Merged in feature/fix_string_utils (pull request #482)

Enhance is_empty function to handle pandas Series and improve empty value checks

* Enhance is_empty function to handle pandas Series and improve empty value checks

* Enhance is_empty function to support pandas Series and add pd_mask parameter for flexible empty checks


Approved-by: Katon Minhas

fieldExtraction/src/utils/string_utils.py

@@ -284,23 +284,32 @@ def count_reimbursements_in_exhibit(exhibit_text: str) -> int: #JUST by regex
     """
     return len(re.findall(reimb_regex, exhibit_text))
 
-def is_empty(value):
+def is_empty(value, pd_mask=True):
     """
     Checks if a value is considered empty or invalid.
 
     Args:
         value: The value to check.
+        Can be a string, list, or pandas Series.
+        pd_mask (bool): Only relevant for Series inputs. 
+            If True, returns a mask for empty values in a pandas Series. 
+            Otherwise, the function returns True iff the entire Series is empty.
 
     Returns:
         bool: True if the value is empty or invalid, False otherwise.
     """
+    empty_values = [None, "", "N/A", "NA", "null", "none", "NaN", np.nan, "nan", "None"]
+    
     if isinstance(value, list):  # Handle list inputs
         return not value or all(is_empty(v) for v in value)
-        
+    
+    # if it's a pd.Series, return the mask (True for empty values)
+    if isinstance(value, pd.Series):
+        return value.isna() | (value.isin(empty_values)) if pd_mask else value.isna().all()
+
     if pd.isna(value):
         return True
     else:
-        empty_values = [None, "", "N/A", "NA", "null", "none", "NaN", np.nan, "nan", "None"]
         return value in empty_values