RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-06-01 08:18:12 +00:00
Code Issues Activity Actions

LibRegex: Allow Unicode escape sequences in capture group names

Browse source 
Unfortunately, this requires a slight divergence in the way the capture
group names are stored. Previously, the generated byte code would simply
store a view into the regex pattern string, so no string copying was
required.

Now, the escape sequences are decoded into a new string, and a vector
of all parsed capture group names are stored in a vector in the parser
result structure. The byte code then stores a view into the
corresponding string in that vector.
This commit is contained in:
Timothy Flynn 2021-08-18 17:17:18 -04:00 • committed by Andreas Kling
parent 6131c0485e
commit 4f2cbe119b
4 changed files with 38 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

26
Userland/Libraries/LibRegex/RegexParser.cpp
View file

@ -195,7 +195,8 @@ Parser::Result Parser::parse(Optional<AllOptions> regex_options)
move(m_parser_state.named_capture_groups_count),
move(m_parser_state.match_length_minimum),
move(m_parser_state.error),
move(m_parser_state.error_token)
move(m_parser_state.error_token),
m_parser_state.named_capture_groups.keys()
};
}
@ -2009,21 +2010,30 @@ bool ECMA262Parser::parse_unicode_property_escape(PropertyEscape& property, bool
[](Empty&) -> bool { VERIFY_NOT_REACHED(); });
}
StringView ECMA262Parser::read_capture_group_specifier(bool take_starting_angle_bracket)
FlyString ECMA262Parser::read_capture_group_specifier(bool take_starting_angle_bracket)
{
if (take_starting_angle_bracket && !consume("<"))
return {};
auto start_token = m_parser_state.current_token;
size_t offset = 0;
while (match(TokenType::Char) || match(TokenType::Dollar)) {
StringBuilder builder;
while (match(TokenType::Char) || match(TokenType::Dollar) || match(TokenType::LeftCurly) || match(TokenType::RightCurly)) {
auto c = m_parser_state.current_token.value();
if (c == ">")
break;
offset += consume().value().length();
if (try_skip("\\u"sv)) {
if (auto code_point = consume_escaped_code_point(true); code_point.has_value()) {
builder.append_code_point(*code_point);
} else {
set_error(Error::InvalidNameForCaptureGroup);
return {};
}
} else {
builder.append(consume().value());
}
}
StringView name { start_token.value().characters_without_null_termination(), offset };
FlyString name = builder.build();
if (!consume(">") || name.is_empty())
set_error(Error::InvalidNameForCaptureGroup);
@ -2146,7 +2156,7 @@ bool ECMA262Parser::parse_capture_group(ByteCode& stack, size_t& match_length_mi
stack.insert_bytecode_group_capture_left(group_index);
stack.extend(move(capture_group_bytecode));
stack.insert_bytecode_group_capture_right(group_index, name);
stack.insert_bytecode_group_capture_right(group_index, name.view());
match_length_minimum += length;