Update app.py

app.py

@@ -20,9 +20,14 @@ def clean_name(name):
         return ""
     return " ".join(str(name).upper().strip().split())
 
+def normalize_columns(df):
+    """Replace newline characters and extra spaces in column headers."""
+    df.columns = [col.replace("\n", " ").strip() for col in df.columns]
+    return df
+
 def process_employee_data(df):
     """Process employee personal information."""
-    df.columns = [col.strip() for col in df.columns]
+    df = normalize_columns(df)
     
     # Create Employee Name if possible
     if 'First Name' in df.columns and 'Last Name' in df.columns:
@@ -43,7 +48,7 @@ def process_employee_data(df):
 
 def process_salary_data(df):
     """Process salary and deductions data."""
-    df.columns = [col.strip() for col in df.columns]
+    df = normalize_columns(df)
     
     if 'TIN' in df.columns:
         df['TIN'] = df['TIN'].apply(standardize_tin)
@@ -52,7 +57,6 @@ def process_salary_data(df):
     else:
         raise KeyError("Salary data must contain a 'TIN' or 'TIN or Personal ID of Employee' column.")
     
-    # Convert numeric columns and fill NaNs with 0
     numeric_columns = df.select_dtypes(include=[np.number]).columns
     df[numeric_columns] = df[numeric_columns].fillna(0)
     
@@ -60,7 +64,7 @@ def process_salary_data(df):
 
 def process_paye_data(df):
     """Process PAYE data."""
-    df.columns = [col.strip() for col in df.columns]
+    df = normalize_columns(df)
     
     if 'TIN' in df.columns:
         df['TIN'] = df['TIN'].apply(standardize_tin)