mirror of
https://github.com/azaion/gps-denied-onboard.git
synced 2026-04-22 21:46:36 +00:00
Yuzviak
b57187e1b8
The prior registry entry was speculative: ``euroc_mh01`` pointing at an
old ``robotics.ethz.ch`` URL that no longer resolves (TCP timeout).
The dataset moved to ETH Research Collection (DOI 10.3929/ethz-b-000690084)
as a single 12.6 GB ``machine_hall.zip`` bundle containing MH_01…MH_05.
There's no stable direct download URL — DSpace gates behind a UI —
so:
- Renamed entry: ``euroc_mh01`` → ``euroc_machine_hall`` (matches the
actual artifact).
- SHA256 set to the real bundle hash 5ed7d07…
- URL left empty (same pattern as ``vpair_sample``); the CLI now
exits 3 and prints fetch instructions for empty-URL entries instead
of crashing on ``urllib.request.urlretrieve("")``.
- Adapter ``DatasetNotAvailableError`` message and conftest skip-reason
updated to tell engineers how to fetch/unpack manually.
- ``test_registry_has_euroc_machine_hall`` pin test replaces the old
pin; asserts real hash (not the ``"0"*64`` placeholder).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
50 lines
1.7 KiB
Python
50 lines
1.7 KiB
Python
"""CLI: python scripts/download_dataset.py <dataset_name>
|
|
|
|
Registered datasets: see DATASET_REGISTRY in gps_denied.testing.download.
|
|
Entries with an empty URL are manual-download-only (e.g. EuRoC via ETH
|
|
Research Collection, VPAIR via a Zenodo form) — this script prints the
|
|
instructions and exits instead of guessing a download URL.
|
|
"""
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
from gps_denied.testing.download import DATASET_REGISTRY, download_dataset
|
|
|
|
|
|
def main(argv: list[str]) -> int:
|
|
if len(argv) != 2:
|
|
print(f"usage: {argv[0]} <dataset_name>", file=sys.stderr)
|
|
print(f"available: {', '.join(DATASET_REGISTRY)}", file=sys.stderr)
|
|
return 2
|
|
name = argv[1]
|
|
if name not in DATASET_REGISTRY:
|
|
print(f"unknown dataset: {name}", file=sys.stderr)
|
|
print(f"available: {', '.join(DATASET_REGISTRY)}", file=sys.stderr)
|
|
return 2
|
|
spec = DATASET_REGISTRY[name]
|
|
if not spec.url:
|
|
print(
|
|
f"Dataset '{name}' has no automated download URL.",
|
|
file=sys.stderr,
|
|
)
|
|
print(
|
|
"Fetch manually, then place the archive so its SHA256 matches:\n"
|
|
f" expected sha256: {spec.sha256}\n"
|
|
f" expected path subdir under datasets/: {spec.target_subdir}\n"
|
|
"See DATASET_REGISTRY comments in src/gps_denied/testing/download.py "
|
|
"for per-dataset instructions.",
|
|
file=sys.stderr,
|
|
)
|
|
return 3
|
|
root = Path("datasets") / spec.target_subdir
|
|
dest = root / Path(spec.url).name
|
|
print(f"→ {dest}")
|
|
download_dataset(spec, dest)
|
|
print("OK")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main(sys.argv))
|