Vladt-Tempest commited on
Commit
c60dd86
·
1 Parent(s): 3744149

Eliminación de carácteres no válidos en campo "Product_desc"

Browse files
Files changed (1) hide show
  1. commercial_invoice.py +5 -1
commercial_invoice.py CHANGED
@@ -151,7 +151,11 @@ def process_product_line(text, invoice_number):
151
  break
152
  product_desc.append(parts[current_idx])
153
  current_idx += 1
154
- product_data["Product_desc"] = " ".join(product_desc) if product_desc else ""
 
 
 
 
155
 
156
  # Número de tarifa
157
  if current_idx < len(parts):
 
151
  break
152
  product_desc.append(parts[current_idx])
153
  current_idx += 1
154
+
155
+ # Unir la descripción y limpiar caracteres no alfanuméricos del inicio
156
+ raw_desc = " ".join(product_desc) if product_desc else ""
157
+ cleaned_desc = re.sub(r'^[^a-zA-Z0-9]+', '', raw_desc).strip()
158
+ product_data["Product_desc"] = cleaned_desc
159
 
160
  # Número de tarifa
161
  if current_idx < len(parts):