import pymysql
import pandas as pd

# Database connection configuration for English Wikipedia replica
# PAWS uses .my.cnf for authentication
config = {
    'host': 'enwiki.analytics.db.svc.wikimedia.cloud',
    'port': 3306,
    'read_default_file': '~/.my.cnf',  # Use the .my.cnf credentials file
    'database': 'enwiki_p',
    'charset': 'utf8mb4'
}

def run_query():
    sql = "SELECT page_title, page_len FROM page WHERE page_namespace = 0 ORDER BY page_len DESC LIMIT 5;"
    
    try:
        # Connect to database
        connection = pymysql.connect(**config)
        
        # Execute query and get results as DataFrame
        df = pd.read_sql(sql, connection)
        connection.close()
        
        # Console log the results
        print("Top 5 Longest Wikipedia Articles:")
        print("=" * 50)
        
        for index, row in df.iterrows():
            title = row['page_title'].decode('utf-8') if isinstance(row['page_title'], bytes) else row['page_title']
            length = row['page_len']
            print(f"{index + 1}. {title} - {length:,} bytes")
        
        print("=" * 50)
        print(f"Query returned {len(df)} rows")
        
        return df
        
    except Exception as e:
        print(f"Error executing query: {e}")
        return None

# Run the query
if __name__ == "__main__":
    results = run_query()