import pandas as pd
import os

def merge_and_sort_leads():
    main_csv = 'leads/leads.csv'
    new_unterfranken_csv = 'leads/raw/leads_unterfranken_v2.csv'
    
    # Read existing leads
    if os.path.exists(main_csv):
        df_main = pd.read_csv(main_csv)
    else:
        df_main = pd.DataFrame(columns=["Firm/Innung", "Contact Person", "Email", "Region"])
    
    # Read new Unterfranken leads
    df_uf = pd.read_csv(new_unterfranken_csv)
    
    # Remove old Unterfranken entries from main df
    # We assume 'Region' column exists and is populated correctly
    df_others = df_main[df_main['Region'] != 'Unterfranken']
    
    # Combine
    df_final = pd.concat([df_others, df_uf], ignore_index=True)
    
    # Clean whitespace in columns (just in case)
    for col in df_final.columns:
        if df_final[col].dtype == 'object':
            df_final[col] = df_final[col].str.strip()
            
    # Sort by Firm/Innung
    df_final = df_final.sort_values(by='Firm/Innung', key=lambda col: col.str.lower())
    
    # Save
    df_final.to_csv(main_csv, index=False)
    print(f"Merged and sorted. Total rows: {len(df_final)}")
    print(f"Unterfranken rows: {len(df_final[df_final['Region'] == 'Unterfranken'])}")

if __name__ == "__main__":
    merge_and_sort_leads()