import streamlit as st
import numpy as np
import pandas as pd
import time
from fuzzywuzzy import process

def clean_player_name(name):
    # Handle colon case first (remove everything before colon)
    if ':' in name:
        name = name.split(':')[1].strip()
    
    # Handle parentheses case (remove everything after opening parenthesis)
    if '(' in name:
        name = name.split('(')[0].strip()
    
    return name

def load_file(upload):
    if upload is not None:
        try:
            if upload.name.endswith('.csv'):
                df = pd.read_csv(upload)
            elif upload.name.endswith(('.xls', '.xlsx')):
                df = pd.read_excel(upload)
            else:
                st.error('Please upload either a CSV or Excel file')
                return None
            
            export_df = df.copy()
            
            for col in df.columns:
                if df[col].dtype == 'object':
                    df[col] = df[col].apply(lambda x: clean_player_name(x) if isinstance(x, str) else x)
            
            return export_df, df
        except Exception as e:
            st.error(f'Error loading file: {str(e)}')
            return None
    return None