RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-06-01 10:08:10 +00:00
Code Issues Activity Actions

LibRegex: Use correct source characters for Unicode identity escapes

Browse source
This commit is contained in:
Timothy Flynn 2021-08-11 17:52:57 -04:00 • committed by Linus Groh
parent 6a485f612f
commit c3e1f1f687
2 changed files with 20 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
Tests/LibRegex/Regex.cpp
View file

@ -557,6 +557,8 @@ TEST_CASE(ECMA262_parse)
{ "[\\0]"sv, regex::Error::NoError, combine_flags(ECMAScriptFlags::Unicode, ECMAScriptFlags::BrowserExtended) },
{ "[\\00]"sv, regex::Error::NoError, ECMAScriptFlags::BrowserExtended },
{ "[\\00]"sv, regex::Error::InvalidPattern, combine_flags(ECMAScriptFlags::Unicode, ECMAScriptFlags::BrowserExtended) },
{ "\\^\\$\\\\\\.\\*\\+\\?\\(\\)\\[\\]\\{\\}\\|\\/"sv, regex::Error::NoError, ECMAScriptFlags::Unicode },
{ "[\\^\\$\\\\\\.\\*\\+\\?\\(\\)\\[\\]\\{\\}\\|\\/]"sv, regex::Error::NoError, ECMAScriptFlags::Unicode },
};
for (auto& test : tests) {
@ -605,6 +607,8 @@ TEST_CASE(ECMA262_match)
{ "((...)X)+"sv, "fooXbarXbazX"sv, true },
{ "(?:)"sv, ""sv, true },
{ "\\^"sv, "^"sv },
{ "\\^\\$\\\\\\.\\*\\+\\?\\(\\)\\[\\]\\{\\}\\|\\/"sv, "^$\\.*+?()[]{}|/"sv, true, ECMAScriptFlags::Unicode },
{ "[\\^\\$\\\\\\.\\*\\+\\?\\(\\)\\[\\]\\{\\}\\|\\/]{15}"sv, "^$\\.*+?()[]{}|/"sv, true, ECMAScriptFlags::Unicode },
// ECMA262, B.1.4. Regular Expression Pattern extensions for browsers
{ "{"sv, "{"sv, true, ECMAScriptFlags::BrowserExtended },
{ "\\5"sv, "\5"sv, true, ECMAScriptFlags::BrowserExtended },

18
Userland/Libraries/LibRegex/RegexParser.cpp
View file

@ -20,6 +20,15 @@ static constexpr size_t s_maximum_repetition_count = 1024 * 1024;
static constexpr auto s_alphabetic_characters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"sv;
static constexpr auto s_decimal_characters = "0123456789"sv;
static constexpr StringView identity_escape_characters(bool unicode, bool browser_extended)
{
if (unicode)
return "^$\\.*+?()[]{}|/"sv;
if (browser_extended)
return "^$\\.*+?()[|"sv;
return "^$\\.*+?()[]{}|"sv;
}
ALWAYS_INLINE bool Parser::set_error(Error error)
{
if (m_parser_state.error == Error::NoError) {
@ -1530,8 +1539,7 @@ bool ECMA262Parser::parse_atom_escape(ByteCode& stack, size_t& match_length_mini
}
// IdentityEscape
auto source_characters = m_should_use_browser_extended_grammar ? "^$\\.*+?()[|"sv : "^$\\.*+?()[]{}|"sv;
for (auto ch : source_characters) {
for (auto ch : identity_escape_characters(unicode, m_should_use_browser_extended_grammar)) {
if (try_skip({ &ch, 1 })) {
match_length_minimum += 1;
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (ByteCodeValueType)ch } });
@ -1840,6 +1848,12 @@ bool ECMA262Parser::parse_nonempty_class_ranges(Vector<CompareTypeAndValuePair>&
}
}
// IdentityEscape
for (auto ch : identity_escape_characters(unicode, m_should_use_browser_extended_grammar)) {
if (try_skip({ &ch, 1 }))
return { CharClassRangeElement { .code_point = (u32)ch, .is_character_class = false } };
}
if (unicode) {
if (try_skip("-"))
return { CharClassRangeElement { .code_point = '-', .is_character_class = false } };