Fix HIX value diff when page content has nested tags

integreat_cms/cms/views/utils/hix.py

@@ -42,7 +42,7 @@ def normalize_text(text: str) -> str:
         root = fromstring(text)
 
         # Remove paragraphs without text (e.g. empty paragraphs or with an image only)
-        for node in root.iter():
+        for node in list(root):
             node_text = node.text_content()
             if not node_text or not node_text.strip():
                 node.getparent().remove(node)

integreat_cms/release_notes/current/unreleased/2652.yml

@@ -0,0 +1,2 @@
+en: Fix HIX value diff when page content has nested tags
+de: Behebe HIX-Wert-Differenz, wenn Seiteninhalt verschachtelte Tags hat

tests/textlab_api/textlab_config.py

@@ -8,8 +8,8 @@
         "<p><strong>One</strong> paragraph</p>",
     ),
     (
-        "<p>One paragraph</p><p>&nbsp;&nbsp;</p><p>&nbsp;</p>",
-        "<p>One paragraph</p>",
+        "<p><strong>One</strong> paragraph</p><p>&nbsp;&nbsp;</p><p>&nbsp;</p>",
+        "<p><strong>One</strong> paragraph</p>",
     ),
     (
         "<div><p>One paragraph</p></div>",
@@ -56,7 +56,7 @@
         '<p><a href="some.url">Some link</a></p>',
     ),
     (
-        '<div><p>Some image</p><p><a href="some.image"><img src="some.image" alt=""></a></p></div>',
+        '<div><p>Some image</p><p><a href="some.image"><img src="some.image" alt=""></a></p><p>&nbsp;</p></div>',
         "<p>Some image</p>",
     ),
     (