Merged in bugfix/uom (pull request #661)

Bugfix/uom

* Add "Per Procedure" to valid unit of measure list

* Enhance unit of measure prompt for clarity and specificity in reimbursement methodologies

* Refine unit of measure prompt to ensure defaulting to 'Per Unit' regardless of procedure codes for flat rate methodologies

* Merge remote-tracking branch 'origin/main' into bugfix/uom

* Merged main into bugfix/uom

* Enhance logic for setting UNIT_OF_MEASURE to 'Per Unit' for Flat Rate reimbursement, handling all edge cases including NaN and empty strings.

* Enhance is_empty function to handle additional empty value cases for pd.Series and strings

* Enhance test cases for is_empty function to cover additional whitespace and null-like values

* Merge branch 'bugfix/uom' of https://bitbucket.org/aarete/doczy.ai into bugfix/uom

* Enhance type checking for is_empty function with overloads for str, list, and pd.Series

* Overload fix

* Merged main into bugfix/uom


Approved-by: Katon Minhas

fieldExtraction/src/utils/string_utils.py

@@ -7,6 +7,8 @@ from datetime import datetime
 import numpy as np
 import pandas as pd
 
+from typing import overload, Literal
+
 from constants.delimiters import Delimiter
 from constants.regex_patterns import (
     BACKTICK_PATTERN,
@@ -295,6 +297,23 @@ def count_reimbursements_in_exhibit(exhibit_text: str) -> int:  # JUST by regex
     return len(re.findall(reimb_regex, exhibit_text))
 
 
+# Overloads for type checking
+@overload
+def is_empty(value: str, pd_mask: bool = True) -> bool: ...
+
+
+@overload
+def is_empty(value: list, pd_mask: bool = True) -> bool: ...
+
+
+@overload
+def is_empty(value: pd.Series, pd_mask: Literal[True] = True) -> pd.Series: ...
+
+
+@overload
+def is_empty(value: pd.Series, pd_mask: Literal[False]) -> bool: ...
+
+
 def is_empty(value: str | list | pd.Series, pd_mask: bool = True) -> bool | pd.Series:
     """
     Checks if a value is considered empty or invalid.
@@ -321,14 +340,32 @@ def is_empty(value: str | list | pd.Series, pd_mask: bool = True) -> bool | pd.S
 
     # 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_mask:
+            return (
+                value.isna()
+                | (value.isin(empty_values))
+                | (value.astype(str).str.strip() == "")
+                | (
+                    value.astype(str)
+                    .str.lower()
+                    .str.strip()
+                    .isin(["n/a", "na", "null", "none", "nan"])
+                )
+            )
+        else:
+            return value.isna().all()
 
     if pd.isna(value):
         return True
-    else:
-        return value in empty_values
+
+    if isinstance(value, str):
+        if not value or value.isspace():
+            return True
+        lower_stripped = value.lower().strip()
+        if lower_stripped in ["n/a", "na", "null", "none", "nan"]:
+            return True
+
+    return value in empty_values
 
 
 def datetime_str():