test.py

import os, subprocess, sys, zipfile

# === 1.B Extraer el dataset
def extract_zip(zip_file_path, destination_path):
    """
    Extracts the contents of a ZIP file to a specified directory.
    
    Args:
        zip_file_path (str): The full path to the ZIP file.
        destination_path (str): The directory where the contents will be extracted.
    """
    # Create the destination directory if it doesn't exist
    os.makedirs(destination_path, exist_ok=True)
    
    try:
        # Open the ZIP file in read mode
        with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
            # Extract all the contents to the specified directory
            zip_ref.extractall(destination_path)
        print(f"✅ Extracted '{zip_file_path}' to '{destination_path}' successfully.")
    except zipfile.BadZipFile:
        print(f"❌ Error: The file '{zip_file_path}' is not a valid ZIP file.")
    except FileNotFoundError:
        print(f"❌ Error: The file '{zip_file_path}' was not found.")
    except Exception as e:
        print(f"❌ An unexpected error occurred: {e}")

# Example usage:
zip_file = "/home/user/app/voxpopuli_es_500.zip"
DATASET_PATH = "/tmp/dataset/voxpopuli_es_500"

# To protect against security vulnerabilities, it is important to sanitize the destination path.
# This prevents an attacker from using a malicious ZIP file to write outside the destination folder.
safe_destination = os.path.abspath(DATASET_PATH)

# Call the function
extract_zip(zip_file, safe_destination)