RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 07:48:11 +00:00
Code Issues Activity Actions

LibWeb: Implement state switch for "[CDATA[" in HTML parser

Browse source
This commit is contained in:
Linus Groh 2022-02-15 18:52:45 +00:00 • committed by Andreas Kling
parent 3f7086f91a
commit 892f6394b8
2 changed files with 14 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.h
View file

@ -42,6 +42,8 @@ namespace Web::HTML {
RefPtr<DOM::Document> parse_html_document(StringView, const AK::URL&, const String& encoding); RefPtr<DOM::Document> parse_html_document(StringView, const AK::URL&, const String& encoding);
class HTMLParser { class HTMLParser {
friend class HTMLTokenizer;
public: public:
HTMLParser(DOM::Document&, StringView input, const String& encoding); HTMLParser(DOM::Document&, StringView input, const String& encoding);
~HTMLParser(); ~HTMLParser();

13
Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
View file

@ -1,5 +1,6 @@
/* /*
* Copyright (c) 2020, Andreas Kling <kling@serenityos.org> * Copyright (c) 2020, Andreas Kling <kling@serenityos.org>
* Copyright (c) 2022, Linus Groh <linusg@serenityos.org>
* *
* SPDX-License-Identifier: BSD-2-Clause * SPDX-License-Identifier: BSD-2-Clause
*/ */
@ -9,8 +10,10 @@
#include <AK/SourceLocation.h> #include <AK/SourceLocation.h>
#include <LibTextCodec/Decoder.h> #include <LibTextCodec/Decoder.h>
#include <LibWeb/HTML/Parser/Entities.h> #include <LibWeb/HTML/Parser/Entities.h>
#include <LibWeb/HTML/Parser/HTMLParser.h>
#include <LibWeb/HTML/Parser/HTMLToken.h> #include <LibWeb/HTML/Parser/HTMLToken.h>
#include <LibWeb/HTML/Parser/HTMLTokenizer.h> #include <LibWeb/HTML/Parser/HTMLTokenizer.h>
#include <LibWeb/Namespace.h>
#include <string.h> #include <string.h>
namespace Web::HTML { namespace Web::HTML {
@ -394,7 +397,15 @@ _StartOfFunction:
SWITCH_TO(DOCTYPE); SWITCH_TO(DOCTYPE);
} }
if (consume_next_if_match("[CDATA[")) { if (consume_next_if_match("[CDATA[")) {
TODO(); // We keep the parser optional so that syntax highlighting can be lexer-only.
// The parser registers itself with the lexer it creates.
if (m_parser != nullptr && m_parser->adjusted_current_node().namespace_() != Namespace::HTML) {
SWITCH_TO(CDATASection);
} else {
create_new_token(HTMLToken::Type::Comment);
m_current_builder.append("[CDATA[");
SWITCH_TO_WITH_UNCLEAN_BUILDER(BogusComment);
}
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {