#!/usr/bin/env python3
"""Report the download sizes of the SUM Parts archives on Hugging Face."""
from huggingface_hub import HfApi

REPO = "gwxgrxhyz/SUM-Parts"

api = HfApi()
info = api.repo_info(REPO, repo_type="dataset", files_metadata=True)

rows = []
for s in info.siblings:
    size = s.size or (s.lfs.size if getattr(s, "lfs", None) else None)
    if size and size > 1_000_000:
        rows.append((s.rfilename, size))

rows.sort(key=lambda r: -r[1])
total = 0
for name, size in rows:
    print(f"{size / 1e9:>8.2f} GB  {name}")
    total += size
print(f"{'-' * 30}")
print(f"{total / 1e9:>8.2f} GB  total (files > 1 MB)")