mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2026-04-18 18:00:31 +00:00
34d954e2d7
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.
56 lines
1.7 KiB
C++
56 lines
1.7 KiB
C++
/*
|
|
* Copyright (c) 2025, Shannon Booth <shannon@serenityos.org>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/HashMap.h>
|
|
#include <AK/Optional.h>
|
|
#include <AK/OwnPtr.h>
|
|
#include <AK/String.h>
|
|
#include <LibRegex/ECMAScriptRegex.h>
|
|
#include <LibURL/Pattern/PatternParser.h>
|
|
|
|
namespace URL::Pattern {
|
|
|
|
// https://urlpattern.spec.whatwg.org/#component
|
|
struct Component {
|
|
static PatternErrorOr<Component> compile(Utf8View const& input, PatternParser::EncodingCallback, Options const&);
|
|
|
|
// https://urlpattern.spec.whatwg.org/#dictdef-urlpatterncomponentresult
|
|
struct Result {
|
|
String input;
|
|
OrderedHashMap<String, Variant<String, Empty>> groups;
|
|
};
|
|
|
|
struct ExecutionResult {
|
|
bool success { false };
|
|
Vector<Optional<String>> captures;
|
|
};
|
|
|
|
Result create_match_result(String const& input, ExecutionResult const& exec_result) const;
|
|
ExecutionResult execute(String const& input) const;
|
|
bool matches(StringView input) const;
|
|
|
|
// https://urlpattern.spec.whatwg.org/#component-pattern-string
|
|
// pattern string, a well formed pattern string
|
|
String pattern_string;
|
|
|
|
// https://urlpattern.spec.whatwg.org/#component-regular-expression
|
|
// regular expression, a RegExp
|
|
OwnPtr<regex::ECMAScriptRegex> regular_expression;
|
|
|
|
// https://urlpattern.spec.whatwg.org/#component-group-name-list
|
|
// group name list, a list of strings
|
|
Vector<String> group_name_list;
|
|
|
|
// https://urlpattern.spec.whatwg.org/#component-has-regexp-groups
|
|
// has regexp groups, a boolean
|
|
bool has_regexp_groups {};
|
|
};
|
|
|
|
bool protocol_component_matches_a_special_scheme(Component const& protocol_component);
|
|
|
|
}
|