refac

backend/open_webui/retrieval/utils.py

@@ -197,14 +197,24 @@ def _extract_text_from_binary_response(
         os.remove(tmp_path)
 
 
+TEXT_APPLICATION_CONTENT_TYPES = {
+    'application/javascript',
+    'application/json',
+    'application/xml',
+    'application/x-javascript',
+}
+
+
 def _is_text_content_type(content_type: str) -> bool:
     """Return True if the content type should be handled by the web loader."""
     ct = content_type.split(';')[0].strip().lower()
+    if not ct:
+        return True
     if ct.startswith('text/'):
         return True
-    if any(t in ct for t in ['xml', 'json', 'javascript']):
+    if ct in TEXT_APPLICATION_CONTENT_TYPES:
         return True
-    return not ct  # empty / missing → assume HTML
+    return ct.endswith(('+xml', '+json'))
 
 
 async def get_content_from_url(request, url: str) -> str: