E, 0x045E, 0x0408, 0x00A4, 0x0490, 0x00A6, 0x00A7, 0x0401, 0x00A9, 0x0404, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x0407,
0x00B0, 0x00B1, 0x0406, 0x0456, 0x0491, 0x00B5, 0x00B6, 0x00B7, 0x0451, 0x2116, 0x0454, 0x00BB, 0x0458, 0x0405, 0x0455, 0x0457,
0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, 0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F,
0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, 0x0428, 0x0429, 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F,
0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, 0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, 0x043F,
0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, 0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D, 0x044E, 0x044F,
}};
// https://encoding.spec.whatwg.org/index-windows-1255.txt
SingleByteDecoder s_hebrew_decoder {{
0x20AC, 0x0081, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6, 0x2030, 0x008A, 0x2039, 0x008C, 0x008D, 0x008E, 0x008F,
0x0090, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0x009A, 0x203A, 0x009C, 0x009D, 0x009E, 0x009F,
0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x20AA, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x00F7, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
0x05B0, 0x05B1, 0x05B2, 0x05B3, 0x05B4, 0x05B5, 0x05B6, 0x05B7, 0x05B8, 0x05B9, 0x05BA, 0x05BB, 0x05BC, 0x05BD, 0x05BE, 0x05BF,
0x05C0, 0x05C1, 0x05C2, 0x05C3, 0x05F0, 0x05F1, 0x05F2, 0x05F3, 0x05F4, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
0x05D0, 0x05D1, 0x05D2, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7, 0x05D8, 0x05D9, 0x05DA, 0x05DB, 0x05DC, 0x05DD, 0x05DE, 0x05DF,
0x05E0, 0x05E1, 0x05E2, 0x05E3, 0x05E4, 0x05E5, 0x05E6, 0x05E7, 0x05E8, 0x05E9, 0x05EA, 0xFFFD, 0xFFFD, 0x200E, 0x200F, 0xFFFD,
}};
// https://encoding.spec.whatwg.org/index-koi8-r.txt
SingleByteDecoder s_koi8r_decoder {{
0x2500, 0x2502, 0x250C, 0x2510, 0x2514, 0x2518, 0x251C, 0x2524, 0x252C, 0x2534, 0x253C, 0x2580, 0x2584, 0x2588, 0x258C, 0x2590,
0x2591, 0x2592, 0x2593, 0x2320, 0x25A0, 0x2219, 0x221A, 0x2248, 0x2264, 0x2265, 0x00A0, 0x2321, 0x00B0, 0x00B2, 0x00B7, 0x00F7,
0x2550, 0x2551, 0x2552, 0xD191, 0x2553, 0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255A, 0x255B, 0x255C, 0x255D, 0x255E,
0x255F, 0x2560, 0x2561, 0xD081, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567, 0x2568, 0x2569, 0x256A, 0x256B, 0x256C, 0x00A9,
0x044E, 0x0430, 0x0431, 0x0446, 0x0434, 0x0435, 0x0444, 0x0433, 0x0445, 0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E,
0x043F, 0x044F, 0x0440, 0x0441, 0x0442, 0x0443, 0x0436, 0x0432, 0x044C, 0x044B, 0x0437, 0x0448, 0x044D, 0x0449, 0x0447, 0x044A,
0x042E, 0x0410, 0x0441, 0x0426, 0x0414, 0x0415, 0x0424, 0x0413, 0x0425, 0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E,
0x041F, 0x042F, 0x0420, 0x0421, 0x0422, 0x0423, 0x0416, 0x0412, 0x042C, 0x042B, 0x0417, 0x0428, 0x042D, 0x0429, 0x0427, 0x042A,
}};
// https://encoding.spec.whatwg.org/index-macintosh.txt
SingleByteDecoder s_mac_roman_decoder {{
0x00C4, 0x00C5, 0x00C7, 0x00C9, 0x00D1, 0x00D6, 0x00DC, 0x00E1, 0x00E0, 0x00E2, 0x00E4, 0x00E3, 0x00E5, 0x00E7, 0x00E9, 0x00E8,
0x00EA, 0x00EB, 0x00ED, 0x00EC, 0x00EE, 0x00EF, 0x00F1, 0x00F3, 0x00F2, 0x00F4, 0x00F6, 0x00F5, 0x00FA, 0x00F9, 0x00FB, 0x00FC,
0x2020, 0x00B0, 0x00A2, 0x00A3, 0x00A7, 0x2022, 0x00B6, 0x00DF, 0x00AE, 0x00A9, 0x2122, 0x00B4, 0x00A8, 0x2260, 0x00C6, 0x00D8,
0x221E, 0x00B1, 0x2264, 0x2265, 0x00A5, 0x00B5, 0x2202, 0x2211, 0x220F, 0x03C0, 0x222B, 0x00AA, 0x00BA, 0x03A9, 0x00E6, 0x00F8,
0x00BF, 0x00A1, 0x00AC, 0x221A, 0x0192, 0x2248, 0x2206, 0x00AB, 0x00BB, 0x2026, 0x00A0, 0x00C0, 0x00C3, 0x00D5, 0x0152, 0x0153,
0x2013, 0x2014, 0x201C, 0x201D, 0x2018, 0x2019, 0x00F7, 0x25CA, 0x00FF, 0x0178, 0x2044, 0x20AC, 0x2039, 0x203A, 0xFB01, 0xFB02,
0x2021, 0x00B7, 0x201A, 0x201E, 0x2030, 0x00C2, 0x00CA, 0x00C1, 0x00CB, 0x00C8, 0x00CD, 0x00CE, 0x00CF, 0x00CC, 0x00D3, 0x00D4,
0xF8FF, 0x00D2, 0x00DA, 0x00DB, 0x00D9, 0x0131, 0x02C6, 0x02DC, 0x00AF, 0x02D8, 0x02D9, 0x02DA, 0x00B8, 0x02DD, 0x02DB, 0x02C7,
}};
// clang-format on
}
Optional<Decoder&> decoder_for(StringView a_encoding)
@ -521,101 +576,6 @@ ErrorOr<void> Latin2Decoder::process(StringView input, Function<ErrorOr<void>(u3
return {};
}
ErrorOr<void> CentralEuropeDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
static constexpr Array<u32, 128> translation_table = {
0x20AC, 0xFFFD, 0x201A, 0xFFFD, 0x201E, 0x2026, 0x2020, 0x2021, 0xFFFD, 0x2030, 0x0160, 0x2039, 0x015A, 0x0164, 0x017D, 0x0179,
0xFFFD, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0xFFFD, 0x2122, 0x0161, 0x203A, 0x015B, 0x0165, 0x017E, 0x017A,
0x00A0, 0x02C7, 0x02D8, 0x0141, 0x00A4, 0x0104, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x015E, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x017B,
0x00B0, 0x00B1, 0x02DB, 0x0142, 0x00B4, 0x00B5, 0x00B6, 0x00B7, 0x00B8, 0x0105, 0x015F, 0x00BB, 0x013D, 0x02DD, 0x013E, 0x017C,
0x0154, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0139, 0x0106, 0x00C7, 0x010C, 0x00C9, 0x0118, 0x00CB, 0x011A, 0x00CD, 0x00CE, 0x010E,
0x0110, 0x0143, 0x0147, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x00D7, 0x0158, 0x016E, 0x00DA, 0x0170, 0x00DC, 0x00DD, 0x0162, 0x00DF,
0x0155, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x013A, 0x0107, 0x00E7, 0x010D, 0x00E9, 0x0119, 0x00EB, 0x011B, 0x00ED, 0x00EE, 0x010F,
0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7, 0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD, 0x0163, 0x02D9
};
for (unsigned char ch : input) {
if (ch < 0x80) { // Superset of ASCII
TRY(on_code_point(ch));
} else {
TRY(on_code_point(translation_table[ch - 0x80]));
}
}
return {};
}
ErrorOr<void> HebrewDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
static constexpr Array<u32, 128> translation_table = {
0x20AC, 0xFFFD, 0x201A, 0x192, 0x201E, 0x2026, 0x2020, 0x2021, 0x2C6, 0x2030, 0xFFFD, 0x2039, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
0xFFFD, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x2DC, 0x2122, 0xFFFD, 0x203A, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
0xA0, 0xA1, 0xA2, 0xA3, 0x20AA, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xD7, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF,
0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xF7, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
0x5B0, 0x5B1, 0x5B2, 0x5B3, 0x5B4, 0x5B5, 0x5B6, 0x5B7, 0x5B8, 0x5B9, 0x5BA, 0x5BB, 0x5BC, 0x5BD, 0x5BE, 0x5BF,
0x5C0, 0x5C1, 0x5C2, 0x5C3, 0x5F0, 0x5F1, 0x5F2, 0x5F3, 0x5F4, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
0x5D0, 0x5D1, 0x5D2, 0x5D3, 0x5D4, 0x5D5, 0x5D6, 0x5D7, 0x5D8, 0x5D9, 0x5DA, 0x5DB, 0x5DC, 0x5DD, 0x5DE, 0x5DF,
0x5E0, 0x5E1, 0x5E2, 0x5E3, 0x5E4, 0x5E5, 0x5E6, 0x5E7, 0x5E8, 0x5E9, 0x5EA, 0xFFFD, 0xFFFD, 0x200E, 0x200F, 0xFFFD
};
for (unsigned char ch : input) {
if (ch < 0x80) { // Superset of ASCII
TRY(on_code_point(ch));
} else {
TRY(on_code_point(translation_table[ch - 0x80]));
}
}
return {};
}
ErrorOr<void> CyrillicDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
static constexpr Array<u32, 128> translation_table = {
0x402, 0x403, 0x201A, 0x453, 0x201E, 0x2026, 0x2020, 0x2021, 0x20AC, 0x2030, 0x409, 0x2039, 0x40A, 0x40C, 0x40B, 0x40F,
0x452, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0xFFFD, 0x2122, 0x459, 0x203A, 0x45A, 0x45C, 0x45B, 0x45F,
0xA0, 0x40E, 0x45E, 0x408, 0xA4, 0x490, 0xA6, 0xA7, 0x401, 0xA9, 0x404, 0xAB, 0xAC, 0xAD, 0xAE, 0x407,
0xB0, 0xB1, 0x406, 0x456, 0x491, 0xB5, 0xB6, 0xB7, 0x451, 0x2116, 0x454, 0xBB, 0x458, 0x405, 0x455, 0x457,
0x410, 0x411, 0x412, 0x413, 0x414, 0x415, 0x416, 0x417, 0x418, 0x419, 0x41A, 0x41B, 0x41C, 0x41D, 0x41E, 0x41F,
0x420, 0x421, 0x422, 0x423, 0x424, 0x425, 0x426, 0x427, 0x428, 0x429, 0x42A, 0x42B, 0x42C, 0x42D, 0x42E, 0x42F,
0x430, 0x431, 0x432, 0x433, 0x434, 0x435, 0x436, 0x437, 0x438, 0x439, 0x43A, 0x43B, 0x43C, 0x43D, 0x43E, 0x43F,
0x440, 0x441, 0x442, 0x443, 0x444, 0x445, 0x446, 0x447, 0x448, 0x449, 0x44A, 0x44B, 0x44C, 0x44D, 0x44E, 0x44F
};
for (unsigned char ch : input) {
if (ch < 0x80) { // Superset of ASCII
TRY(on_code_point(ch));
} else {
TRY(on_code_point(translation_table[ch - 0x80]));
}
}
return {};
}
ErrorOr<void> Koi8RDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
// clang-format off
static constexpr Array<u32, 128> translation_table = {
0x2500,0x2502,0x250c,0x2510,0x2514,0x2518,0x251c,0x2524,0x252c,0x2534,0x253c,0x2580,0x2584,0x2588,0x258c,0x2590,
0x2591,0x2592,0x2593,0x2320,0x25a0,0x2219,0x221a,0x2248,0x2264,0x2265,0xA0,0x2321,0xb0,0xb2,0xb7,0xf7,
0x2550,0x2551,0x2552,0xd191,0x2553,0x2554,0x2555,0x2556,0x2557,0x2558,0x2559,0x255a,0x255b,0x255c,0x255d,0x255e,
0x255f,0x2560,0x2561,0xd081,0x2562,0x2563,0x2564,0x2565,0x2566,0x2567,0x2568,0x2569,0x256a,0x256b,0x256c,0xa9,
0x44e,0x430,0x431,0x446,0x434,0x435,0x444,0x433,0x445,0x438,0x439,0x43a,0x43b,0x43c,0x43d,0x43e,
0x43f,0x44f,0x440,0x441,0x442,0x443,0x436,0x432,0x44c,0x44b,0x437,0x448,0x44d,0x449,0x447,0x44a,
0x42e,0x410,0x441,0x426,0x414,0x415,0x424,0x413,0x425,0x418,0x419,0x41a,0x41b,0x41c,0x41d,0x41e,
0x41f,0x42f,0x420,0x421,0x422,0x423,0x416,0x412,0x42c,0x42b,0x417,0x428,0x42d,0x429,0x427,0x42a,
};
// clang-format on
for (unsigned char ch : input) {
if (ch < 0x80) { // Superset of ASCII
TRY(on_code_point(ch));
} else {
TRY(on_code_point(translation_table[ch - 0x80]));
}
}
return {};
}
ErrorOr<void> Latin9Decoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
auto convert_latin9_to_utf8 = [](u8 ch) -> u32 {
@ -649,33 +609,6 @@ ErrorOr<void> Latin9Decoder::process(StringView input, Function<ErrorOr<void>(u3
return {};
}
ErrorOr<void> MacRomanDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
// https://encoding.spec.whatwg.org/index-macintosh.txt
// clang-format off
static constexpr Array<u32, 128> translation_table = {
0x00C4, 0x00C5, 0x00C7, 0x00C9, 0x00D1, 0x00D6, 0x00DC, 0x00E1, 0x00E0, 0x00E2, 0x00E4, 0x00E3, 0x00E5, 0x00E7, 0x00E9, 0x00E8,
0x00EA, 0x00EB, 0x00ED, 0x00EC, 0x00EE, 0x00EF, 0x00F1, 0x00F3, 0x00F2, 0x00F4, 0x00F6, 0x00F5, 0x00FA, 0x00F9, 0x00FB, 0x00FC,
0x2020, 0x00B0, 0x00A2, 0x00A3, 0x00A7, 0x2022, 0x00B6, 0x00DF, 0x00AE, 0x00A9, 0x2122, 0x00B4, 0x00A8, 0x2260, 0x00C6, 0x00D8,
0x221E, 0x00B1, 0x2264, 0x2265, 0x00A5, 0x00B5, 0x2202, 0x2211, 0x220F, 0x03C0, 0x222B, 0x00AA, 0x00BA, 0x03A9, 0x00E6, 0x00F8,
0x00BF, 0x00A1, 0x00AC, 0x221A, 0x0192, 0x2248, 0x2206, 0x00AB, 0x00BB, 0x2026, 0x00A0, 0x00C0, 0x00C3, 0x00D5, 0x0152, 0x0153,
0x2013, 0x2014, 0x201C, 0x201D, 0x2018, 0x2019, 0x00F7, 0x25CA, 0x00FF, 0x0178, 0x2044, 0x20AC, 0x2039, 0x203A, 0xFB01, 0xFB02,
0x2021, 0x00B7, 0x201A, 0x201E, 0x2030, 0x00C2, 0x00CA, 0x00C1, 0x00CB, 0x00C8, 0x00CD, 0x00CE, 0x00CF, 0x00CC, 0x00D3, 0x00D4,
0xF8FF, 0x00D2, 0x00DA, 0x00DB, 0x00D9, 0x0131, 0x02C6, 0x02DC, 0x00AF, 0x02D8, 0x02D9, 0x02DA, 0x00B8, 0x02DD, 0x02DB, 0x02C7,
};
// clang-format on
for (u8 ch : input) {
if (ch < 0x80) { // Superset of ASCII
TRY(on_code_point(ch));
} else {
TRY(on_code_point(translation_table[ch - 0x80]));
}
}
return {};
}
ErrorOr<void> PDFDocEncodingDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
// PDF 1.7 spec, Appendix D.2 "PDFDocEncoding Character Set"
@ -776,4 +709,26 @@ ErrorOr<void> XUserDefinedDecoder::process(StringView input, Function<ErrorOr<vo
return {};
}
// https://encoding.spec.whatwg.org/#single-byte-decoder
ErrorOr<void> SingleByteDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
{
for (u8 const byte : input) {
if (byte < 0x80) {
// 2. If byte is an ASCII byte, return a code point whose value is byte.
TRY(on_code_point(byte));
} else {
// 3. Let code point be the index code point for byte − 0x80 in index single-byte.
auto code_point = m_translation_table[byte - 0x80];
// 4. If code point is null, return error.
// NOTE: Error is communicated with 0xFFFD
// 5. Return a code point whose value is code point.
TRY(on_code_point(code_point));
}
}
// 1. If byte is end-of-queue, return finished.
return {};
}
}

18
Userland/Libraries/LibTextCodec/Decoder.h
View file

@ -46,6 +46,19 @@ public:
virtual ErrorOr<String> to_utf8(StringView) override;
};
class SingleByteDecoder final : public Decoder {
public:
SingleByteDecoder(Array<u32, 128> translation_table)
: m_translation_table(translation_table)
{
}
virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
private:
Array<u32, 128> m_translation_table;
};
class Latin1Decoder final : public Decoder {
public:
virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
@ -81,11 +94,6 @@ public:
virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
};
class MacRomanDecoder final : public Decoder {
public:
virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
};
class PDFDocEncodingDecoder final : public Decoder {
public:
virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;