OCR Template mapping done Now lets work on user and permission modules

docengine/app/utils/sanitizers.py

@@ -1,5 +1,7 @@
 import re
-from typing import Optional, Union
+from typing import Optional
+from datetime import datetime
+from dateutil import parser
 
 def sanitize_amount(text: str) -> Optional[float]:
     """
@@ -31,3 +33,30 @@ def sanitize_amount(text: str) -> Optional[float]:
         return float(cleaned_text)
     except ValueError:
         return None
+
+def sanitize_date(text: str, field_type: str = 'DATE') -> Optional[str]:
+    """
+    Sanitizes a string representing a date or datetime and converts it to ISO 8601 format.
+    
+    Args:
+        text (str): The raw extracted text from the document.
+        field_type (str): 'DATE' or 'DATETIME'. Determines the output format.
+        
+    Returns:
+        Optional[str]: The sanitized date string in ISO format, or None if it could not be parsed.
+    """
+    if not text:
+        return None
+        
+    try:
+        # dateutil.parser is very robust at handling formats like "Dec 11, 2020", "11/12/2020", etc.
+        # fuzzy=True allows it to ignore extra words/characters around the date
+        parsed_date = parser.parse(text, fuzzy=True)
+        
+        if field_type == 'DATETIME':
+            return parsed_date.strftime('%Y-%m-%dT%H:%M:%S')
+        else:
+            return parsed_date.strftime('%Y-%m-%d')
+    except (ValueError, TypeError, OverflowError):
+        return None
+