Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
27 changes: 15 additions & 12 deletions uv.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion vortex-python/python/vortex/ray/datasource.py
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@ def _read_task(
num_rows=num_rows,
size_bytes=None,
exec_stats=None,
input_files=paths,
input_files=tuple(paths),
)

def read() -> Iterable[pandas.DataFrame]:
Expand Down
18 changes: 10 additions & 8 deletions vortex-python/test/test_datasource.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,15 @@

@pytest.fixture(scope="module")
def ray_init():
# https://github.com/ray-project/ray/issues/53848#issuecomment-3056271943
ray.init( # pyright: ignore[reportUnknownMemberType]
runtime_env={
"working_dir": None,
"excludes": [".git", ".venv"],
}
)
# Ray's uv_runtime_env_hook would auto-upload the working directory to
# workers, but vortex-python's compiled _lib extension exceeds Ray's
# 512 MiB upload limit. Disable the hook for these local-mode tests.
# (Ray 2.55 added a string-type validation that broke the previous
# `working_dir: None` workaround from ray-project/ray#53848.)
import ray._private.ray_constants as ray_constants

ray_constants.RAY_ENABLE_UV_RUN_RUNTIME_ENV = False
_ = ray.init() # pyright: ignore[reportUnknownMemberType]
yield None
ray.shutdown() # pyright: ignore[reportUnknownMemberType]

Expand Down Expand Up @@ -53,7 +55,7 @@ def test_vortex_datasource(ray_init, tmpdir_factory): # pyright: ignore[reportU
# Without an explicit sort, Ray may reorder rows *even within a single record batch*.
ds = ds.sort("index")

tbl = pa.concat_tables(pa.Table.from_pydict(x) for x in ds.iter_batches()) # pyright: ignore[reportArgumentType]
tbl = pa.concat_tables(pa.Table.from_pydict(x) for x in ds.iter_batches()) # pyright: ignore[reportArgumentType, reportUnknownMemberType, reportUnknownVariableType]
expected = pa.Table.from_pylist([record(x) for x in range(0, 10)], schema=tbl.schema)

assert tbl == expected
Loading