import pandas as pd
import numpy as np
import logging
import sys
import io

# Configure logging to stdout only
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    handlers=[
        logging.StreamHandler(sys.stdout)
    ]
)
logger = logging.getLogger(__name__)

def preprocess_csv(input_data):
    """
    Preprocess a CSV file:
    - Remove empty rows
    - Handle newline characters in string columns
    - Fill No. column with sequential numbers
    
    Args:
        input_data: File-like object or path to the input CSV file
    
    Returns:
        DataFrame: The processed dataframe
    """
    try:
        logger.info("Reading input data")
        
        # Read CSV data (can handle both file path string or file-like object)
        df = pd.read_csv(input_data)
        
        logger.info(f"Original dataframe shape: {df.shape}")
        
        # Remove completely empty rows
        df = df.dropna(how='all')
        logger.info(f"Shape after removing empty rows: {df.shape}")
        
        # Handle newline characters in string columns
        for column in df.columns:
            if df[column].dtype == 'object':  # Only apply to string columns
                df[column] = df[column].str.replace('\n', ' ').str.strip()
        
        # Fill No. column with sequential numbers
        df['No.'] = np.arange(1, len(df) + 1)
        
        logger.info("Preprocessing complete:")
        logger.info(f"- Removed empty rows")
        logger.info(f"- Processed newline characters in string columns")
        logger.info(f"- Filled No. column with values from 1 to {len(df)}")
        
        return df
    
    except Exception as e:
        logger.error(f"Error preprocessing CSV: {str(e)}")
        raise