system/serenity
system/serenity
1
0
Fork 0
mirror of https://github.com/SerenityOS/serenity synced 2024-07-01 11:19:21 +00:00
Code Issues Projects Releases Wiki Activity

LibTextCodec: Bring TextCodec::get_standardized_encoding closer to spec

Browse Source 
(cherry picked from commit 09f2d79cb10f84dfaedea61264d8a9d91bdfa17c)
This commit is contained in:
Simon Wanner 2024-05-30 21:35:50 +02:00 committed by Nico Weber
parent 30609289b5
commit 328552a269
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Userland/Libraries/LibTextCodec/Decoder.cpp
View File

@ -388,8 +388,11 @@ Optional<Decoder&> decoder_for(StringView a_encoding)
// https://encoding.spec.whatwg.org/#concept-encoding-get
Optional<StringView> get_standardized_encoding(StringView encoding)
{
encoding = encoding.trim_whitespace();
// 1. Remove any leading and trailing ASCII whitespace from label.
// https://infra.spec.whatwg.org/#ascii-whitespace: ASCII whitespace is U+0009 TAB, U+000A LF, U+000C FF, U+000D CR, or U+0020 SPACE.
encoding = encoding.trim("\t\n\f\r "sv);
// 2. If label is an ASCII case-insensitive match for any of the labels listed in the table below, then return the corresponding encoding; otherwise return failure.
if (encoding.is_one_of_ignoring_ascii_case("unicode-1-1-utf-8"sv, "unicode11utf8"sv, "unicode20utf8"sv, "utf-8"sv, "utf8"sv, "x-unicode20utf8"sv))
return "UTF-8"sv;
if (encoding.is_one_of_ignoring_ascii_case("866"sv, "cp866"sv, "csibm866"sv, "ibm866"sv))