RFC: html: add parse_html

Signed-off-by: Florian Scherf <[email protected]>
lona-web-org · Jul 7, 2023 · fb9dbac · fb9dbac
1 parent d0b50b9
commit fb9dbac
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 12 deletions.
diff --git a/lona/html/__init__.py b/lona/html/__init__.py
@@ -125,13 +125,13 @@
 from lona.html.nodes.scripting import NoScript, Script, Canvas
 from lona.html.nodes.forms.select2 import Select2, Option2
 from lona.html.nodes.web_components import Template, Slot
+from lona.html.parsing import NodeHTMLParser, parse_html
 from lona.html.nodes.forms.select import Select, Option
 from lona.html.nodes.demarcating_edits import Ins, Del
 from lona.html.nodes.svg_and_mathml import Math, SVG
 from lona.events.event_types import *  # NOQA: F403
 from lona.html.nodes.sectioning_root import Body
 from lona.html.nodes.raw_nodes import RawHTML
-from lona.html.parsing import NodeHTMLParser
 from lona.html.widgets import HTML as HTML1
 from lona.html.parsing import HTML as HTML2
 from lona.compat import get_client_version

diff --git a/lona/html/parsing.py b/lona/html/parsing.py
@@ -5,7 +5,7 @@
     tagfind_tolerant,
     HTMLParser,
 )
-from typing import List, Dict
+from typing import List, Dict, cast
 from html import unescape
 import logging
 
@@ -198,11 +198,15 @@ def handle_endtag(self, tag):
         self.set_current_node(self._node.parent)
 
 
-def html_string_to_node_list(html_string, use_high_level_nodes=True,
-                             node_classes=None):
+def parse_html(
+        html_string: str,
+        use_high_level_nodes: bool = True,
+        node_classes: Dict[str, AbstractNode] | None = None,
+        flat: bool = True,
+) -> AbstractNode | List[AbstractNode]:
 
-    root_node = Node()
-    nodes = []
+    root_node: Node = Node()
+    nodes: List[AbstractNode] = []
 
     html_parser = NodeHTMLParser(
         use_high_level_nodes=use_high_level_nodes,
@@ -221,6 +225,9 @@ def html_string_to_node_list(html_string, use_high_level_nodes=True,
         node.remove()
         nodes.append(node)
 
+    if flat and len(nodes) == 1:
+        return nodes[0]
+
     return nodes
 
 
@@ -230,6 +237,8 @@ def HTML(
         node_classes: Dict[str, AbstractNode] | None = None,
 ) -> AbstractNode:
 
+    # TODO: remove HTML parsing in 2.0
+
     _nodes: List[AbstractNode] = []
 
     for node in nodes:
@@ -243,10 +252,14 @@ def HTML(
 
             # html string
             elif '<' in node or '>' in node:
-                parsed_nodes = html_string_to_node_list(
-                    html_string=node,
-                    use_high_level_nodes=use_high_level_nodes,
-                    node_classes=node_classes or {},
+                parsed_nodes = cast(
+                    list,
+                    parse_html(
+                        html_string=node,
+                        use_high_level_nodes=use_high_level_nodes,
+                        node_classes=node_classes or {},
+                        flat=False,
+                    ),
                 )
 
                 if len(nodes) > 1:

diff --git a/lona/html/widgets.py b/lona/html/widgets.py
@@ -1,5 +1,5 @@
-from lona.html.parsing import html_string_to_node_list
 from lona.html.text_node import TextNode
+from lona.html.parsing import parse_html
 from lona.html.widget import Widget
 
 
@@ -22,10 +22,11 @@ def __init__(self, *nodes, use_high_level_nodes=True, node_classes=None):
                         self.nodes.append(HTML(node))
 
                     else:
-                        self.nodes = html_string_to_node_list(
+                        self.nodes = parse_html(
                             html_string=node,
                             use_high_level_nodes=use_high_level_nodes,
                             node_classes=node_classes or {},
+                            flat=False,
                         )
 
                 else: