def work(self):
"""
Go through all datasources, and if it is configured to automatically
delete old datasets, do so for all qualifying datasets
:return:
"""
for datasource_id in self.all_modules.datasources:
datasource = self.all_modules.datasources[datasource_id]
# default = never expire
if not datasource.get("expire-datasets", None):
continue
cutoff = time.time() - datasource.get("expire-datasets")
datasets = self.db.fetchall(
"SELECT key FROM datasets WHERE key_parent = '' AND parameters::json->>'datasource' = %s AND timestamp < %s",
(datasource_id, cutoff))
# we instantiate the dataset, because its delete() method does all
# the work (e.g. deleting child datasets) for us
for dataset in datasets:
dataset = DataSet(key=dataset["key"], db=self.db)
dataset.delete()
self.log.info("Deleting dataset %s/%s (expired per configuration)" % (datasource, dataset.key))
self.job.finish()
def delete_dataset(key=None):
"""
Delete a dataset
Only available to administrators. Deletes a dataset, as well as any
children linked to it, from 4CAT. Calling this on a dataset that is
currently being executed is undefined behaviour.
:request-param str query_key: ID of the dataset for which to return the status
:request-param str ?access_token: Access token; only required if not
logged in currently.
:return: A dictionary with a successful `status`.
:return-schema: {type=object,properties={status={type=string}}}
:return-error 404: If the dataset does not exist.
"""
if not current_user.is_admin():
return error(403, message="Not allowed")
dataset_key = request.form.get("key", "") if not key else key
try:
dataset = DataSet(key=dataset_key, db=db)
except TypeError:
return error(404, error="Dataset does not exist.")
dataset.delete()
return jsonify({"status": "success"})
def delete_dataset(key=None):
"""
Delete a dataset
Only available to administrators and dataset owners. Deletes a dataset, as
well as any children linked to it, from 4CAT. Also tells the backend to stop
any jobs dealing with the dataset.
:request-param str key: ID of the dataset to delete
:request-param str ?access_token: Access token; only required if not
logged in currently.
:return: A dictionary with a successful `status`.
:return-schema: {type=object,properties={status={type=string}}}
:return-error 404: If the dataset does not exist.
"""
dataset_key = request.form.get("key", "") if not key else key
try:
dataset = DataSet(key=dataset_key, db=db)
except TypeError:
return error(404, error="Dataset does not exist.")
if not current_user.is_admin() and not current_user.get_id() == dataset.parameters.get("user"):
return error(403, message="Not allowed")
# if there is an active or queued job for some child dataset, cancel and
# delete it
children = dataset.get_all_children()
for child in children:
try:
job = Job.get_by_remote_ID(child.key, database=db, jobtype=child.type)
call_api("cancel-job", {"remote_id": child.key, "jobtype": dataset.type, "level": BasicWorker.INTERRUPT_CANCEL})
job.finish()
except JobNotFoundException:
pass
# now cancel and delete the job for this one (if it exists)
try:
job = Job.get_by_remote_ID(dataset.key, database=db, jobtype=dataset.type)
call_api("cancel-job", {"remote_id": dataset.key, "jobtype": dataset.type, "level": BasicWorker.INTERRUPT_CANCEL})
except JobNotFoundException:
pass
# and delete the dataset and child datasets
dataset.delete()
return jsonify({"status": "success", "key": dataset.key})
description="Deletes a query, the corresponding job, and any sub-queries.")
cli.add_argument("-k", "--key", required=True, help="Query key to delete.")
cli.add_argument(
"-q",
"--quiet",
type=bool,
default=False,
help="Whether to skip asking for confirmation. Defaults to false.")
args = cli.parse_args()
if not args.quiet:
confirm = input(
"This will delete the query, and any sub-queries. Are you sure? (y/n)")
if confirm.strip().lower() != "y":
sys.exit(0)
logger = Logger()
database = Database(logger=logger, appname="delete-query")
# Initialize query
try:
parent = DataSet(key=args.key, db=database)
except TypeError:
print("No query found with that key.")
sys.exit(1)
parent.delete()
print(
"Done. Note that running jobs for the queries above are not stopped; you will have to wait for them to finish on their own."
)