def transfer_inputs(dataset_ids, results_ids, from_storage, to_storage):
tantalus_api = TantalusApi()
for dataset_id in dataset_ids:
transfer_dataset(tantalus_api, dataset_id, 'sequencedataset', from_storage, to_storage)
for results_id in results_ids:
transfer_dataset(tantalus_api, results_id, 'resultsdataset', from_storage, to_storage)
def download_datasets(results_type,
from_storage_name,
to_storage_name,
dataset_id=None,
jira_ticket=None):
''' Download a set of datasets by type.
'''
tantalus_api = TantalusApi()
if dataset_id is not None:
datasets = tantalus_api.list('results', id=dataset_id)
elif jira_ticket is not None:
datasets = tantalus_api.list('results',
results_type=results_type,
analysis__jira_ticket=jira_ticket)
else:
datasets = tantalus_api.list('results', results_type=results_type)
dataset_ids = list()
for dataset in datasets:
dataset_ids.append(dataset['id'])
# Download most recent first
dataset_ids = reversed(sorted(dataset_ids))
failed = False
for dataset_id in dataset_ids:
try:
transfer_dataset(tantalus_api, dataset_id, 'resultsdataset',
from_storage_name, to_storage_name)
except:
logging.exception(f'failed to download {dataset_id}')
failed = True
if failed:
raise Exception('one or more downloads failed')
def add_generic_results(filepaths,
storage_name,
results_name,
results_type,
results_version,
sample_ids=(),
library_ids=(),
analysis_pk=None,
recursive=False,
tag_name=None,
update=False,
remote_storage_name=None):
tantalus_api = TantalusApi()
sample_pks = []
for sample_id in sample_ids:
samples = tantalus_api.get(
"sample",
sample_id=sample_id,
)
sample_pks.append(samples['id'])
library_pks = []
for library_id in library_ids:
librarys = tantalus_api.get(
"dna_library",
library_id=library_id,
)
library_pks.append(librarys['id'])
#Add the file resource to tantalus
file_resource_pks = []
for filepath in filepaths:
if recursive:
logging.info("Recursing directory {}".format(filepath))
add_filepaths = []
for (dirpath, dirnames, filenames) in os.walk(filepath):
for filename in filenames:
add_filepaths.append(os.path.join(dirpath, filename))
else:
add_filepaths = [filepath]
for add_filepath in add_filepaths:
logging.info(
"Adding file resource for {} to Tantalus".format(add_filepath))
resource, instance = tantalus_api.add_file(
storage_name=storage_name,
filepath=add_filepath,
update=update,
)
file_resource_pks.append(resource["id"])
results_dataset_fields = dict(
name=results_name,
results_type=results_type,
results_version=results_version,
analysis=analysis_pk,
samples=sample_pks,
libraries=library_pks,
file_resources=file_resource_pks,
)
#Add the dataset to tantalus
try:
results_id = tantalus_api.get(
"results", name=results_dataset_fields["name"])["id"]
except NotFoundError:
results_id = None
if update and results_id is not None:
logging.warning("results dataset {} exists, updating".format(
results_dataset_fields["name"]))
results_dataset = tantalus_api.update("results",
id=results_id,
**results_dataset_fields)
else:
logging.info("creating results dataset {}".format(
results_dataset_fields["name"]))
results_dataset = tantalus_api.get_or_create("results",
**results_dataset_fields)
if tag_name is not None:
tantalus_api.tag(tag_name, resultsdataset_set=[results_id])
logging.info("Succesfully created sequence dataset with ID {}".format(
results_dataset["id"]))
if remote_storage_name is not None:
transfer_files.transfer_dataset(tantalus_api, results_dataset['id'],
"resultsdataset", storage_name,
remote_storage_name)
return results_dataset
