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.

1 files changed, 17 insertions, 0 deletions

diff --git a/Libraries/LibHTML/DOM/Document.cpp b/Libraries/LibHTML/DOM/Document.cpp
index 8b4af6a0bd..4262bca329 100644
--- a/Libraries/LibHTML/DOM/Document.cpp
+++ b/Libraries/LibHTML/DOM/Document.cpp
@@ -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()))