Skip to content

only check strings for new datasets #824

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
mfeurer merged 1 commit into from
Oct 15, 2019
Merged

only check strings for new datasets #824

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
23 changes: 12 additions & 11 deletions openml/datasets/dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,17 +109,18 @@ def __init__(self, name, description, format=None,
paper_url=None, update_comment=None,
md5_checksum=None, data_file=None, features=None,
qualities=None, dataset=None):
if description and not re.match("^[\x00-\x7F]*$", description):
# not basiclatin (XSD complains)
raise ValueError("Invalid symbols in description: {}".format(
description))
if citation and not re.match("^[\x00-\x7F]*$", citation):
# not basiclatin (XSD complains)
raise ValueError("Invalid symbols in citation: {}".format(
citation))
if not re.match("^[a-zA-Z0-9_\\-\\.\\(\\),]+$", name):
# regex given by server in error message
raise ValueError("Invalid symbols in name: {}".format(name))
if dataset_id is None:
if description and not re.match("^[\x00-\x7F]*$", description):
# not basiclatin (XSD complains)
raise ValueError("Invalid symbols in description: {}".format(
description))
if citation and not re.match("^[\x00-\x7F]*$", citation):
# not basiclatin (XSD complains)
raise ValueError("Invalid symbols in citation: {}".format(
citation))
if not re.match("^[a-zA-Z0-9_\\-\\.\\(\\),]+$", name):
# regex given by server in error message
raise ValueError("Invalid symbols in name: {}".format(name))
# TODO add function to check if the name is casual_string128
# Attributes received by querying the RESTful API
self.dataset_id = int(dataset_id) if dataset_id is not None else None
Expand Down