beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-22 07:30:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

LibWeb: Don't skip filtering when CSS contains null or surrogates

Browse source
This commit is contained in:
Gingeh 2024-11-20 20:55:46 +11:00 committed by Jelle Raaijmakers
parent 356507284e
commit 4b1deb6fe1
Notes: github-actions[bot] 2024-11-20 14:48:10 +00:00 
Author: https://github.com/Gingeh
Commit: https://github.com/LadybirdBrowser/ladybird/commit/4b1deb6fe12
Pull-request: https://github.com/LadybirdBrowser/ladybird/pull/2453
3 changed files with 52 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
Libraries/LibWeb/CSS/Parser/Tokenizer.cpp
View file

@ -204,15 +204,15 @@ Vector<Token> Tokenizer::tokenize(StringView input, StringView encoding)
auto decoded_input = MUST(decoder->to_utf8(input)); auto decoded_input = MUST(decoder->to_utf8(input));
// OPTIMIZATION: If the input doesn't contain any CR or FF, we can skip the filtering // OPTIMIZATION: If the input doesn't contain any filterable characters, we can skip the filtering
bool const contains_cr_or_ff = [&] { bool const contains_filterable = [&] {
for (auto byte : decoded_input.bytes()) { for (auto code_point : decoded_input.code_points()) {
if (byte == '\r' || byte == '\f') if (code_point == '\r' || code_point == '\f' || code_point == 0x00 || is_unicode_surrogate(code_point))
return true; return true;
} }
return false; return false;
}(); }();
if (!contains_cr_or_ff) { if (!contains_filterable) {
return decoded_input; return decoded_input;
} }
@ -242,7 +242,7 @@ Vector<Token> Tokenizer::tokenize(StringView input, StringView encoding)
} else if (code_point == '\f') { } else if (code_point == '\f') {
builder.append('\n'); builder.append('\n');
// Replace any U+0000 NULL or surrogate code points in input with U+FFFD REPLACEMENT CHARACTER (<28>). // Replace any U+0000 NULL or surrogate code points in input with U+FFFD REPLACEMENT CHARACTER (<28>).
} else if (code_point == 0x00 || (code_point >= 0xD800 && code_point <= 0xDFFF)) { } else if (code_point == 0x00 || is_unicode_surrogate(code_point)) {
builder.append_code_point(REPLACEMENT_CHARACTER); builder.append_code_point(REPLACEMENT_CHARACTER);
} else { } else {
builder.append_code_point(code_point); builder.append_code_point(code_point);

BIN
Tests/LibWeb/Text/expected/wpt-import/css/css-syntax/input-preprocessing.txt Normal file
View file

Binary file not shown.

46
Tests/LibWeb/Text/input/wpt-import/css/css-syntax/input-preprocessing.html Normal file
View file

@ -0,0 +1,46 @@
<!doctype html>
<title>Input Preprocessing</title>
<script src="../../resources/testharness.js"></script>
<script src="../../resources/testharnessreport.js"></script>
<style>
foo { color: blue; }
</style>
<meta name="author" title="Tab Atkins-Bittner">
<link rel=help href="https://drafts.csswg.org/css-syntax/#input-preprocessing">
<script>
function roundtripIdent(str) {
const rule = document.styleSheets[0].cssRules[0];
rule.selectorText = "original-ident";
rule.selectorText = str;
// Check for parse error.
if(rule.selectorText == "original-ident") return "parse error";
return rule.selectorText;
}
function testParsing(input, expected) {
test(()=>{
assert_equals(roundtripIdent(input), expected);
}, `"${input}" becomes "${expected}"`);
}
/* Can't figure out how to test the newline normalization... */
/* NULL becomes FFFD */
testParsing("foo\x00", "foo\ufffd");
testParsing("f\x00oo", "f\ufffdoo");
testParsing("\x00foo", "\ufffdfoo");
testParsing("\x00", "\ufffd");
testParsing("\x00\x00\x00", "\ufffd\ufffd\ufffd");
/* surrogates become FFFD */
testParsing("foo\ud800", "foo\ufffd");
testParsing("f\ud800oo", "f\ufffdoo");
testParsing("\ud800foo", "\ufffdfoo");
testParsing("\ud800", "\ufffd");
testParsing("\ud800\ud800\ud800", "\ufffd\ufffd\ufffd");
</script>