Skip to content

fix(dataset): import renku datasets #1894

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
mohammad-alisafaee merged 2 commits into from
Feb 23, 2021
Merged

fix(dataset): import renku datasets #1894

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
02d61b9
fix(dataset): import renku datasets
mohammad-alisafaee Feb 23, 2021
fa8d94e
Merge branch 'master' into 1741-dataset-import-failed
mohammad-alisafaee Feb 23, 2021
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
14 changes: 11 additions & 3 deletions renku/core/commands/providers/renku.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ def find_record(self, uri, client=None):

self._prepare_authentication(client, uri)

initial_identifier, kg_urls = self._get_dataset_info(uri)
same_as, initial_identifier, kg_urls = self._get_dataset_info(uri)

project_url = None
failed_urls = []
Expand All @@ -77,7 +77,14 @@ def find_record(self, uri, client=None):

datasets = self._query_knowledge_graph(project_datasets_kg_url)

dataset_name = next(ds["name"] for ds in datasets if ds["versions"].get("initial") == initial_identifier)
dataset_name = next(
(ds["name"] for ds in datasets if ds["versions"].get("initial") == initial_identifier), None
)
if not dataset_name and same_as:
dataset_name = next((ds["name"] for ds in datasets if ds.get("sameAs") == same_as), None)

if not dataset_name:
continue

# Check if we can clone the project
for url in (ssh_url, https_url):
Expand Down Expand Up @@ -144,6 +151,7 @@ def _get_dataset_info(self, uri):

response = self._query_knowledge_graph(kg_url)
initial_identifier = response.get("versions", {}).get("initial")
same_as = response.get("sameAs")

if project_id:
kg_path = f"/knowledge-graph/{project_id.strip('/')}"
Expand All @@ -160,7 +168,7 @@ def get_project_link(project):
kg_urls = [get_project_link(p) for p in projects]
kg_urls = [u for u in kg_urls if u]

return initial_identifier, kg_urls
return same_as, initial_identifier, kg_urls

@staticmethod
def _extract_project_and_dataset_ids(parsed_url):
Expand Down
6 changes: 4 additions & 2 deletions renku/core/management/datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -784,7 +784,7 @@ def _add_from_git(self, url, sources, destination, ref):
if remote_client._is_external_file(src):
operation = (src.resolve(), dst, "symlink")
else:
operation = (src, dst, "copy")
operation = (src, dst, "move")

results.append(
{
Expand Down Expand Up @@ -1237,6 +1237,7 @@ def checkout(repo, ref):
except GitCommandError:
raise errors.ParameterError('Cannot find reference "{}" in Git repository: {}'.format(ref, url))

depth = 1 if not ref else None
ref = ref or renku_branch
u = GitURL.parse(url)
path = u.pathname
Expand All @@ -1251,6 +1252,7 @@ def checkout(repo, ref):
repo = Repo(str(repo_path))
if repo.remotes.origin.url == url:
try:
repo.git.checkout(".")
repo.git.fetch(all=True)
repo.git.checkout(ref)
try:
Expand All @@ -1269,7 +1271,7 @@ def checkout(repo, ref):
except PermissionError:
raise errors.InvalidFileOperation("Cannot delete files in {}: Permission denied".format(repo_path))

repo, _ = clone(url, path=str(repo_path), install_githooks=False)
repo, _ = clone(url, path=str(repo_path), install_githooks=False, depth=depth)

# Because the name of the default branch is not always 'master', we
# create an alias of the default branch when cloning the repo. It
Expand Down