Skip to content

Raise early for invalid revision in load_dataset #7929

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
Scott-Simmons wants to merge 2 commits into
base: main
Choose a base branch
from
+14 −8
Open

Raise early for invalid revision in load_dataset #7929

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cc23990
Add test for checking invalid revision handling
Scott-Simmons Jan 2, 2026
9fec0b6
Fix load_dataset ignoring invalid revision when cache exists
Scott-Simmons Jan 2, 2026
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
10 changes: 2 additions & 8 deletions src/datasets/load.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -977,10 +977,6 @@ def dataset_module_factory(
elif e.response.status_code == 403:
message += f" Visit the dataset page at https://huggingface.co/datasets/{path} to ask for access."
raise DatasetNotFoundError(message) from e
except RevisionNotFoundError as e:
raise DatasetNotFoundError(
f"Revision '{revision}' doesn't exist for dataset '{path}' on the Hub."
) from e
except RepositoryNotFoundError as e:
raise DatasetNotFoundError(f"Dataset '{path}' doesn't exist on the Hub or cannot be accessed.") from e
try:
Expand Down Expand Up @@ -1014,10 +1010,8 @@ def dataset_module_factory(
elif e.response.status_code == 403:
message += f" Visit the dataset page at https://huggingface.co/datasets/{path} to ask for access."
raise DatasetNotFoundError(message) from e
except RevisionNotFoundError as e:
raise DatasetNotFoundError(
f"Revision '{revision}' doesn't exist for dataset '{path}' on the Hub."
) from e
except RevisionNotFoundError as e:
raise DatasetNotFoundError(f"Revision '{revision}' doesn't exist for dataset '{path}' on the Hub.") from e
except Exception as e1:
# All the attempts failed, before raising the error we should check if the module is already cached
try:
Expand Down
12 changes: 12 additions & 0 deletions tests/test_load.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -763,6 +763,18 @@ def test_load_dataset_from_hub(self):
str(context.exception),
)

@pytest.mark.integration
def test_load_dataset_invalid_revision_with_cache(self):
repo_id = SAMPLE_DATASET_IDENTIFIER2
builder = load_dataset_builder(repo_id, cache_dir=self.cache_dir)
builder.download_and_prepare()
with self.assertRaises(DatasetNotFoundError) as context:
datasets.load_dataset(repo_id, revision="invalid_revision", cache_dir=self.cache_dir)
self.assertIn(
"Revision 'invalid_revision' doesn't exist for dataset",
str(context.exception),
)

def test_load_dataset_namespace(self):
with self.assertRaises(DatasetNotFoundError) as context:
datasets.load_dataset("hf-internal-testing/_dummy")
Expand Down