Files
lerobot-clone/tests/scripts/test_lerobot_annotate.py

59 lines
1.7 KiB
Python
Raw Normal View History

#!/usr/bin/env python
import json
from types import SimpleNamespace
tests(annotations): guard on the 'dataset' extra so base fast-test tier skips cleanly Fast Pytest Tests failed at COLLECTION in the base '--extra test' tier with 'ModuleNotFoundError: No module named datasets': tests/annotations/ conftest.py imported the fixture dataset builder (-> lerobot.datasets -> the HF 'datasets' lib + pandas/pyarrow), which only ship under the 'dataset' extra, so the whole annotations package crashed. Fix uses the repo's proven module-level guard pattern (see tests/datasets/test_language.py), NOT a conftest-level importorskip — verified empirically that pytest.importorskip raised during conftest *import* is treated as a collection ERROR (exit 1), while module-level importorskip is a clean SKIP. * conftest.py: import build_annotation_dataset LAZILY inside the fixtures so the conftest itself imports cleanly in every tier. * test_modules / test_validator / test_writer / test_pipeline_recipe_ render: add module-level pytest.importorskip('datasets') + ('pandas') before the pyarrow / lerobot.* imports (# noqa: E402 to match the existing convention). pyarrow-importing modules place the guard before the pyarrow import. * tests/scripts/test_lerobot_annotate.py: same guard (its _push_to_hub path imports lerobot.datasets). Result: - base / hardware / viz tiers (no dataset extra): annotation tests skip cleanly; the rest of the suite runs -> exit 0. - dataset tier: datasets present -> guards pass through -> annotation tests run with the stub VLM. The pipeline modules import only stdlib + relative + lerobot.datasets (no module-level datatrove / vllm / openai), so they import fine there. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-03 15:56:53 +02:00
import pytest
# ``lerobot.scripts.lerobot_annotate`` (and the ``_push_to_hub`` path it
# exercises) imports ``lerobot.datasets``, which only ships under the
# ``dataset`` extra. Skip in tiers without it instead of erroring.
pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
def test_push_to_hub_tags_uploaded_dataset_revision(tmp_path, monkeypatch):
from lerobot.scripts.lerobot_annotate import _push_to_hub
root = tmp_path / "dataset"
(root / "meta").mkdir(parents=True)
(root / "meta" / "info.json").write_text(json.dumps({"codebase_version": "v3.0"}))
calls = {}
class FakeHfApi:
def create_repo(self, **kwargs):
calls["create_repo"] = kwargs
def upload_folder(self, **kwargs):
calls["upload_folder"] = kwargs
return SimpleNamespace(oid="abc123")
def create_tag(self, **kwargs):
calls["create_tag"] = kwargs
monkeypatch.setattr("huggingface_hub.HfApi", FakeHfApi)
cfg = SimpleNamespace(
repo_id="source/dataset",
dest_repo_id="annotated/dataset",
push_private=True,
push_commit_message=None,
)
_push_to_hub(root, cfg)
assert calls["create_repo"] == {
"repo_id": "annotated/dataset",
"repo_type": "dataset",
"private": True,
"exist_ok": True,
}
assert calls["upload_folder"]["repo_id"] == "annotated/dataset"
assert calls["create_tag"] == {
"repo_id": "annotated/dataset",
"tag": "v3.0",
"repo_type": "dataset",
"exist_ok": True,
"revision": "abc123",
}