Update app.py

app.py

@@ -920,9 +920,11 @@ def extract_po(docx_path):
     # Step 1: Extract XML content from DOCX
     print("Extracting Docs data to XML...")
     xml_filename = os.path.splitext(os.path.basename(docx_path))[0] + "_document.xml"
-    xml_file = extract_docx_as_xml(docx_bytes, save_xml=False, xml_filename=xml_filename)
-    
-    get_namespace(ET.fromstring(xml_file))
+    try:
+        xml_file = extract_docx_as_xml(docx_bytes, save_xml=False, xml_filename=xml_filename)
+        get_namespace(ET.fromstring(xml_file))
+    except (zipfile.BadZipFile, KeyError):
+        raise ValueError(f"Invalid file: {docx_path}")
     
     # Step 2: Extract tables from DOCX and save JSON
     print("Extracting XML data to JSON...")
@@ -974,7 +976,7 @@ def extract_po(docx_path):
 # Example Usage
 
 # extract_po("test-contract-converted.docx")
-# extract_po("test-contracts\GN-SMBLMCD202501-032WJ SMB联盟菜地PVC球阀等五金物资采购合同-ZHUOKE.docx")
+# extract_po("EPC简明合同格式-中英对照版.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'}]))
 
@@ -992,5 +994,4 @@ interface = gr.Interface(
     theme=Base()
 )
 
-interface.launch()
-
+interface.launch(show_error=True)