LibWeb: Implement aborting the HTML parser

This is roughly on-spec, although I had to invent a simple "aborted"
state for the tokenizer.

4 files changed, 33 insertions, 0 deletions

diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.cpp
index 5885c21291..84a960b62d 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.cpp
@@ -3751,4 +3751,25 @@ JS::Realm& HTMLParser::realm()
     return m_document->realm();
 }
 
+// https://html.spec.whatwg.org/multipage/parsing.html#abort-a-parser
+void HTMLParser::abort()
+{
+    // 1. Throw away any pending content in the input stream, and discard any future content that would have been added to it.
+    m_tokenizer.abort();
+
+    // FIXME: 2. Stop the speculative HTML parser for this HTML parser.
+
+    // 3. Update the current document readiness to "interactive".
+    m_document->update_readiness(DocumentReadyState::Interactive);
+
+    // 4. Pop all the nodes off the stack of open elements.
+    while (!m_stack_of_open_elements.is_empty())
+        m_stack_of_open_elements.pop();
+
+    // 5. Update the current document readiness to "complete".
+    m_document->update_readiness(DocumentReadyState::Complete);
+
+    m_aborted = true;
+}
+
 }
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.h b/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.h
index 6838972ba4..861acc4b08 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.h
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLParser.h
@@ -68,7 +68,11 @@ public:
 
     HTMLTokenizer& tokenizer() { return m_tokenizer; }
 
+    // https://html.spec.whatwg.org/multipage/parsing.html#abort-a-parser
+    void abort();
+
     bool aborted() const { return m_aborted; }
+    bool stopped() const { return m_stop_parsing; }
 
     size_t script_nesting_level() const { return m_script_nesting_level; }
 
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
index b5619786bd..5905561f9e 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
@@ -257,6 +257,9 @@ _StartOfFunction:
     if (!m_queued_tokens.is_empty())
         return m_queued_tokens.dequeue();
 
+    if (m_aborted)
+        return {};
+
     for (;;) {
         auto current_input_character = next_code_point();
         switch (m_state) {
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h
index 05f5c5b697..2b0e17e601 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h
@@ -143,6 +143,9 @@ public:
         m_insertion_point.position = m_utf8_view.iterator_offset(m_utf8_iterator);
     }
 
+    // This permanently cuts off the tokenizer input stream.
+    void abort() { m_aborted = true; }
+
 private:
     void skip(size_t count);
     Optional<u32> next_code_point();
@@ -207,6 +210,8 @@ private:
 
     bool m_blocked { false };
 
+    bool m_aborted { false };
+
     Vector<HTMLToken::Position> m_source_positions;
 };