Skip to content

fix: forward storage_options as kwargs in CloudParquetDir #836

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tchaton merged 1 commit into from
Jul 2, 2026
Merged

fix: forward storage_options as kwargs in CloudParquetDir #836

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/litdata/utilities/parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ def __init__(
for provider in _CLOUD_PROVIDER:
if self.dir.url.startswith(provider):
# Initialize the cloud filesystem
self.fs = fsspec.filesystem(provider, *self.storage_options)
self.fs = fsspec.filesystem(provider, **self.storage_options)
print(f"using provider: {provider}")
break

Expand Down
14 changes: 14 additions & 0 deletions tests/streaming/test_parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,6 +129,20 @@ def test_get_parquet_indexer_cls(pq_url, tmp_path, cls, expectation, monkeypatch
assert isinstance(indexer_obj, cls)


@pytest.mark.skipif(condition=sys.platform == "win32", reason="Fails on windows bcoz of urllib.parse")
def test_cloud_parquet_dir_forwards_storage_options(tmp_path, monkeypatch, fsspec_mock):
Comment thread
deependujha marked this conversation as resolved.
fsspec_fs_mock = Mock()
fsspec_fs_mock.ls = Mock(return_value=[])
fsspec_mock.filesystem = Mock(return_value=fsspec_fs_mock)

monkeypatch.setattr("litdata.utilities.parquet._FSSPEC_AVAILABLE", True)

storage_options = {"key": "ACCESS_KEY", "secret": "SECRET_KEY", "endpoint_url": "https://s3.example.com"}
CloudParquetDir("s3://some_bucket/some_path", tmp_path, storage_options=storage_options)

fsspec_mock.filesystem.assert_called_once_with("s3", **storage_options)


@pytest.mark.usefixtures("clean_pq_index_cache")
@patch("litdata.utilities.parquet._HF_HUB_AVAILABLE", True)
@patch("litdata.streaming.downloader._HF_HUB_AVAILABLE", True)
Expand Down
Loading