mirrors/ladybird
0
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2025-09-13 13:02:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

LibJS: Extract some JS lexer helpers to free functions

Browse source 
We will need these in an upcoming proposal.
This commit is contained in:
Timothy Flynn 2024-12-04 16:41:02 -05:00 • committed by Jelle Raaijmakers
commit bd1009f3c1
Notes: github-actions[bot] 2024-12-05 12:57:21 +00:00
2 changed files with 45 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

47
Libraries/LibJS/Lexer.cpp
View file

@ -481,13 +481,13 @@ bool Lexer::is_eof() const
ALWAYS_INLINE bool Lexer::is_line_terminator() const ALWAYS_INLINE bool Lexer::is_line_terminator() const
{ {
// OPTIMIZATION: Fast-path for ASCII characters.
if (m_current_char == '\n' || m_current_char == '\r') if (m_current_char == '\n' || m_current_char == '\r')
return true; return true;
if (!is_unicode_character()) if (!is_unicode_character())
return false; return false;
auto code_point = current_code_point(); return JS::is_line_terminator(current_code_point());
return code_point == LINE_SEPARATOR || code_point == PARAGRAPH_SEPARATOR;
} }
ALWAYS_INLINE bool Lexer::is_unicode_character() const ALWAYS_INLINE bool Lexer::is_unicode_character() const
@ -511,14 +511,13 @@ ALWAYS_INLINE u32 Lexer::current_code_point() const
bool Lexer::is_whitespace() const bool Lexer::is_whitespace() const
{ {
// OPTIMIZATION: Fast-path for ASCII characters.
if (is_ascii_space(m_current_char)) if (is_ascii_space(m_current_char))
return true; return true;
if (!is_unicode_character()) if (!is_unicode_character())
return false; return false;
auto code_point = current_code_point();
if (code_point == NO_BREAK_SPACE || code_point == ZERO_WIDTH_NO_BREAK_SPACE) return JS::is_whitespace(current_code_point());
return true;
return Unicode::code_point_has_space_separator_general_category(code_point);
} }
// UnicodeEscapeSequence :: https://tc39.es/ecma262/#prod-UnicodeEscapeSequence // UnicodeEscapeSequence :: https://tc39.es/ecma262/#prod-UnicodeEscapeSequence
@ -1059,4 +1058,40 @@ TokenType Lexer::consume_regex_literal()
return TokenType::UnterminatedRegexLiteral; return TokenType::UnterminatedRegexLiteral;
} }
// https://tc39.es/ecma262/#prod-SyntaxCharacter
bool is_syntax_character(u32 code_point)
{
// SyntaxCharacter :: one of
// ^ $ \ . * + ? ( ) [ ] { } |
static constexpr Utf8View syntax_characters { "^$\\.*+?()[]{}|"sv };
return syntax_characters.contains(code_point);
}
// https://tc39.es/ecma262/#prod-WhiteSpace
bool is_whitespace(u32 code_point)
{
// WhiteSpace ::
// <TAB>
// <VT>
// <FF>
// <ZWNBSP>
// <USP>
if (is_ascii_space(code_point))
return true;
if (code_point == NO_BREAK_SPACE || code_point == ZERO_WIDTH_NO_BREAK_SPACE)
return true;
return Unicode::code_point_has_space_separator_general_category(code_point);
}
// https://tc39.es/ecma262/#prod-LineTerminator
bool is_line_terminator(u32 code_point)
{
// LineTerminator ::
// <LF>
// <CR>
// <LS>
// <PS>
return code_point == '\n' || code_point == '\r' || code_point == LINE_SEPARATOR || code_point == PARAGRAPH_SEPARATOR;
}
} }

4
Libraries/LibJS/Lexer.h
View file

@ -91,4 +91,8 @@ private:
RefPtr<ParsedIdentifiers> m_parsed_identifiers; RefPtr<ParsedIdentifiers> m_parsed_identifiers;
}; };
bool is_syntax_character(u32 code_point);
bool is_whitespace(u32 code_point);
bool is_line_terminator(u32 code_point);
} }