mirrors/ladybird
0
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2025-07-28 11:49:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

HTMLEncodingDetection: Use mime type in encoding sniffing

Browse source 
Also added proper spec comments.
Fixes at least one WPT test that was failing previously:
https://wpt.live/encoding/single-byte-decoder.window.html?document
This commit is contained in:
0x4261756D 2024-10-10 02:04:07 +02:00 • committed by Andreas Kling
commit c1a14f66ad
Notes: github-actions[bot] 2024-10-12 14:15:30 +00:00
3 changed files with 67 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

8
Userland/Libraries/LibWeb/DOM/DocumentLoading.cpp
View file

@ -146,14 +146,14 @@ static WebIDL::ExceptionOr<JS::NonnullGCPtr<DOM::Document>> load_xml_document(HT
if (auto maybe_encoding = type.parameters().get("charset"sv); maybe_encoding.has_value())
content_encoding = maybe_encoding.value();
auto process_body = JS::create_heap_function(document->heap(), [document, url = navigation_params.response->url().value(), content_encoding = move(content_encoding)](ByteBuffer data) {
auto process_body = JS::create_heap_function(document->heap(), [document, url = navigation_params.response->url().value(), content_encoding = move(content_encoding), mime = type](ByteBuffer data) {
Optional<TextCodec::Decoder&> decoder;
// The actual HTTP headers and other metadata, not the headers as mutated or implied by the algorithms given in this specification,
// are the ones that must be used when determining the character encoding according to the rules given in the above specifications.
if (content_encoding.has_value())
decoder = TextCodec::decoder_for(*content_encoding);
if (!decoder.has_value()) {
auto encoding = HTML::run_encoding_sniffing_algorithm(document, data);
auto encoding = HTML::run_encoding_sniffing_algorithm(document, data, mime);
decoder = TextCodec::decoder_for(encoding);
}
VERIFY(decoder.has_value());
@ -226,8 +226,8 @@ static WebIDL::ExceptionOr<JS::NonnullGCPtr<DOM::Document>> load_text_document(H
// document's relevant global object to have the parser to process the implied EOF character, which eventually causes a
// load event to be fired.
// FIXME: Parse as we receive the document data, instead of waiting for the whole document to be fetched first.
auto process_body = JS::create_heap_function(document->heap(), [document, url = navigation_params.response->url().value()](ByteBuffer data) {
auto encoding = run_encoding_sniffing_algorithm(document, data);
auto process_body = JS::create_heap_function(document->heap(), [document, url = navigation_params.response->url().value(), mime = type](ByteBuffer data) {
auto encoding = run_encoding_sniffing_algorithm(document, data, mime);
dbgln_if(HTML_PARSER_DEBUG, "The encoding sniffing algorithm returned encoding '{}'", encoding);
auto parser = HTML::HTMLParser::create_for_scripting(document);