beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-21 23:20:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

LibWeb: Deduplicate attributes when emitting start and end tags
Some checks are pending
CI / Lagom (true, NO_FUZZ, ubuntu-22.04, Linux, Clang) (push) Waiting to run
Details
CI / Lagom (false, FUZZ, ubuntu-22.04, Linux, Clang) (push) Waiting to run
Details
CI / Lagom (false, NO_FUZZ, macos-14, macOS, Clang) (push) Waiting to run
Details
CI / Lagom (false, NO_FUZZ, ubuntu-22.04, Linux, GNU) (push) Waiting to run
Details
Package the js repl as a binary artifact / build-and-package (macos-14, macOS, macOS-universal2) (push) Waiting to run
Details
Package the js repl as a binary artifact / build-and-package (ubuntu-22.04, Linux, Linux-x86_64) (push) Waiting to run
Details
Run test262 and test-wasm / run_and_update_results (push) Waiting to run
Details
Lint Code / lint (push) Waiting to run
Details
Push notes / build (push) Waiting to run
Details

Browse source 
The HTML tokenizer specification says that we're supposed to do this
when leaving the Attribute name or when emitting the token, as
appropriate.

Hopefully 'as appropriate' can mean only when emitting the token, as
that's the easiest place to insert this logic without complicating the
tokenizer any more.
This commit is contained in:
Andrew Kaster 2024-09-30 17:52:30 -06:00 committed by Andreas Kling
parent b3f8d63372
commit 7aa0165fe7
Notes: github-actions[bot] 2024-10-01 09:05:13 +00:00 
Author: https://github.com/ADKaster
Commit: https://github.com/LadybirdBrowser/ladybird/commit/7aa0165fe75
Pull-request: https://github.com/LadybirdBrowser/ladybird/pull/1582
5 changed files with 63 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
Tests/LibWeb/Text/expected/html-parser-duplicate-attributes.txt Normal file
View file

@ -0,0 +1,8 @@
divs[0].id: fred
divs[0].className: math
divs[1].id: spaghetti
divs[1].className:
divs[2].getAttribute("grape"): foo
divs[0].numAttributes: 2
divs[1].numAttributes: 2
divs[2].numAttributes: 1

21
Tests/LibWeb/Text/input/html-parser-duplicate-attributes.html Normal file
View file

@ -0,0 +1,21 @@
<!DOCTYPE html>
<script src="include.js"></script>
<div id="fred"id="barney" class="math"></div>
<div class class=1"foo" id="spaghetti" id></div>
<div grape="foo" grape grape="bar" grape grape grape=baz></div>
<script>
test(() => {
let divs = document.getElementsByTagName("div");
// Per the HTML spec, the first attribute wins.
println(`divs[0].id: ${divs[0].id}`);
println(`divs[0].className: ${divs[0].className}`);
println(`divs[1].id: ${divs[1].id}`);
println(`divs[1].className: ${divs[1].className}`);
println(`divs[2].getAttribute("grape"): ${divs[2].getAttribute("grape")}`);
println(`divs[0].numAttributes: ${divs[0].attributes.length}`); // 2
println(`divs[1].numAttributes: ${divs[1].attributes.length}`); // 2
println(`divs[2].numAttributes: ${divs[2].attributes.length}`); // 1
});
</script>

29
Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp
View file

@ -4,6 +4,7 @@
* SPDX-License-Identifier: BSD-2-Clause
*/
#include <AK/HashTable.h>
#include <LibWeb/HTML/Parser/HTMLToken.h>
namespace Web::HTML {
@ -73,4 +74,32 @@ String HTMLToken::to_string() const
return MUST(builder.to_string());
}
void HTMLToken::normalize_attributes()
{
// From AttributeNameState: https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state
//
// When the user agent leaves the attribute name state (and before emitting the tag token, if appropriate),
// the complete attribute's name must be compared to the other attributes on the same token;
// if there is already an attribute on the token with the exact same name, then this is a duplicate-attribute
// parse error and the new attribute must be removed from the token.
// NOTE: If an attribute is so removed from a token, it, and the value that gets associated with it, if any,
// are never subsequently used by the parser, and are therefore effectively discarded. Removing the attribute
// in this way does not change its status as the "current attribute" for the purposes of the tokenizer, however.
HashTable<FlyString> seen_attributes;
auto* ptr = tag_attributes();
if (!ptr)
return;
auto& tag_attributes = *ptr;
for (size_t i = 0; i < tag_attributes.size(); ++i) {
auto& attribute = tag_attributes[i];
if (seen_attributes.set(attribute.local_name, AK::HashSetExistingEntryBehavior::Keep) == AK::HashSetResult::KeptExistingEntry) {
// This is a duplicate attribute, remove it.
tag_attributes.remove(i);
--i;
}
}
}
}

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

@ -328,6 +328,8 @@ public:
void set_start_position(Badge<HTMLTokenizer>, Position start_position) { m_start_position = start_position; }
void set_end_position(Badge<HTMLTokenizer>, Position end_position) { m_end_position = end_position; }
void normalize_attributes();
private:
Vector<Attribute> const* tag_attributes() const
{

3
Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
View file

@ -2863,6 +2863,9 @@ void HTMLTokenizer::will_emit(HTMLToken& token)
auto is_start_or_end_tag = token.type() == HTMLToken::Type::StartTag || token.type() == HTMLToken::Type::EndTag;
token.set_end_position({}, nth_last_position(is_start_or_end_tag ? 1 : 0));
if (is_start_or_end_tag)
token.normalize_attributes();
}
bool HTMLTokenizer::current_end_tag_token_is_appropriate() const