"""Download the three Stage A pilot months with checksums into data/raw/."""

from __future__ import annotations

import hashlib
import json
import sys
import time
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))

from huggingface_hub import hf_hub_download

from intraday_fragility import paths

PILOT_MONTHS = ["1992-06", "2009-06", "2025-12"]


def main() -> None:
    cfg = paths.base_config()["dataset"]
    records = []
    for m in PILOT_MONTHS:
        y, mm = map(int, m.split("-"))
        t0 = time.time()
        p = hf_hub_download(cfg["id"], cfg["file_pattern"].format(year=y, month=mm),
                            repo_type="dataset", revision=cfg["revision"],
                            local_dir=paths.get("raw"))
        h = hashlib.sha256()
        with open(p, "rb") as f:
            for chunk in iter(lambda: f.read(1 << 20), b""):
                h.update(chunk)
        records.append({"month": m, "bytes": Path(p).stat().st_size,
                        "sha256": h.hexdigest(), "secs": round(time.time() - t0, 1)})
        print(records[-1])
    out = paths.get("manifests") / "pilot_downloads.json"
    out.write_text(json.dumps({"dataset_id": cfg["id"], "revision": cfg["revision"],
                               "files": records}, indent=1))


if __name__ == "__main__":
    main()