from pathlib import Path
from sp2xr.io import process_sp2xr_file

# from sp2xr.io import read_csv_files_with_dask

DATA = Path(__file__).parent / "data"


def test_read_real_pbp_zip(tmp_path):
    mini_zip = DATA / "mini_SP2XR_PbP_20190409110737_x0001.zip"
    config_file = DATA / "config.yaml"

    df = process_sp2xr_file(
        file_path=str(mini_zip),
        config_path=str(config_file),
        target_directory=str(tmp_path / "pq_out"),
    )

    # 50 lines in file = 50 rows returned
    assert len(df) == 50
    # parquet really written
    assert list((tmp_path / "pq_out").rglob("*.parquet")), "No parquet output"


def test_read_real_hk_zip(tmp_path):
    mini_zip = DATA / "mini_SP2XR_hk_20190409110737_x0001.zip"
    config_file = DATA / "config.yaml"

    df = process_sp2xr_file(
        file_path=str(mini_zip),
        config_path=str(config_file),
        target_directory=str(tmp_path / "pq_out"),
    )

    assert len(df) == 50  # or assert exact number if known
    assert list((tmp_path / "pq_out").rglob("*.parquet")), "No parquet output"