Update app.py

app.py

@@ -189,41 +189,42 @@ entities_data = {}
 if text_input and model is not None:
     try:
         if selected_language in ["German", "English - spaCy"]:
-            # Process the text with error handling
+            # Process the text with error handling for spaCy
             doc = model(text_input)
-            
-            # Fixed the syntax error: ent._.kb_qid instead of ent..kb_qid
             entities = []
             for ent in doc.ents:
                 try:
-                    # Check if the custom attributes exist
-                    kb_qid = getattr(ent._, 'kb_qid', None) if hasattr(ent, '_') else None
-                    url_wikidata = getattr(ent._, 'url_wikidata', None) if hasattr(ent, '_') else None
+                    kb_qid = getattr(ent._, 'kb_qid', None)
+                    url_wikidata = getattr(ent._, 'url_wikidata', None)
                     entities.append((ent.text, ent.label_, kb_qid, url_wikidata))
-                except AttributeError as e:
-                    # If the entityfishing attributes don't exist, use basic entity info
+                except AttributeError:
                     entities.append((ent.text, ent.label_, None, None))
                     
-            for entity in entities:
-                entity_string, entity_type, wikidata_id, wikidata_url = entity
+            for entity_string, entity_type, wikidata_id, wikidata_url in entities:
                 if wikidata_url:
-                    # Ensure correct format for the German and English model
-                    formatted_wikidata_url = wikidata_url.replace("https://www.wikidata.org/wiki/", "http://www.wikidata.org/entity/")
-                    entities_map[entity_string] = {"id": wikidata_id, "link": formatted_wikidata_url}
-                    entity_data = get_entity_data(formatted_wikidata_url)
-
-                    if entity_data is not None:
+                    entities_map[entity_string] = {"id": wikidata_id, "link": wikidata_url}
+                    entity_data = get_entity_data(wikidata_url)
+                    if entity_data:
                         entities_data[entity_string] = entity_data
+        
         else:
+            # === CORRECTED ReFinED PROCESSING LOGIC ===
             entities = model.process_text(text_input)
 
+            # Iterate through the entity objects directly and safely
             for entity in entities:
-                single_entity_list = str(entity).strip('][').replace("\'", "").split(', ')
-                if len(single_entity_list) >= 2 and "wikidata" in single_entity_list[1]:
-                    entities_map[single_entity_list[0].strip()] = get_wikidata_id(single_entity_list[1])
-                    entity_data = get_entity_data(entities_map[single_entity_list[0].strip()]["link"])
+                # Check if the entity has a wikidata_id before processing
+                if entity.wikidata_id:
+                    entity_text = entity.text
+                    entity_id = entity.wikidata_id
+                    entity_link = f"http://www.wikidata.org/entity/{entity_id}"
+
+                    # Populate your dictionaries
+                    entities_map[entity_text] = {"id": entity_id, "link": entity_link}
+                    entity_data = get_entity_data(entity_link)
                     if entity_data is not None:
-                        entities_data[single_entity_list[0].strip()] = entity_data
+                        entities_data[entity_text] = entity_data
+
 
     except Exception as e:
         st.error(f"Error processing text: {e}")