Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

css2: Tokenize cdo tokens, and improve escape-sequence handling #1162

Merged
merged 2 commits into from
Jan 23, 2025
+47 −0
Merged

css2: Tokenize cdo tokens, and improve escape-sequence handling #1162

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
95c49f2
css2: Support tokenizing cdo tokens
robinlinden Jan 21, 2025
bb7ff0c
css2: Handle escape sequences more correctly
robinlinden Jan 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions css2/tokenizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,8 @@ std::string_view to_string(ParseError e) {
return "EofInEscapeSequence";
case ParseError::EofInString:
return "EofInString";
case ParseError::InvalidEscapeSequence:
return "InvalidEscapeSequence";
case ParseError::NewlineInString:
return "NewlineInString";
}
Expand Down Expand Up @@ -165,9 +167,27 @@ void Tokenizer::run() {
case ';':
emit(SemiColonToken{});
continue;
case '<':
if (peek_input(0) == '!' && peek_input(1) == '-' && peek_input(2) == '-') {
emit(CdoToken{});
pos_ += 3;
continue;
}

emit(DelimToken{'<'});
continue;
case '[':
emit(OpenSquareToken{});
continue;
case '\\':
if (is_valid_escape_sequence('\\', peek_input(0))) {
reconsume_in(State::IdentLike);
continue;
}

emit(ParseError::InvalidEscapeSequence);
emit(DelimToken{'\\'});
continue;
case ']':
emit(CloseSquareToken{});
continue;
Expand Down
1 change: 1 addition & 0 deletions css2/tokenizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ enum class ParseError : std::uint8_t {
EofInComment,
EofInEscapeSequence,
EofInString,
InvalidEscapeSequence,
NewlineInString,
};

Expand Down
26 changes: 26 additions & 0 deletions css2/tokenizer_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -316,6 +316,7 @@ int main() {
s.add_test("at keyword start, but with bad escape", [](etest::IActions &a) {
auto output = run_tokenizer(a, "@\\\n");
expect_token(output, DelimToken{'@'});
expect_error(output, ParseError::InvalidEscapeSequence);
expect_token(output, DelimToken{'\\'});
expect_token(output, WhitespaceToken{});
});
Expand Down Expand Up @@ -508,6 +509,18 @@ int main() {
expect_token(output, IdentToken{"lol"});
});

s.add_test("<: delim", [](etest::IActions &a) {
auto output = run_tokenizer(a, "<hello");
expect_token(output, DelimToken{'<'});
expect_token(output, IdentToken{"hello"});
});

s.add_test("<: cdo", [](etest::IActions &a) {
auto output = run_tokenizer(a, "<!--lol");
expect_token(output, CdoToken{});
expect_token(output, IdentToken{"lol"});
});

s.add_test("number: ez", [](etest::IActions &a) {
auto output = run_tokenizer(a, "0.25");
expect_token(output, NumberToken{0.25});
Expand Down Expand Up @@ -626,6 +639,19 @@ int main() {
s.add_test("hash token: invalid escape", [](etest::IActions &a) {
auto output = run_tokenizer(a, "#\\\n");
expect_token(output, DelimToken{'#'});
expect_error(output, ParseError::InvalidEscapeSequence);
expect_token(output, DelimToken{'\\'});
expect_token(output, WhitespaceToken{});
});

s.add_test("\\: ident-like", [](etest::IActions &a) {
auto output = run_tokenizer(a, "\\Hallo");
expect_token(output, IdentToken{"Hallo"});
});

s.add_test("\\: invalid escape", [](etest::IActions &a) {
auto output = run_tokenizer(a, "\\\n");
expect_error(output, ParseError::InvalidEscapeSequence);
expect_token(output, DelimToken{'\\'});
expect_token(output, WhitespaceToken{});
});
Expand Down