system/serenity
system/serenity
1
0
Fork 0
mirror of https://github.com/SerenityOS/serenity synced 2024-07-09 05:20:45 +00:00
Code Issues Projects Releases Wiki Activity

LibWeb: Fix assertion failure when tokenizing JS regex literals

Browse Source 
This fixes parsing the following regular expression: /</g;

It also adds a simple script element to the HTMLTokenizer regression
test, which also contains that specific regex.
This commit is contained in:
Max Wipfli 2021-07-15 01:25:34 +02:00 committed by Andreas Kling
parent c82c652ee4
commit 2404ad6897
3 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Tests/LibWeb/TestHTMLTokenizer.cpp
View File

@ -193,5 +193,5 @@ TEST_CASE(regression)
auto file_contents = file.value()->read_all();
auto tokens = run_tokenizer(file_contents);
u32 hash = hash_tokens(tokens);
EXPECT_EQ(hash, 2891738465u);
EXPECT_EQ(hash, 2203864459u);
}

7
Tests/LibWeb/tokenizer-test.html
View File

@ -3,6 +3,13 @@
<head>
<meta charset="UTF-8">
<title>This is a test page :^)</title>
<script>
let foo = 2;
var bar = 3;
if (foo < bar)
alert("Check happens with HTML special <characters>.");
let regex = /</g;
</script>
</head>
<body>
<p>This is the first paragraph.</p>

2
Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
View File

@ -2561,6 +2561,8 @@ _StartOfFunction:
{
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/'));
// NOTE: The spec doesn't mention this, but it seems that m_current_token (an end tag) is just dropped in this case.
m_current_builder.clear();
for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(ScriptData);