diff options
author | Idan Horowitz <idan.horowitz@gmail.com> | 2021-04-17 18:15:32 +0300 |
---|---|---|
committer | Linus Groh <mail@linusgroh.de> | 2021-04-17 18:13:20 +0200 |
commit | 4a2c0d721f5f8b2fba4355556e729c6f13f26b6c (patch) | |
tree | fe1dae5bb10933911f7144d6948c0fc703d9a350 /Userland/Libraries/LibTextCodec | |
parent | 79b1270711b7038eb8de6ef108cd3ca132abbc32 (diff) | |
download | serenity-4a2c0d721f5f8b2fba4355556e729c6f13f26b6c.zip |
LibTextCodec: Implement a Windows-1255 decoder.
This is a superset of ascii that adds in the hebrew alphabet.
(Google currently assumes we are running windows due to not
recognizing Serenity as the OS in the user agent, resulting
in this encoding instead of UTF8 in google search results)
Diffstat (limited to 'Userland/Libraries/LibTextCodec')
-rw-r--r-- | Userland/Libraries/LibTextCodec/Decoder.cpp | 39 | ||||
-rw-r--r-- | Userland/Libraries/LibTextCodec/Decoder.h | 5 |
2 files changed, 41 insertions, 3 deletions
diff --git a/Userland/Libraries/LibTextCodec/Decoder.cpp b/Userland/Libraries/LibTextCodec/Decoder.cpp index b075a81870..f273d267cb 100644 --- a/Userland/Libraries/LibTextCodec/Decoder.cpp +++ b/Userland/Libraries/LibTextCodec/Decoder.cpp @@ -33,7 +33,7 @@ namespace TextCodec { namespace { Latin1Decoder& latin1_decoder() { - static Latin1Decoder* decoder; + static Latin1Decoder* decoder = nullptr; if (!decoder) decoder = new Latin1Decoder; return *decoder; @@ -41,7 +41,7 @@ Latin1Decoder& latin1_decoder() UTF8Decoder& utf8_decoder() { - static UTF8Decoder* decoder; + static UTF8Decoder* decoder = nullptr; if (!decoder) decoder = new UTF8Decoder; return *decoder; @@ -49,7 +49,7 @@ UTF8Decoder& utf8_decoder() UTF16BEDecoder& utf16be_decoder() { - static UTF16BEDecoder* decoder; + static UTF16BEDecoder* decoder = nullptr; if (!decoder) decoder = new UTF16BEDecoder; return *decoder; @@ -63,6 +63,14 @@ Latin2Decoder& latin2_decoder() return *decoder; } +HebrewDecoder& hebrew_decoder() +{ + static HebrewDecoder* decoder = nullptr; + if (!decoder) + decoder = new HebrewDecoder; + return *decoder; +} + } Decoder* decoder_for(const String& a_encoding) @@ -76,6 +84,8 @@ Decoder* decoder_for(const String& a_encoding) return &utf16be_decoder(); if (encoding.equals_ignoring_case("iso-8859-2")) return &latin2_decoder(); + if (encoding.equals_ignoring_case("windows-1255")) + return &hebrew_decoder(); dbgln("TextCodec: No decoder implemented for encoding '{}'", a_encoding); return nullptr; } @@ -291,4 +301,27 @@ String Latin2Decoder::to_utf8(const StringView& input) return builder.to_string(); } +String HebrewDecoder::to_utf8(const StringView& input) +{ + 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 + }; + StringBuilder builder(input.length()); + for (unsigned char ch : input) { + if (ch < 0x80) { // Superset of ASCII + builder.append(ch); + } else { + builder.append_code_point(translation_table[ch - 0x80]); + } + } + return builder.to_string(); +} + } diff --git a/Userland/Libraries/LibTextCodec/Decoder.h b/Userland/Libraries/LibTextCodec/Decoder.h index 1740d6975e..22faf6fb36 100644 --- a/Userland/Libraries/LibTextCodec/Decoder.h +++ b/Userland/Libraries/LibTextCodec/Decoder.h @@ -58,6 +58,11 @@ public: virtual String to_utf8(const StringView&) override; }; +class HebrewDecoder final : public Decoder { +public: + virtual String to_utf8(const StringView&) override; +}; + Decoder* decoder_for(const String& encoding); String get_standardized_encoding(const String& encoding); bool is_standardized_encoding(const String& encoding); |