system/serenity
system/serenity
1
0
Fork 0
mirror of https://github.com/SerenityOS/serenity synced 2024-07-21 01:55:07 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

LibTextCodec: Add ISO-8859-10 decoder

Browse source
This commit is contained in:
Simon Wanner 2024-05-27 18:02:23 +02:00 committed by Andreas Kling
parent d73220837e
commit cc640f4363
1 changed files with 14 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
Userland/Libraries/LibTextCodec/Decoder.cpp
View file

@ -105,6 +105,17 @@ SingleByteDecoder s_latin_hebrew_decoder {{
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-iso-8859-10.txt
SingleByteDecoder s_latin6_decoder {{
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, 0x0104, 0x0112, 0x0122, 0x012A, 0x0128, 0x0136, 0x00A7, 0x013B, 0x0110, 0x0160, 0x0166, 0x017D, 0x00AD, 0x016A, 0x014A,
0x00B0, 0x0105, 0x0113, 0x0123, 0x012B, 0x0129, 0x0137, 0x00B7, 0x013C, 0x0111, 0x0161, 0x0167, 0x017E, 0x2015, 0x016B, 0x014B,
0x0100, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x012E, 0x010C, 0x00C9, 0x0118, 0x00CB, 0x0116, 0x00CD, 0x00CE, 0x00CF,
0x00D0, 0x0145, 0x014C, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x0168, 0x00D8, 0x0172, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF,
0x0101, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x012F, 0x010D, 0x00E9, 0x0119, 0x00EB, 0x0117, 0x00ED, 0x00EE, 0x00EF,
0x00F0, 0x0146, 0x014D, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x0169, 0x00F8, 0x0173, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x0138,
}};
// 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,
@ -194,6 +205,8 @@ Optional<Decoder&> decoder_for(StringView a_encoding)
return s_latin_hebrew_decoder;
if (encoding.value().equals_ignoring_ascii_case("iso-8859-8-i"sv))
return s_latin_hebrew_decoder;
if (encoding.value().equals_ignoring_ascii_case("iso-8859-10"sv))
return s_latin6_decoder;
if (encoding.value().equals_ignoring_ascii_case("windows-1250"sv))
return s_centraleurope_decoder;
if (encoding.value().equals_ignoring_ascii_case("windows-1255"sv))
@ -242,7 +255,7 @@ Optional<StringView> get_standardized_encoding(StringView encoding)
return "ISO-8859-8"sv;
if (encoding.is_one_of_ignoring_ascii_case("csiso88598i"sv, "iso-8859-8-i"sv, "logical"sv))
return "ISO-8859-8-I"sv;
if (encoding.is_one_of_ignoring_ascii_case("csisolatin6"sv, "iso8859-10"sv, "iso-ir-157"sv, "iso8859-10"sv, "iso885910"sv, "l6"sv, "latin6"sv))
if (encoding.is_one_of_ignoring_ascii_case("csisolatin6"sv, "iso-8859-10"sv, "iso-ir-157"sv, "iso8859-10"sv, "iso885910"sv, "l6"sv, "latin6"sv))
return "ISO-8859-10"sv;
if (encoding.is_one_of_ignoring_ascii_case("iso-8859-13"sv, "iso8859-13"sv, "iso885913"sv))
return "ISO-8859-13"sv;