WIP

src/ocr/machine_code_parser.py

@@ -42,6 +42,7 @@ from dataclasses import dataclass, field
 from typing import Optional
 
 from src.pdf.extractor import Token as TextToken
+from src.utils.validators import FieldValidators
 
 
 @dataclass
@@ -484,21 +485,42 @@ class MachineCodeParser:
         def format_account(account_digits: str) -> tuple[str, str]:
             """Format account and determine type (bankgiro or plusgiro).
 
+            Uses context keywords first, then falls back to Luhn validation
+            to determine the most likely account type.
+
             Returns: (formatted_account, account_type)
             """
             if is_plusgiro_context:
-                # Plusgiro format: XXXXXXX-X
+                # Context explicitly indicates Plusgiro
                 formatted = f"{account_digits[:-1]}-{account_digits[-1]}"
                 return formatted, 'plusgiro'
+
+            # No explicit context - use Luhn validation to determine type
+            # Try both formats and see which passes Luhn check
+
+            # Format as Plusgiro: XXXXXXX-X (all digits, check digit at end)
+            pg_formatted = f"{account_digits[:-1]}-{account_digits[-1]}"
+            pg_valid = FieldValidators.is_valid_plusgiro(account_digits)
+
+            # Format as Bankgiro: XXX-XXXX or XXXX-XXXX
+            if len(account_digits) == 7:
+                bg_formatted = f"{account_digits[:3]}-{account_digits[3:]}"
+            elif len(account_digits) == 8:
+                bg_formatted = f"{account_digits[:4]}-{account_digits[4:]}"
             else:
-                # Bankgiro format: XXX-XXXX or XXXX-XXXX
-                if len(account_digits) == 7:
-                    formatted = f"{account_digits[:3]}-{account_digits[3:]}"
-                elif len(account_digits) == 8:
-                    formatted = f"{account_digits[:4]}-{account_digits[4:]}"
-                else:
-                    formatted = account_digits
-                return formatted, 'bankgiro'
+                bg_formatted = account_digits
+            bg_valid = FieldValidators.is_valid_bankgiro(account_digits)
+
+            # Decision logic:
+            # 1. If only one format passes Luhn, use that
+            # 2. If both pass or both fail, default to Bankgiro (more common in payment lines)
+            if pg_valid and not bg_valid:
+                return pg_formatted, 'plusgiro'
+            elif bg_valid and not pg_valid:
+                return bg_formatted, 'bankgiro'
+            else:
+                # Both valid or both invalid - default to bankgiro
+                return bg_formatted, 'bankgiro'
 
         # Try primary pattern
         match = self.PAYMENT_LINE_PATTERN.search(raw_line)