RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-26 05:17:34 +00:00
Code Issues Activity Actions

LibWeb: Start building the tree building part of the new HTML parser

Browse source 
This patch adds a new HTMLDocumentParser class. It keeps a tokenizer
object internally and feeds itself with one token at a time from it.

The names and idioms in this class are expressed as closely to the
actual HTML parsing spec as possible, to make development as easy
and bug free as possible. :^)

This is going to become pretty large, but it's pretty cool!
This commit is contained in:
Andreas Kling 2020-05-24 00:14:23 +02:00
parent 0b61e21873
commit fd1b31d0ff
8 changed files with 515 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

19
Userland/ht.cpp
View file

@ -24,13 +24,19 @@
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <LibWeb/Parser/HTMLTokenizer.h>
#include <LibCore/File.h>
#include <AK/ByteBuffer.h>
#include <AK/LogStream.h>
#include <LibCore/EventLoop.h>
#include <LibCore/File.h>
#include <LibWeb/DOM/Document.h>
#include <LibWeb/Dump.h>
#include <LibWeb/Parser/HTMLDocumentParser.h>
#include <LibWeb/Parser/HTMLTokenizer.h>
int main(int argc, char** argv)
{
Core::EventLoop loop;
// This is a temporary test program to aid with bringing up the new HTML parser. :^)
const char* input_path = "/home/anon/www/simple.html";
if (argc > 1)
@ -40,7 +46,12 @@ int main(int argc, char** argv)
if (file_or_error.is_error())
return 1;
auto contents = file_or_error.value()->read_all();
Web::HTMLTokenizer tokenizer(contents);
tokenizer.run();
Web::HTMLDocumentParser parser(contents);
parser.run();
auto& document = parser.document();
Web::dump_tree(document);
return 0;
}