mirror of
https://github.com/huggingface/lerobot.git
synced 2026-06-04 21:01:26 +00:00
b9246ef61b
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>
59 lines
1.7 KiB
Python
59 lines
1.7 KiB
Python
#!/usr/bin/env python
|
|
|
|
import json
|
|
from types import SimpleNamespace
|
|
|
|
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",
|
|
}
|