#!/usr/bin/env bash
# SUM Parts - check the downloaded archives survived
#
# The WSL VM has now died twice under load, and the first time it left pip's
# in-flight files as 0-byte stubs. A download interrupted the same way leaves a
# truncated zip, so verify before trusting anything that was in flight.
set -euo pipefail

source "$HOME/miniconda3/etc/profile.d/conda.sh"
conda activate sumparts

python - <<'PY'
import zipfile
from pathlib import Path

d = Path.home() / "sum-parts/data/_archives"
expected = {"demo.zip": 0.12, "mesh.zip": 0.52, "pcl.zip": 4.66}  # GB, from the HF listing

if not d.exists():
    print(f"{d} missing")
    raise SystemExit(1)

bad = []
for f in sorted(d.glob("*.zip")):
    gb = f.stat().st_size / 1e9
    want = expected.get(f.name)
    line = f"{f.name:<12} {gb:>6.2f} GB"
    if want:
        line += f"  (expected ~{want:.2f} GB)"
        if gb < want * 0.97:
            line += "  TRUNCATED"
            bad.append(f.name)
            print(line)
            continue
    try:
        z = zipfile.ZipFile(f)
        broken = z.testzip()
        if broken:
            line += f"  CORRUPT at {broken}"
            bad.append(f.name)
        else:
            line += f"  OK, {len(z.namelist())} entries"
    except Exception as e:
        line += f"  UNREADABLE {type(e).__name__}: {e}"
        bad.append(f.name)
    print(line)

for name in expected:
    if not (d / name).exists():
        print(f"{name:<12}  MISSING")

print()
print("all good" if not bad else f"re-download: {', '.join(bad)}")
raise SystemExit(1 if bad else 0)
PY