fix: improve HTML layer detection, various MD fixes (#1241)

Markdown fixes:
- properly propagate section header levels
- improve handling of list subroots without text

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

docling/backend/html_backend.py

@@ -206,9 +206,9 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         hlevel = int(element.name.replace("h", ""))
         text = element.text.strip()
 
-        if hlevel == 1:
-            self.content_layer = ContentLayer.BODY
+        self.content_layer = ContentLayer.BODY
 
+        if hlevel == 1:
             for key in self.parents.keys():
                 self.parents[key] = None