RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-26 07:07:45 +00:00
Code Issues Activity Actions

LibJS: Use GenericLexer to consume escaped code points

Browse source
This commit is contained in:
Timothy Flynn 2021-08-17 22:24:17 -04:00 • committed by Andreas Kling
parent fd8ccedf2b
commit dd44a5e948
1 changed files with 17 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

69
Userland/Libraries/LibJS/Token.cpp
View file

@ -10,7 +10,6 @@
#include <AK/CharacterTypes.h>
#include <AK/GenericLexer.h>
#include <AK/StringBuilder.h>
#include <AK/Utf16View.h>
namespace JS {
@ -103,16 +102,6 @@ String Token::string_value(StringValueStatus& status) const
return {};
};
auto decode_surrogate = [&lexer]() -> Optional<u16> {
u16 surrogate = 0;
for (int j = 0; j < 4; ++j) {
if (!lexer.next_is(is_ascii_hex_digit))
return {};
surrogate = (surrogate << 4u) | hex2int(lexer.consume());
}
return surrogate;
};
StringBuilder builder;
while (!lexer.is_eof()) {
// No escape, consume one char and continue
@ -121,6 +110,23 @@ String Token::string_value(StringValueStatus& status) const
continue;
}
// Unicode escape
if (lexer.next_is("\\u"sv)) {
auto code_point_or_error = lexer.consume_escaped_code_point();
if (code_point_or_error.is_error()) {
switch (code_point_or_error.error()) {
case GenericLexer::UnicodeEscapeError::MalformedUnicodeEscape:
return encoding_failure(StringValueStatus::MalformedUnicodeEscape);
case GenericLexer::UnicodeEscapeError::UnicodeEscapeOverflow:
return encoding_failure(StringValueStatus::UnicodeEscapeOverflow);
}
}
builder.append_code_point(code_point_or_error.value());
continue;
}
lexer.ignore();
VERIFY(!lexer.is_eof());
@ -150,47 +156,6 @@ String Token::string_value(StringValueStatus& status) const
builder.append_code_point(code_point);
continue;
}
// Unicode escape
if (lexer.next_is('u')) {
lexer.ignore();
u32 code_point = 0;
if (lexer.next_is('{')) {
lexer.ignore();
while (true) {
if (!lexer.next_is(is_ascii_hex_digit))
return encoding_failure(StringValueStatus::MalformedUnicodeEscape);
auto new_code_point = (code_point << 4u) | hex2int(lexer.consume());
if (new_code_point < code_point)
return encoding_failure(StringValueStatus::UnicodeEscapeOverflow);
code_point = new_code_point;
if (lexer.next_is('}'))
break;
}
lexer.ignore();
} else {
auto high_surrogate = decode_surrogate();
if (!high_surrogate.has_value())
return encoding_failure(StringValueStatus::MalformedUnicodeEscape);
if (Utf16View::is_high_surrogate(*high_surrogate) && lexer.consume_specific("\\u"sv)) {
auto low_surrogate = decode_surrogate();
if (!low_surrogate.has_value())
return encoding_failure(StringValueStatus::MalformedUnicodeEscape);
if (Utf16View::is_low_surrogate(*low_surrogate)) {
code_point = Utf16View::decode_surrogate_pair(*high_surrogate, *low_surrogate);
} else {
builder.append_code_point(*high_surrogate);
code_point = *low_surrogate;
}
} else {
code_point = *high_surrogate;
}
}
builder.append_code_point(code_point);
continue;
}
// In non-strict mode LegacyOctalEscapeSequence is allowed in strings:
// https://tc39.es/ecma262/#sec-additional-syntax-string-literals