Skip to content

fix(parquet): pass storage_options as **kwargs to fsspec.filesystem, fix mutable default args #837

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

Open
Tejas5405 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(parquet): pass storage_options as **kwargs to fsspec.filesystem, fix mutable default args #837

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
6 changes: 3 additions & 3 deletions src/litdata/utilities/parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ def __init__(
self,
dir_path: str | Dir | None,
cache_path: str | None = None,
storage_options: dict | None = {},
storage_options: dict | None = None,
num_workers: int = 4,
):
if not _PYARROW_AVAILABLE:
Expand Down 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 Expand Up @@ -304,7 +304,7 @@ def write_index(self, chunks_info: list[dict[str, Any]], config: dict[str, Any])
def get_parquet_indexer_cls(
dir_path: str,
cache_path: str | None = None,
storage_options: dict | None = {},
storage_options: dict | None = None,
num_workers: int = 4,
) -> ParquetDir:
"""Get the appropriate ParquetDir class based on the directory path scheme.
Expand Down