From e45c8b842c64bef30286ac3a34fc5385d1308a9f Mon Sep 17 00:00:00 2001
From: Andreas Kling <kling@serenityos.org>
Date: Sat, 23 May 2020 19:56:07 +0200
Subject: [PATCH] LibWeb: Implement a bit more of DOCTYPE tokenization

---
 Libraries/LibWeb/Parser/HTMLTokenizer.cpp | 71 +++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/Libraries/LibWeb/Parser/HTMLTokenizer.cpp b/Libraries/LibWeb/Parser/HTMLTokenizer.cpp
index 39e3f8b5947..b5835446d39 100644
--- a/Libraries/LibWeb/Parser/HTMLTokenizer.cpp
+++ b/Libraries/LibWeb/Parser/HTMLTokenizer.cpp
@@ -58,6 +58,9 @@
 #define ON_ASCII_ALPHA \
     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 \
     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);
                 }
+                ON('>')
+                {
+                    RECONSUME_IN(BeforeDOCTYPEName);
+                }
+                ON_EOF
+                {
+                    TODO();
+                }
+                ANYTHING_ELSE
+                {
+                    TODO();
+                }
             }
             END_STATE
 
@@ -216,6 +231,24 @@ void HTMLTokenizer::run()
                 {
                     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
                 {
                     create_new_token(HTMLToken::Type::DOCTYPE);
@@ -227,11 +260,27 @@ void HTMLTokenizer::run()
 
             BEGIN_STATE(DOCTYPEName)
             {
+                ON_WHITESPACE
+                {
+                    SWITCH_TO(AfterDOCTYPEName);
+                }
                 ON('>')
                 {
                     emit_current_token();
                     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
                 {
                     m_current_token.m_doctype.name.append(current_input_character.value());
@@ -240,6 +289,28 @@ void HTMLTokenizer::run()
             }
             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)
             {
                 ON_WHITESPACE