1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 10:58:12 +00:00

LibHTML: Add Comment and CharacterData nodes and improve HTML parsing

This patch adds the CharacterData subclass of Node, which is now the
parent class of Text and a new Comment class.

A Comment node is one of these in HTML: <!--hello friends-->
Since these occur somewhat frequently on the web, we need to be able
to parse them.

This patch also adds a child rejection mechanism to the DOM tree.
Nodes can now override is_child_allowed(Node) and return false if they
don't want a particular Node to become a child of theirs. This is used
to prevent Document from taking on unwanted children.
This commit is contained in:
Andreas Kling 2019-10-12 23:26:47 +02:00
parent 6d150df58a
commit b083a233d8
15 changed files with 158 additions and 25 deletions

View file

@ -29,6 +29,23 @@ StyleResolver& Document::style_resolver()
return *m_style_resolver;
}
bool Document::is_child_allowed(const Node& node) const
{
switch (node.type()) {
case NodeType::DOCUMENT_NODE:
case NodeType::TEXT_NODE:
return false;
case NodeType::COMMENT_NODE:
return true;
case NodeType::DOCUMENT_TYPE_NODE:
return !first_child_of_type<DocumentType>();
case NodeType::ELEMENT_NODE:
return !first_child_of_type<Element>();
default:
return false;
}
}
void Document::fixup()
{
if (!is<DocumentType>(first_child()))