Update app.py

app.py

@@ -602,6 +602,80 @@ Contract data in JSON format:""" + f"""
     
     return json.dumps(empty_json, ensure_ascii=False, indent=4)
 
+def handle_weight_conversion_edge_case(transformed_data):
+    """
+    Handles the edge case where converted weight is in '其他' field.
+    If found, replaces quantity and unit with the converted weight values.
+    Extracts unit from the bracket in the column header.
+    """
+    for row in transformed_data:
+        if "其他" not in row or not isinstance(row["其他"], dict):
+            continue
+            
+        other_fields = row["其他"]
+        
+        # Look for weight conversion column with various possible names
+        weight_key = None
+        weight_patterns = [
+            r"换算重量（吨）",
+            r"converted weight（t）",
+            r"换算重量",
+            r"converted weight",
+            r"重量换算",
+            r"weight conversion"
+        ]
+        
+        for key in other_fields:
+            # Check if any pattern is contained within the key
+            if any(re.search(pattern, key, re.IGNORECASE) for pattern in weight_patterns):
+                weight_key = key
+                break
+        
+        if weight_key and other_fields[weight_key]:
+            try:
+                # Try to convert to float to ensure it's a valid number
+                weight_value = float(other_fields[weight_key])
+                
+                # Only replace if the weight value is valid
+                if weight_value > 0:
+                    # Store original values in case we need to revert
+                    original_quantity = row.get("数量", "")
+                    original_unit = row.get("单位", "")
+                    
+                    # Extract unit from the bracket in the column header
+                    unit = "吨"  # default unit
+                    bracket_match = re.search(r'[（(]([^）)]+)[）)]', weight_key)
+                    if bracket_match:
+                        unit = bracket_match.group(1).strip()
+                        # Clean up the unit (remove any extra text)
+                        unit = re.sub(r'[^a-zA-Z\u4e00-\u9fff]', '', unit)
+                    
+                    # Replace with converted weight
+                    row["数量"] = str(weight_value)
+                    row["单位"] = unit
+                    
+                    # Log the conversion
+                    print(f"Converted weight: {weight_value}{unit} (original: {original_quantity} {original_unit})")
+                    
+                    # Remove the weight field from other_fields
+                    del other_fields[weight_key]
+            except (ValueError, TypeError):
+                # If conversion fails, log and skip
+                print(f"Warning: Invalid weight value '{other_fields[weight_key]}' in row")
+                continue
+    
+    return transformed_data
+
+def handle_edge_cases(transformed_data):
+    """
+    Main function to handle all edge cases in the transformed data.
+    Currently handles:
+    1. Weight conversion from '其他' field
+    """
+    # Handle weight conversion edge case
+    transformed_data = handle_weight_conversion_edge_case(transformed_data)
+    
+    return transformed_data
 
 def extract_price_list(price_list, save_json=False, json_name="price_list.json"):
     """
@@ -971,6 +1045,9 @@ Do not force map 名称(英文) to 单价
 
     # Save to file if requested
     if save_json and transformed_data:
+        # Handle edge cases before saving
+        transformed_data = handle_edge_cases(transformed_data)
+        
         with open(json_name, "w", encoding="utf-8") as f:
             json.dump(transformed_data, f, ensure_ascii=False, indent=4)
         print(f"✅ Saved to {json_name}")
@@ -1090,7 +1167,7 @@ def extract_po(docx_path):
 
 # Example Usage
 
-# extract_po("test-contract-converted.docx")
+# extract_po("GN-WARJS2504-282GC烟台嘉益钢材采购合同(1).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'}]))