RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 08:18:11 +00:00
Code Issues Activity Actions

LibTextCodec: Change UTF-8's decoder to replace invalid code points

Browse source 
The UTF-8 decoder will currently crash if it is provided invalid UTF-8
input. Instead, change its behavior to match that of all other decoders
to replace invalid code points with U+FFFD. This is required by the web.
This commit is contained in:
Timothy Flynn 2023-05-11 11:22:41 -04:00 • committed by Andreas Kling
parent cb32bb3502
commit 00fa23237a
1 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
Userland/Libraries/LibTextCodec/Decoder.cpp
View file

@ -213,10 +213,12 @@ ErrorOr<String> convert_input_to_utf8_using_given_decoder_unless_there_is_a_byte
VERIFY(actual_decoder); VERIFY(actual_decoder);
// FIXME: 3. Process a queue with an instance of encoding’s decoder, ioQueue, output, and "replacement". // 3. Process a queue with an instance of encoding’s decoder, ioQueue, output, and "replacement".
// This isn't the exact same as the spec, especially the error mode of "replacement", which we don't have the concept of yet. // FIXME: This isn't the exact same as the spec, which is written in terms of I/O queues.
auto output = TRY(actual_decoder->to_utf8(input));
// 4. Return output. // 4. Return output.
return actual_decoder->to_utf8(input); return output;
} }
ErrorOr<String> Decoder::to_utf8(StringView input) ErrorOr<String> Decoder::to_utf8(StringView input)
@ -242,7 +244,7 @@ ErrorOr<String> UTF8Decoder::to_utf8(StringView input)
bomless_input = input.substring_view(3); bomless_input = input.substring_view(3);
} }
return String::from_utf8(bomless_input); return Decoder::to_utf8(bomless_input);
} }
ErrorOr<void> UTF16BEDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point) ErrorOr<void> UTF16BEDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)