def mutate_and_get_payload(cls,
root,
info,
labbook_owner,
labbook_name,
dataset_owner,
dataset_name,
action,
dataset_url=None,
client_mutation_id=None):
logged_in_username = get_logged_in_username()
im = InventoryManager()
lb = im.load_labbook(logged_in_username,
labbook_owner,
labbook_name,
author=get_logged_in_author())
with lb.lock():
if action == 'link':
if dataset_url:
remote_domain = cls._get_remote_domain(
dataset_url, dataset_owner, dataset_name)
if remote_domain:
# Make sure git creds are configured for the remote
admin_service = None
for remote in lb.client_config.config['git'][
'remotes']:
if remote_domain == remote:
admin_service = lb.client_config.config['git'][
'remotes'][remote]['admin_service']
break
if "HTTP_AUTHORIZATION" in info.context.headers.environ:
token = parse_token(info.context.headers.
environ["HTTP_AUTHORIZATION"])
else:
raise ValueError(
"Authorization header not provided."
" Must have a valid session to query for collaborators"
)
mgr = GitLabManager(remote_domain, admin_service,
token)
mgr.configure_git_credentials(remote_domain,
logged_in_username)
else:
# Link to local dataset
ds = im.load_dataset(logged_in_username, dataset_owner,
dataset_name)
dataset_url = f"{ds.root_dir}/.git"
# Link the dataset to the labbook
ds = im.link_dataset_to_labbook(dataset_url, dataset_owner,
dataset_name, lb)
ds.namespace = dataset_owner
# Preload the dataloader
info.context.dataset_loader.prime(
f"{get_logged_in_username()}&{dataset_owner}&{dataset_name}",
ds)
# Relink the revision
m = Manifest(ds, logged_in_username)
m.link_revision()
elif action == 'unlink':
im.unlink_dataset_from_labbook(dataset_owner, dataset_name, lb)
elif action == 'update':
ds = im.update_linked_dataset_reference(
dataset_owner, dataset_name, lb)
m = Manifest(ds, logged_in_username)
m.force_reload()
info.context.dataset_loader.prime(
f"{get_logged_in_username()}&{dataset_owner}&{dataset_name}",
ds)
else:
raise ValueError(
"Unsupported action. Use `link`, `unlink`, or `update`")
info.context.labbook_loader.prime(
f"{get_logged_in_username()}&{labbook_owner}&{labbook_name}",
lb)
edge = LabbookConnection.Edge(node=Labbook(owner=labbook_owner,
name=labbook_name),
cursor=base64.b64encode(
f"{0}".encode('utf-8')))
return ModifyDatasetLink(new_labbook_edge=edge)
def test_link_unlink_dataset_across_branches(self, mock_labbook):
"""Test to verify linked Dataset initialization works across branching in Projects
- Create a project
- Create a dataset
- Link dataset on master
- Switch to another branch
- Unlink dataset: dataset is gone
- Switch to master: dataset is available
- Switch to other branch: dataset is gone
- Switch to master: dataset is available
"""
inv_manager = InventoryManager(mock_labbook[0])
lb = mock_labbook[2]
ds = inv_manager.create_dataset("test",
"test",
"dataset100",
"gigantum_object_v1",
description="my dataset")
# Fake publish to a local bare repo
_MOCK_create_remote_repo2(ds, 'test', None, None)
assert os.path.exists(os.path.join(lb.root_dir,
'.gitmodules')) is False
# link dataset and make sure it's there
inv_manager.link_dataset_to_labbook(ds.remote, 'test', 'dataset100',
lb)
assert os.path.exists(os.path.join(lb.root_dir, '.gitmodules')) is True
dataset_submodule_dir = os.path.join(lb.root_dir, '.gigantum',
'datasets', 'test', 'dataset100')
assert os.path.exists(dataset_submodule_dir) is True
assert os.path.exists(os.path.join(dataset_submodule_dir,
'.gigantum')) is True
# Create a branch
bm = BranchManager(lb, username="******")
assert bm.active_branch == 'master'
branch_name = bm.create_branch(title="test-branch")
assert bm.active_branch == branch_name
assert lb.is_repo_clean
# Dataset still there
assert os.path.exists(os.path.join(lb.root_dir, '.gitmodules')) is True
dataset_submodule_dir = os.path.join(lb.root_dir, '.gigantum',
'datasets', 'test', 'dataset100')
assert os.path.exists(dataset_submodule_dir) is True
assert os.path.exists(os.path.join(dataset_submodule_dir,
'.gigantum')) is True
# Unlink dataset in branch
inv_manager.unlink_dataset_from_labbook('test', 'dataset100', lb)
# Dataset gone
dataset_submodule_dir = os.path.join(lb.root_dir, '.gigantum',
'datasets', 'test', 'dataset100')
assert os.path.exists(dataset_submodule_dir) is False
assert os.path.exists(os.path.join(dataset_submodule_dir,
'.gigantum')) is False
with open(os.path.join(lb.root_dir, '.gitmodules'), 'rt') as mf:
data = mf.read()
assert len(data) == 0
# Switch back to master
bm.workon_branch('master')
assert bm.active_branch == 'master'
assert lb.active_branch == 'master'
assert lb.is_repo_clean
# Dataset is back!
assert os.path.exists(os.path.join(lb.root_dir, '.gitmodules')) is True
dataset_submodule_dir = os.path.join(lb.root_dir, '.gigantum',
'datasets', 'test', 'dataset100')
assert os.path.exists(dataset_submodule_dir) is True
assert os.path.exists(os.path.join(dataset_submodule_dir,
'.gigantum')) is True
with open(os.path.join(lb.root_dir, '.gitmodules'), 'rt') as mf:
data = mf.read()
assert len(data) > 0
# Switch back to branch
bm.workon_branch('test-branch')
assert bm.active_branch == 'test-branch'
assert lb.active_branch == 'test-branch'
assert lb.is_repo_clean
dataset_submodule_dir = os.path.join(lb.root_dir, '.gigantum',
'datasets', 'test', 'dataset100')
assert os.path.exists(dataset_submodule_dir) is False
assert os.path.exists(os.path.join(dataset_submodule_dir,
'.gigantum')) is False
with open(os.path.join(lb.root_dir, '.gitmodules'), 'rt') as mf:
data = mf.read()
assert len(data) == 0
# Switch back to master
bm.workon_branch('master')
assert bm.active_branch == 'master'
assert lb.active_branch == 'master'
assert lb.is_repo_clean
# Dataset is back!
assert os.path.exists(os.path.join(lb.root_dir, '.gitmodules')) is True
dataset_submodule_dir = os.path.join(lb.root_dir, '.gigantum',
'datasets', 'test', 'dataset100')
assert os.path.exists(dataset_submodule_dir) is True
assert os.path.exists(os.path.join(dataset_submodule_dir,
'.gigantum')) is True
with open(os.path.join(lb.root_dir, '.gitmodules'), 'rt') as mf:
data = mf.read()
assert len(data) > 0
