nwb-hdf5-to-zarr

#!/usr/bin/env python
# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "pynwb>=2.8.0",
#     "hdmf-zarr>=0.8.0",
# ]
# ///
"""Convert NWB file from HDF5 to Zarr format."""

import sys
from pathlib import Path

from hdmf_zarr import NWBZarrIO
from pynwb import NWBHDF5IO


def nwb_to_zarr(input_path: str | Path, output_path: str | Path | None = None) -> Path:
    """
    Convert an HDF5 NWB file to Zarr format.

    Parameters
    ----------
    input_path : str | Path
        Path to input .nwb (HDF5) file
    output_path : str | Path | None
        Path for output .zarr directory. If None, uses input name with .zarr extension

    Returns
    -------
    Path
        Path to the created Zarr store
    """
    input_path = Path(input_path)
    if output_path is None:
        output_path = input_path.with_suffix(".zarr")
    output_path = Path(output_path)

    # Read the HDF5 NWB file
    with NWBHDF5IO(input_path, mode="r", load_namespaces=True) as read_io:
        nwbfile = read_io.read()

        # Export to Zarr
        with NWBZarrIO(output_path, mode="w") as export_io:
            export_io.export(src_io=read_io, nwbfile=nwbfile, write_args={'link_data': False})

    print(f"Converted: {input_path} -> {output_path}")
    return output_path


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print(f"Usage: {sys.argv[0]} <input.nwb> [output.zarr]", file=sys.stderr)
        sys.exit(1)

    input_file = sys.argv[1]
    output_file = sys.argv[2] if len(sys.argv) > 2 else None
    nwb_to_zarr(input_file, output_file)