src/utils/helper.py

import os
import zipfile
from typing import Optional


def extract_zip_file(zip_file_path: str, destination_folder: str) -> None:
    """
    Extract a zip file to a destination folder.
    If destination folder already exists, extraction is skipped.
    
    Args:
        zip_file_path (str): Path to the zip file
        destination_folder (str): Path to the destination folder
    
    Raises:
        FileNotFoundError: If the zip file doesn't exist
    """
    # Check if destination folder already exists
    if os.path.exists(destination_folder):
        print(f"Destination folder {destination_folder} already exists. Skipping extraction.")
        return
    
    # Check if zip file exists
    if not os.path.exists(zip_file_path):
        raise FileNotFoundError(f"Zip file not found: {zip_file_path}")
    
    # Create destination folder
    os.makedirs(destination_folder, exist_ok=True)
    
    # Extract the zip file
    with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
        for member in zip_ref.infolist():
            # Handle non-ASCII filenames
            filename = member.filename.encode('cp437').decode('utf-8')
            extracted_path = os.path.join(destination_folder, filename)
            
            # Create directories if needed
            os.makedirs(os.path.dirname(extracted_path), exist_ok=True)
            
            # Extract file
            if not filename.endswith('/'):  # Skip directories
                with zip_ref.open(member) as source, open(extracted_path, 'wb') as target:
                    target.write(source.read())
    
    print(f"Successfully extracted {zip_file_path} to {destination_folder}")


def ensure_directory_exists(directory_path: str) -> None:
    """
    Ensure that a directory exists, create it if it doesn't.
    
    Args:
        directory_path (str): Path to the directory
    """
    os.makedirs(directory_path, exist_ok=True)


def get_file_extension(filename: str) -> Optional[str]:
    """
    Get the extension of a file.
    
    Args:
        filename (str): Name of the file
    
    Returns:
        Optional[str]: The file extension without the dot, or None if no extension
    """
    split = os.path.splitext(filename)
    if len(split) > 1:
        return split[1][1:]  # Remove the dot
    return None