Update app.py

app.py

@@ -2368,9 +2368,8 @@ def build_subject_body_map(jsons):
 
 def identify_headers_and_save_excel(pdf_path, model,LLM_prompt):
     try:
-        # result = identify_headers_with_openrouterNEWW(pdf_path, model)
-        jsons,result = testFunction(pdf_path, model,LLM_prompt)
-        print('jsonssss',jsons)
+        jsons, result = testFunction(pdf_path, model,LLM_prompt)
+
         if not result:
             df = pd.DataFrame([{
                 "text": None,
@@ -2380,66 +2379,46 @@ def identify_headers_and_save_excel(pdf_path, model,LLM_prompt):
                 "body": None,
                 "System Message": "No headers were identified by the LLM."
             }])
+
         else:
             print('here')
             df = pd.DataFrame(result)
 
-            # subject_body_map = {}
+            # Convert JSON string to list if needed
+            if isinstance(jsons, str):
+                jsons = json.loads(jsons)
 
-            # for pdf_sections in jsons:
-            #     for obj in pdf_sections:
-            #         subject = obj.get("Subject")
-            #         body = obj.get("BodyText", [])
+            subject_body_map = {}
 
-            #         if subject:
-            #             subject_body_map[subject.strip()] = " ".join(body)
+            # ✅ jsons is a flat list of dicts
+            for obj in jsons:
 
-            # df["body"] = df["text"].map(subject_body_map)
-            subject_body_map = {}
-            
-            def process_obj(obj):
                 if not isinstance(obj, dict):
-                    return
-            
+                    continue
+
                 subject = obj.get("Subject")
                 body = obj.get("BodyText", [])
-            
+
                 if subject:
-                    if isinstance(body, list):
-                        body_text = " ".join(body)
-                    else:
-                        body_text = str(body)
-            
-                    subject_body_map[subject.strip()] = body_text
-            
-            
-            for item in jsons:
-            
-                # Case: flat list of dicts
-                if isinstance(item, dict):
-                    process_obj(item)
-            
-                # Case: nested list
-                elif isinstance(item, list):
-                    for obj in item:
-                        process_obj(obj)
-            
-        
+                    subject_body_map[subject.strip()] = " ".join(body)
+
+            # ✅ Map body to dataframe
             df["body"] = df["text"].map(subject_body_map).fillna("")
-            
-            output_path = os.path.abspath("header_analysis_output.xlsx")
-            df.to_excel(output_path, index=False, engine="openpyxl")
-            
-            print("--- Processed DataFrame ---")
-            print(df)
-            
-            return output_path
 
+        # ✅ Save once at end
+        output_path = os.path.abspath("header_analysis_output.xlsx")
+        df.to_excel(output_path, index=False, engine="openpyxl")
+
+        print("--- Processed DataFrame ---")
+        print(df)
+
+        return output_path
 
     except Exception as e:
         logger.error(f"Critical error in processing: {str(e)}")
         return None
-        
+
+    
 # Improved launch with debug mode enabled
 iface = gr.Interface(
     fn=identify_headers_and_save_excel,