def unmap_dataset(
project: Project,
*,
source_dataset: Dataset,
remove_dataset_from_project: bool = False,
skip_if_missing: bool = False,
) -> None:
"""
Wholly unmaps a dataset and optionally removes it from a project.
Args:
source_dataset: the source dataset (Dataset object not a string) to unmap
project: the project in which to unmap the dataset
remove_dataset_from_project: boolean to also remove the dataset from the project
skip_if_missing: boolean to skip if dataset is not in project. If set to false and
dataset is not in project will raise a RuntimeError
Returns:
None
Raises:
RuntimeError: if `source_dataset` is not in `project` and `skip_if_missing` not set to True
"""
# check to make sure dataset is in project and log a warning if it is not
if source_dataset.name not in [x.name for x in project.input_datasets()]:
if skip_if_missing:
LOGGER.warning(
f"Dataset to unmap {source_dataset.name} not in project {project.name}! "
f"However skip_if_missing flag is set so will do nothing"
)
return None
else:
error_message = (
f"Dataset to unmap {source_dataset.name} not in project "
f"{project.name} and skip_if_missing not set to True so failing! "
)
LOGGER.error(error_message)
raise RuntimeError(error_message)
# the resource ids of attribute mappings unfortunately change when you delete one
# so need to just do this until there are no mappings left for the source dataset of interest
while True:
mappings = [
x
for x in project.attribute_mappings().stream()
if x.input_dataset_name == source_dataset.name
]
# if no mappings found for this dataset then break
if not mappings:
break
for mapping in mappings:
# can only delete one then have to break out of inner loop
project.attribute_mappings().delete_by_resource_id(mapping.resource_id)
break
# optionally remove dataset from the project
if remove_dataset_from_project:
project.remove_input_dataset(source_dataset)
def test_project_remove_input_dataset(self):
dataset_id = self.dataset_json[0]["relativeId"]
responses.add(responses.GET, self.input_datasets_url, json=self.dataset_json)
responses.add(
responses.DELETE, f"{self.input_datasets_url}?id={dataset_id}", status=204
)
responses.add(responses.GET, self.input_datasets_url, json=[])
project = Project(self.tamr, self.project_json[0])
dataset = next(project.input_datasets().stream())
response = project.remove_input_dataset(dataset)
self.assertEqual(response.status_code, 204)
input_datasets = project.input_datasets()
self.assertEqual(list(input_datasets), [])
