RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-25 05:47:35 +00:00
Code Issues Activity Actions

LibRegex: Treat pattern string characters as unsigned

Browse source 
For example, consider the following pattern:

    new RegExp('\ud834\udf06', 'u')

With this pattern, the regex parser should insert the UTF-8 encoded
bytes 0xf0, 0x9d, 0x8c, and 0x86. However, because these characters are
currently treated as normal char types, they have a negative value since
they are all > 0x7f. Then, due to sign extension, when these characters
are cast to u64, the sign bit is preserved. The result is that these
bytes are inserted as 0xfffffffffffffff0, 0xffffffffffffff9d, etc.

Fortunately, there are only a few places where we insert bytecode with
the raw characters. In these places, be sure to treat the bytes as u8
before they are cast to u64.
This commit is contained in:
Timothy Flynn 2021-08-20 10:22:23 -04:00 • committed by Andreas Kling
parent 7c54b6bd45
commit 562d4e497b
3 changed files with 9 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

12
Userland/Libraries/LibRegex/RegexParser.cpp
View file

@ -145,9 +145,9 @@ ALWAYS_INLINE bool Parser::lookahead_any(StringView str)
return false;
}
ALWAYS_INLINE char Parser::skip()
ALWAYS_INLINE unsigned char Parser::skip()
{
char ch;
unsigned char ch;
if (m_parser_state.current_token.value().length() == 1) {
ch = m_parser_state.current_token.value()[0];
} else {
@ -1287,7 +1287,7 @@ bool ECMA262Parser::parse_atom(ByteCode& stack, size_t& match_length_minimum, bo
// Also part of AtomEscape.
auto token = consume();
match_length_minimum += 1;
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (ByteCodeValueType)token.value()[1] } });
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (u8)token.value()[1] } });
return true;
}
if (try_skip("\\")) {
@ -1326,7 +1326,7 @@ bool ECMA262Parser::parse_atom(ByteCode& stack, size_t& match_length_minimum, bo
if (m_should_use_browser_extended_grammar) {
auto token = consume();
match_length_minimum += 1;
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (ByteCodeValueType)token.value()[0] } });
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (u8)token.value()[0] } });
return true;
} else {
return false;
@ -1336,7 +1336,7 @@ bool ECMA262Parser::parse_atom(ByteCode& stack, size_t& match_length_minimum, bo
if (match_ordinary_characters()) {
auto token = consume().value();
match_length_minimum += 1;
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (ByteCodeValueType)token[0] } });
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (u8)token[0] } });
return true;
}
@ -1594,7 +1594,7 @@ bool ECMA262Parser::parse_atom_escape(ByteCode& stack, size_t& match_length_mini
// Allow all SourceCharacter's as escapes here.
auto token = consume();
match_length_minimum += 1;
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (ByteCodeValueType)token.value()[0] } });
stack.insert_bytecode_compare_values({ { CharacterCompareType::Char, (u8)token.value()[0] } });
return true;
}