RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 12:48:10 +00:00
Code Issues Activity Actions

LibWeb: Implement a bit more of DOCTYPE tokenization

Browse source
This commit is contained in:
Andreas Kling 2020-05-23 19:56:07 +02:00
parent b5c0703e14
commit e45c8b842c
1 changed files with 71 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

71
Libraries/LibWeb/Parser/HTMLTokenizer.cpp
View file

@ -58,6 +58,9 @@
#define ON_ASCII_ALPHA \ #define ON_ASCII_ALPHA \
if (current_input_character.has_value() && isalpha(current_input_character.value())) if (current_input_character.has_value() && isalpha(current_input_character.value()))
#define ON_ASCII_UPPER_ALPHA \
if (current_input_character.has_value() && current_input_character.value() >= 'A' && current_input_character.value() <= 'Z')
#define ON_WHITESPACE \ #define ON_WHITESPACE \
if (current_input_character.has_value() && (current_input_character.value() == '\t' || current_input_character.value() == '\a' || current_input_character.value() == '\f' || current_input_character.value() == ' ')) if (current_input_character.has_value() && (current_input_character.value() == '\t' || current_input_character.value() == '\a' || current_input_character.value() == '\f' || current_input_character.value() == ' '))
@ -207,6 +210,18 @@ void HTMLTokenizer::run()
{ {
SWITCH_TO(BeforeDOCTYPEName); SWITCH_TO(BeforeDOCTYPEName);
} }
ON('>')
{
RECONSUME_IN(BeforeDOCTYPEName);
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE
{
TODO();
}
} }
END_STATE END_STATE
@ -216,6 +231,24 @@ void HTMLTokenizer::run()
{ {
continue; continue;
} }
ON_ASCII_UPPER_ALPHA
{
create_new_token(HTMLToken::Type::DOCTYPE);
m_current_token.m_doctype.name.append(tolower(current_input_character.value()));
SWITCH_TO(DOCTYPEName);
}
ON(0)
{
TODO();
}
ON('>')
{
TODO();
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE ANYTHING_ELSE
{ {
create_new_token(HTMLToken::Type::DOCTYPE); create_new_token(HTMLToken::Type::DOCTYPE);
@ -227,11 +260,27 @@ void HTMLTokenizer::run()
BEGIN_STATE(DOCTYPEName) BEGIN_STATE(DOCTYPEName)
{ {
ON_WHITESPACE
{
SWITCH_TO(AfterDOCTYPEName);
}
ON('>') ON('>')
{ {
emit_current_token(); emit_current_token();
SWITCH_TO(Data); SWITCH_TO(Data);
} }
ON_ASCII_UPPER_ALPHA
{
m_current_token.m_doctype.name.append(tolower(current_input_character.value()));
}
ON(0)
{
TODO();
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_doctype.name.append(current_input_character.value()); m_current_token.m_doctype.name.append(current_input_character.value());
@ -240,6 +289,28 @@ void HTMLTokenizer::run()
} }
END_STATE END_STATE
BEGIN_STATE(AfterDOCTYPEName)
{
ON_WHITESPACE
{
continue;
}
ON('>')
{
emit_current_token();
SWITCH_TO(Data);
}
ON_EOF
{
TODO();
}
ANYTHING_ELSE
{
TODO();
}
}
END_STATE
BEGIN_STATE(BeforeAttributeName) BEGIN_STATE(BeforeAttributeName)
{ {
ON_WHITESPACE ON_WHITESPACE