Stowage/ladybird
2
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2026-04-21 11:20:32 +00:00
Code Issues Projects Releases Packages Wiki Activity

LibRegex: Add ECMAScriptRegex and migrate callers

Browse source 
Add `ECMAScriptRegex`, LibRegex's C++ facade for ECMAScript regexes.

The facade owns compilation, execution, captures, named groups, and
error translation for the Rust backend, which lets callers stop
depending on the legacy parser and matcher types directly. Use it in the
remaining non-LibJS callers: URLPattern, HTML input pattern handling,
and the places in LibHTTP that only needed token validation.

Where a full regex engine was unnecessary, replace those call sites with
direct character checks. Also update focused LibURL, LibHTTP, and WPT
coverage for the migrated callers and corrected surrogate handling.
This commit is contained in:
Andreas Kling 2026-03-25 10:52:20 +01:00 • committed by Ali Mohammad Pur
parent 66fb0a8394
commit 34d954e2d7
Notes: github-actions[bot] 2026-03-27 16:35:21 +00:00
21 changed files with 394 additions and 104 deletions
Download patch file Download diff file Expand all files Collapse all files

33
Libraries/LibWeb/HTML/HTMLInputElement.cpp
View file

@ -275,7 +275,7 @@ Optional<GC::Ref<HTMLDataListElement const>> HTMLInputElement::suggestions_sourc
}
// https://html.spec.whatwg.org/multipage/input.html#compiled-pattern-regular-expression
Optional<Regex<ECMA262>> HTMLInputElement::compiled_pattern_regular_expression() const
Optional<regex::ECMAScriptRegex> HTMLInputElement::compiled_pattern_regular_expression() const
{
// 1. If the element does not have a pattern attribute specified, then return nothing. The element has no compiled pattern regular expression.
auto maybe_pattern = get_attribute(HTML::AttributeNames::pattern);
@ -283,20 +283,25 @@ Optional<Regex<ECMA262>> HTMLInputElement::compiled_pattern_regular_expression()
return {};
// 2. Let pattern be the value of the pattern attribute of the element.
auto pattern = maybe_pattern.release_value().to_byte_string();
auto pattern = maybe_pattern.release_value();
// 3. Let regexpCompletion be RegExpCreate(pattern, "v").
Regex<ECMA262> regexp_completion(pattern, JS::RegExpObject::default_flags | ECMAScriptFlags::UnicodeSets);
regex::ECMAScriptCompileFlags compile_flags {};
compile_flags.unicode_sets = true;
auto regexp_completion = regex::ECMAScriptRegex::compile(pattern.bytes_as_string_view(), compile_flags);
// 4. If regexpCompletion is an abrupt completion, then return nothing. The element has no compiled pattern regular expression.
if (regexp_completion.parser_result.error != regex::Error::NoError)
if (regexp_completion.is_error())
return {};
// 5. Let anchoredPattern be the string "^(?:", followed by pattern, followed by ")$".
auto anchored_pattern = ByteString::formatted("^(?:{})$", pattern);
auto anchored_pattern = MUST(String::formatted("^(?:{})$", pattern));
// 6. Return ! RegExpCreate(anchoredPattern, "v").
return Regex<ECMA262>(anchored_pattern, JS::RegExpObject::default_flags | ECMAScriptFlags::UnicodeSets);
auto anchored = regex::ECMAScriptRegex::compile(anchored_pattern.bytes_as_string_view(), compile_flags);
if (anchored.is_error())
return {};
return anchored.release_value();
}
// https://html.spec.whatwg.org/multipage/input.html#dom-input-files
@ -3557,7 +3562,13 @@ bool HTMLInputElement::suffering_from_being_missing() const
}
// https://html.spec.whatwg.org/multipage/input.html#valid-e-mail-address
static Regex<ECMA262> const valid_email_address_regex = Regex<ECMA262>("^[a-zA-Z0-9.!#$%&'*+\\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*$");
static regex::ECMAScriptRegex& valid_email_address_regex()
{
static auto regex = MUST(regex::ECMAScriptRegex::compile(
"^[a-zA-Z0-9.!#$%&'*+\\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*$"sv,
regex::ECMAScriptCompileFlags {}));
return regex;
}
// https://html.spec.whatwg.org/multipage/form-control-infrastructure.html#suffering-from-a-type-mismatch
bool HTMLInputElement::suffering_from_a_type_mismatch() const
@ -3577,7 +3588,7 @@ bool HTMLInputElement::suffering_from_a_type_mismatch() const
// When the multiple attribute is not specified on the element: While the value of the element is neither the
// empty string nor a single valid email address, the element is suffering from a type mismatch.
if (!has_attribute(HTML::AttributeNames::multiple))
return !input.is_empty() && !valid_email_address_regex.match(input.utf16_view()).success;
return !input.is_empty() && valid_email_address_regex().exec(input.utf16_view(), 0) != regex::MatchResult::Match;
// When the multiple attribute is specified on the element: While the value of the element is not a valid email
// address list, the element is suffering from a type mismatch.
@ -3588,7 +3599,7 @@ bool HTMLInputElement::suffering_from_a_type_mismatch() const
bool valid = true;
input.for_each_split_view(',', SplitBehavior::Nothing, [&](auto const& address) {
if (valid_email_address_regex.match(address).success)
if (valid_email_address_regex().exec(address, 0) == regex::MatchResult::Match)
return IterationDecision::Continue;
valid = false;
@ -3633,7 +3644,7 @@ bool HTMLInputElement::suffering_from_a_pattern_mismatch() const
bool valid = true;
value.for_each_split_view(',', SplitBehavior::Nothing, [&](auto const& value) {
if (regexp_object->match(value).success)
if (regexp_object->exec(value, 0) == regex::MatchResult::Match)
return IterationDecision::Continue;
valid = false;
@ -3643,7 +3654,7 @@ bool HTMLInputElement::suffering_from_a_pattern_mismatch() const
return !valid;
}
return !regexp_object->match(value.utf16_view()).success;
return regexp_object->exec(value.utf16_view(), 0) != regex::MatchResult::Match;
}
// https://html.spec.whatwg.org/multipage/form-control-infrastructure.html#suffering-from-an-underflow