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()
cli.add_argument("-k", "--key", required=True, help="Dataset 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 dataset and any child datasets. Are you sure? (y/n)"
)
if confirm.strip().lower() != "y":
sys.exit(0)
logger = Logger()
database = Database(logger=logger, appname="delete-dataset")
# Initialize query
try:
parent = DataSet(key=args.key, db=database)
except TypeError:
print("No dataset found with that key.")
sys.exit(1)
parent.delete()
print(
"Done. Note that running jobs for the datasets above are not stopped; you will have to wait for them to finish on their own."
)