d476144565
Some of the code assumed that chars were always signed while that is not the case on ARM hosts. Also, some of the code tried to use EOF (-1) in a way similar to what fgetc() does, however instead of storing the characters in an int variable a char was used. While this seemed to work it also meant that character 0xFF would be incorrectly seen as an end-of-file. Careful reading of fgetc() reveals that fgetc() stores character data in an int where valid characters are in the range of 0-255 and the EOF value is explicitly outside of that range (usually -1).
69 lines
1.8 KiB
C++
69 lines
1.8 KiB
C++
/*
|
|
* Copyright (c) 2020, Stephan Unverwerth <s.unverwerth@serenityos.org>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "Token.h"
|
|
|
|
#include <AK/HashMap.h>
|
|
#include <AK/String.h>
|
|
#include <AK/StringView.h>
|
|
|
|
namespace JS {
|
|
|
|
class Lexer {
|
|
public:
|
|
explicit Lexer(StringView source, StringView filename = "(unknown)", size_t line_number = 1, size_t line_column = 0);
|
|
|
|
Token next();
|
|
|
|
const StringView& source() const { return m_source; };
|
|
const StringView& filename() const { return m_filename; };
|
|
|
|
private:
|
|
void consume();
|
|
bool consume_exponent();
|
|
bool consume_octal_number();
|
|
bool consume_hexadecimal_number();
|
|
bool consume_binary_number();
|
|
bool is_eof() const;
|
|
bool is_line_terminator() const;
|
|
bool is_identifier_start() const;
|
|
bool is_identifier_middle() const;
|
|
bool is_line_comment_start(bool line_has_token_yet) const;
|
|
bool is_block_comment_start() const;
|
|
bool is_block_comment_end() const;
|
|
bool is_numeric_literal_start() const;
|
|
bool match(char, char) const;
|
|
bool match(char, char, char) const;
|
|
bool match(char, char, char, char) const;
|
|
bool slash_means_division() const;
|
|
|
|
StringView m_source;
|
|
size_t m_position { 0 };
|
|
Token m_current_token;
|
|
char m_current_char { 0 };
|
|
bool m_eof { false };
|
|
|
|
StringView m_filename;
|
|
size_t m_line_number { 1 };
|
|
size_t m_line_column { 0 };
|
|
|
|
bool m_regex_is_in_character_class { false };
|
|
|
|
struct TemplateState {
|
|
bool in_expr;
|
|
u8 open_bracket_count;
|
|
};
|
|
Vector<TemplateState> m_template_states;
|
|
|
|
static HashMap<String, TokenType> s_keywords;
|
|
static HashMap<String, TokenType> s_three_char_tokens;
|
|
static HashMap<String, TokenType> s_two_char_tokens;
|
|
static HashMap<char, TokenType> s_single_char_tokens;
|
|
};
|
|
|
|
}
|