import os
import streamlit as st
from pathlib import Path
from datasets import load_dataset
from dotenv import load_dotenv


def list_files_in_directory(directory):
    """List all files in the given directory and its subdirectories."""
    files = []
    for root, dirs, filenames in os.walk(directory):
        for filename in filenames:
            files.append(os.path.join(root, filename))
    return files


def main():
    st.title("Embeddings File Browser")

    # Load environment variables
    load_dotenv()

    # Retrieve the Hugging Face token
    hf_token = os.getenv("HF_TOKEN")
    if not hf_token:
        st.error("HF_TOKEN not found in environment variables.")
        return

    # Load the dataset using the token
    try:
        dataset = load_dataset("SongLift/LyrGen2_DB", use_auth_token=hf_token)
        st.write("Dataset loaded successfully.")
    except Exception as e:
        st.error(f"Error loading dataset: {str(e)}")
        return

    # Directory to browse
    directory = "/data"  # Persistent storage directory
    st.write(f"Browsing directory: {directory}")

    # List files
    files = list_files_in_directory(directory)

    if files:
        st.write("Files found:")
        for file in files:
            st.write(file)
    else:
        st.write("No files found in the directory.")


if __name__ == "__main__":
    main()