fergalmoran/ladybird
1
0
Fork 0
mirror of https://github.com/fergalmoran/ladybird.git synced 2026-01-04 15:45:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

LibJS: Lex and parse regex literals, add RegExp objects

Browse Source 
This adds regex parsing/lexing, as well as a relatively empty
RegExpObject. The purpose of this patch is to allow the engine to not
get hung up on parsing regexes. This will aid in finding new syntax
errors (say, from google or twitter) without having to replace all of
their regexes first!
This commit is contained in:
Matthew Olsson
2020-06-03 16:05:49 -07:00
committed by Andreas Kling
parent 984a6ff97b
commit 61ac1d3ffa
20 changed files with 424 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
Libraries/LibJS/Lexer.cpp
View File

@@ -244,6 +244,22 @@ bool Lexer::is_numeric_literal_start() const
return isdigit(m_current_char) || (m_current_char == '.' && m_position < m_source.length() && isdigit(m_source[m_position]));
}
bool Lexer::slash_means_division() const
{
auto type = m_current_token.type();
return type == TokenType::BoolLiteral
|| type == TokenType::BracketClose
|| type == TokenType::CurlyClose
|| type == TokenType::Identifier
|| type == TokenType::NullLiteral
|| type == TokenType::NumericLiteral
|| type == TokenType::ParenClose
|| type == TokenType::RegexLiteral
|| type == TokenType::StringLiteral
|| type == TokenType::TemplateLiteralEnd
|| type == TokenType::This;
}
Token Lexer::next()
{
size_t trivia_start = m_position;
@@ -277,7 +293,11 @@ Token Lexer::next()
size_t value_start = m_position;
auto token_type = TokenType::Invalid;
if (m_current_char == '`') {
if (m_current_token.type() == TokenType::RegexLiteral && !is_eof() && isalpha(m_current_char)) {
token_type = TokenType::RegexFlags;
while (!is_eof() && isalpha(m_current_char))
consume();
} else if (m_current_char == '`') {
consume();
if (!in_template) {
@@ -452,6 +472,28 @@ Token Lexer::next()
if (!found_four_char_token && !found_three_char_token && !found_two_char_token && !found_one_char_token) {
consume();
token_type = TokenType::Invalid;
} else if (token_type == TokenType::Slash && !slash_means_division()) {
token_type = TokenType::RegexLiteral;
while (!is_eof()) {
if (m_current_char == '[') {
m_regex_is_in_character_class = true;
} else if (m_current_char == ']') {
m_regex_is_in_character_class = false;
} else if (!m_regex_is_in_character_class && m_current_char == '/') {
break;
}
if (match('\\', '/') || match('\\', '[') || (m_regex_is_in_character_class && match('\\', ']')))
consume();
consume();
}
if (is_eof()) {
token_type = TokenType::UnterminatedRegexLiteral;
} else {
consume();
}
}
}