mirrors/ladybird
0
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2025-05-09 20:52:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

LibWeb: Teach HTMLTokenizer how to tokenize comments

Browse source 
We can now correctly tokenize the welcome.html test page. :^)
This commit is contained in:
Andreas Kling 2020-05-23 01:54:26 +02:00
parent 909ac2a558
commit a58500fdc5
Notes: sideshowbarker 2024-07-19 06:13:48 +09:00
1 changed files with 196 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

196
Libraries/LibWeb/Parser/HTMLTokenizer.cpp
View file

@ -171,6 +171,11 @@ void HTMLTokenizer::run()
BEGIN_STATE(MarkupDeclarationOpen)
{
DONT_CONSUME_NEXT_INPUT_CHARACTER;
if (next_few_characters_are("--")) {
consume("--");
create_new_token(HTMLToken::Type::Comment);
SWITCH_TO(CommentStart);
}
if (next_few_characters_are("DOCTYPE")) {
consume("DOCTYPE");
SWITCH_TO(DOCTYPE);
@ -424,6 +429,197 @@ void HTMLTokenizer::run()
}
END_STATE
BEGIN_STATE(CommentStart)
{
ON('-')
{
SWITCH_TO(CommentStartDash);
}
ON('>')
{
TODO();
}
ANYTHING_ELSE
{
RECONSUME_IN(Comment);
}
}
END_STATE
BEGIN_STATE(CommentStartDash)
{
ON('-')
{
SWITCH_TO(CommentEnd);
}
ON('>')
{
TODO();
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE
{
m_current_token.m_comment_or_character.data.append('-');
RECONSUME_IN(Comment);
}
}
END_STATE
BEGIN_STATE(Comment)
{
ON('<')
{
m_current_token.m_comment_or_character.data.append(current_input_character.value());
SWITCH_TO(CommentLessThanSign);
}
ON('-')
{
SWITCH_TO(CommentEndDash);
}
ON(0)
{
TODO();
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE
{
m_current_token.m_comment_or_character.data.append(current_input_character.value());
continue;
}
}
BEGIN_STATE(CommentEnd)
{
ON('>')
{
emit_current_token();
SWITCH_TO(Data);
}
ON('!')
{
SWITCH_TO(CommentEndBang);
}
ON('-')
{
m_current_token.m_comment_or_character.data.append('-');
continue;
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE
{
m_current_token.m_comment_or_character.data.append('-');
RECONSUME_IN(Comment);
}
}
END_STATE
BEGIN_STATE(CommentEndBang)
{
ON('-')
{
m_current_token.m_comment_or_character.data.append("--!");
SWITCH_TO(CommentEndDash);
}
ON('>')
{
TODO();
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE
{
m_current_token.m_comment_or_character.data.append("--!");
RECONSUME_IN(Comment);
}
}
END_STATE
BEGIN_STATE(CommentEndDash)
{
ON('-')
{
SWITCH_TO(CommentEnd);
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE
{
m_current_token.m_comment_or_character.data.append('-');
RECONSUME_IN(Comment);
}
}
BEGIN_STATE(CommentLessThanSign)
{
ON('!')
{
m_current_token.m_comment_or_character.data.append(current_input_character.value());
SWITCH_TO(CommentLessThanSignBang);
}
ON('<')
{
m_current_token.m_comment_or_character.data.append(current_input_character.value());
continue;
}
ANYTHING_ELSE
{
RECONSUME_IN(Comment);
}
}
END_STATE
BEGIN_STATE(CommentLessThanSignBang)
{
ON('-')
{
SWITCH_TO(CommentLessThanSignBangDash);
}
ANYTHING_ELSE
{
RECONSUME_IN(Comment);
}
}
END_STATE
BEGIN_STATE(CommentLessThanSignBangDash)
{
ON('-')
{
SWITCH_TO(CommentLessThanSignBangDashDash);
}
ANYTHING_ELSE
{
RECONSUME_IN(Comment);
}
}
END_STATE
BEGIN_STATE(CommentLessThanSignBangDashDash)
{
ON('>')
{
SWITCH_TO(CommentEnd);
}
ANYTHING_ELSE
{
TODO();
}
}
END_STATE
BEGIN_STATE(CharacterReference)
{
}