packager.py

import tempfile
import zipfile
from typing import Optional
from pathlib import Path

from dataset import ImageDataset


def create_dataset_zip(
    dataset: ImageDataset, organize_in_folders: bool = True
) -> Optional[str]:
    """Create a zip file containing images and their text labels.

    Args:
        dataset: ImageDataset containing images with labels
        organize_in_folders: If True, puts images in 'images/' folder and texts in 'labels/' folder.
                           If False, puts all files in the root folder.

    Returns:
        str: Path to the created zip file, or None if dataset is empty
    """
    if not dataset.images:
        return None

    # Create a temporary file
    temp_file = tempfile.NamedTemporaryFile(
        delete=False, prefix="image-dataset", suffix=".zip"
    )
    temp_path = temp_file.name
    temp_file.close()

    try:
        with zipfile.ZipFile(temp_path, "w", zipfile.ZIP_DEFLATED) as zip_file:
            for image_data in dataset.images:
                image_path = image_data["path"]
                label = image_data["label"]

                try:
                    # Determine file paths based on organization option
                    image_filename = Path(image_path).name
                    base_name = Path(image_path).stem
                    text_filename = f"{base_name}.txt"

                    if organize_in_folders:
                        image_zip_path = f"images/{image_filename}"
                        text_zip_path = f"labels/{text_filename}"
                    else:
                        image_zip_path = image_filename
                        text_zip_path = text_filename

                    # Add the image file to zip
                    with open(image_path, "rb") as img_file:
                        zip_file.writestr(image_zip_path, img_file.read())

                    # Create and add the text file
                    zip_file.writestr(text_zip_path, label.encode("utf-8"))

                except FileNotFoundError:
                    # Skip if image file doesn't exist
                    continue
                except Exception as e:
                    # Log error but continue with other files
                    print(f"Error processing {image_path}: {e}")
                    continue

        return temp_path

    except Exception:
        # Clean up temp file if creation failed
        Path(temp_path).unlink(missing_ok=True)
        return None