Update app.py

app.py

@@ -1133,26 +1133,43 @@ def extract_po(docx_path):
     print("Extracting XML data to JSON...")
     json_filename = os.path.splitext(os.path.basename(docx_path))[0] + "_extracted_data.json"
     extracted_data = xml_to_json(xml_file, save_json=False, json_filename=json_filename)
+
+    # Find and rename the price list table before contract summary processing
+    print("Identifying Price List table...")
+    extracted_data_dict = json.loads(extracted_data)
+    price_list_table = find_price_list_table(extracted_data_dict)
+    
+    # Rename the price list table key
+    if price_list_table:
+        # Find and rename the key containing the price list table
+        for key in list(extracted_data_dict.keys()):
+            if "long_table" in key and extracted_data_dict[key] == price_list_table:
+                extracted_data_dict["price_list"] = extracted_data_dict.pop(key)
+                break
+        # Update the extracted_data string with proper formatting
+        extracted_data = json.dumps(extracted_data_dict, ensure_ascii=False, indent=4)
+    else:
+        print("⚠️ No suitable price list table found!")
+        extracted_data_dict["price_list"] = []
+        extracted_data = json.dumps(extracted_data_dict, ensure_ascii=False, indent=4)
+    
     print(f"✅ Extracted Data: {extracted_data}")
 
+    # Create a copy of the data with only first row of price list for contract summary
+    contract_summary_dict = json.loads(extracted_data)
+    if contract_summary_dict.get("price_list"):
+        contract_summary_dict["price_list"] = [contract_summary_dict["price_list"][0]] if contract_summary_dict["price_list"] else []
+    contract_summary_data = json.dumps(contract_summary_dict, ensure_ascii=False, indent=4)
+
     # Step 3: Process JSON with OpenAI to get structured output
     print("Processing Contract Summary data with AI...")
     contract_summary_filename = os.path.splitext(os.path.basename(docx_path))[0] + "_contract_summary.json"
-    contract_summary = deepseek_extract_contract_summary(extracted_data, save_json=False, json_filename=contract_summary_filename)
+    contract_summary = deepseek_extract_contract_summary(contract_summary_data, save_json=False, json_filename=contract_summary_filename)
     
-    # Find the last long table (excluding summary tables)
+    # Process the price list
     print("Processing Price List data with AI...")
-    extracted_data_dict = json.loads(extracted_data)
-    price_list_table = find_price_list_table(extracted_data_dict)
-    if not price_list_table:
-        print("⚠️ No suitable price list table found!")
-        price_list_table = []
-
-    # Generate the price list filename in the same folder as the document
     price_list_filename = os.path.join(os.path.dirname(docx_path), os.path.splitext(os.path.basename(docx_path))[0] + "_price_list.json")
-    
-    # Process the price list and save it to a JSON file
-    price_list = extract_price_list(price_list_table, save_json=True, json_name=price_list_filename)
+    price_list = extract_price_list(price_list_table, save_json=False, json_name=price_list_filename)
 
     # Step 4: Combine contract summary and long table data into a single JSON object
     print("Combining AI Generated JSON with Extracted Data...")
@@ -1180,7 +1197,7 @@ def extract_po(docx_path):
 # Example Usage
 
 # extract_po("test-contracts\GN-SMB268202501-042WJ SMB268波纹管采购合同-东营顺航.docx")
-# extract_po("EPC简明合同格式-中英对照版.docx")
+#extract_po("UAT Contracts\GN-WCIE2025-WCSP-276BJ-稳定土拌合机配件-合同.docx")
 
 # print(extract_price_list([{'序号 No.': '1', '名称 Name': 'PE波纹管(双壁波纹管） PE corrugated pipe (double wall corrugated pipe)', '规格 Specification': '内径600mm,6米/根，SN8 Inner diameter 600mm, 6 meters per piece, SN8', '单位 Unit': '米m', '数量 Quantity': '180', '单价（元） Unit Price (CNY)': '106.00', '总额（元） Total Amount (CNY)': '1080.00', '几郎单价（元） Unit Price (GNF)': '16.21', '几郎总额（元） Total Amount (GNF)': '22118.38', '品牌 Brand': '鹏洲PZ', '计划来源 Planned Source': 'SMB268-GNHY-0021-WJ-20250108'}]))