LibJS: Lex single quote strings, escaped chars and unterminated strings
This commit is contained in:
parent
d439013903
commit
c0e6234219
Notes:
sideshowbarker
2024-07-19 08:19:00 +09:00
Author: https://github.com/sunverwerth Commit: https://github.com/SerenityOS/serenity/commit/c0e62342197 Pull-request: https://github.com/SerenityOS/serenity/pull/1451
5 changed files with 33 additions and 4 deletions
7
Base/home/anon/js/strings.js
Normal file
7
Base/home/anon/js/strings.js
Normal file
|
@ -0,0 +1,7 @@
|
|||
var d = "Double quoted string";
|
||||
var s = 'Single quoted string';
|
||||
var e = "Escaped characters \n \" \t \\"
|
||||
var u = "Unterminated string
|
||||
this is not possible in js"
|
||||
|
||||
var u2 = 'This is neither
|
|
@ -169,6 +169,12 @@ bool Lexer::is_block_comment_end() const
|
|||
return m_current_char == '*' && m_position < m_source.length() && m_source[m_position] == '/';
|
||||
}
|
||||
|
||||
void Lexer::syntax_error(const char* msg)
|
||||
{
|
||||
m_has_errors = true;
|
||||
fprintf(stderr, "Syntax Error: %s\n", msg);
|
||||
}
|
||||
|
||||
Token Lexer::next()
|
||||
{
|
||||
size_t trivia_start = m_position;
|
||||
|
@ -218,13 +224,22 @@ Token Lexer::next()
|
|||
consume();
|
||||
}
|
||||
token_type = TokenType::NumericLiteral;
|
||||
} else if (m_current_char == '"') {
|
||||
} else if (m_current_char == '"' || m_current_char == '\'') {
|
||||
char stop_char = m_current_char;
|
||||
consume();
|
||||
while (m_current_char != '"' && !is_eof()) {
|
||||
while (m_current_char != stop_char && m_current_char != '\n' && !is_eof()) {
|
||||
if (m_current_char == '\\') {
|
||||
consume();
|
||||
}
|
||||
consume();
|
||||
}
|
||||
consume();
|
||||
token_type = TokenType::StringLiteral;
|
||||
if (m_current_char != stop_char) {
|
||||
syntax_error("unterminated string literal");
|
||||
token_type = TokenType::UnterminatedStringLiteral;
|
||||
} else {
|
||||
consume();
|
||||
token_type = TokenType::StringLiteral;
|
||||
}
|
||||
} else if (m_current_char == EOF) {
|
||||
token_type = TokenType::Eof;
|
||||
} else {
|
||||
|
|
|
@ -38,6 +38,7 @@ class Lexer {
|
|||
public:
|
||||
explicit Lexer(StringView source);
|
||||
Token next();
|
||||
bool has_errors() const { return m_has_errors; }
|
||||
|
||||
private:
|
||||
void consume();
|
||||
|
@ -48,10 +49,13 @@ private:
|
|||
bool is_block_comment_start() const;
|
||||
bool is_block_comment_end() const;
|
||||
|
||||
void syntax_error(const char*);
|
||||
|
||||
StringView m_source;
|
||||
size_t m_position = 0;
|
||||
Token m_current_token;
|
||||
int m_current_char;
|
||||
bool m_has_errors = false;
|
||||
|
||||
static HashMap<String, TokenType> s_keywords;
|
||||
static HashMap<String, TokenType> s_three_char_tokens;
|
||||
|
|
|
@ -186,6 +186,8 @@ const char* Token::name(TokenType type)
|
|||
return "UnsignedShiftRight";
|
||||
case TokenType::UnsignedShiftRightEquals:
|
||||
return "UnsignedShiftRightEquals";
|
||||
case TokenType::UnterminatedStringLiteral:
|
||||
return "UnterminatedStringLiteral";
|
||||
case TokenType::Var:
|
||||
return "Var";
|
||||
case TokenType::Void:
|
||||
|
|
|
@ -109,6 +109,7 @@ enum class TokenType {
|
|||
Typeof,
|
||||
UnsignedShiftRight,
|
||||
UnsignedShiftRightEquals,
|
||||
UnterminatedStringLiteral,
|
||||
Var,
|
||||
Void,
|
||||
While,
|
||||
|
|
Loading…
Add table
Reference in a new issue