def test_notify_file_archiver(self, expand_curie):
archive_submission = MagicMock(ArchiveSubmission)
archive_submission.get_url = MagicMock(return_value='url')
mock_manifest = self._mock_manifest(self.base_manifest)
mock_manifest.get_library_preparation_protocol = MagicMock(
return_value=self.base_manifest.get(
'library_preparation_protocol_10x'))
seq_files = self.base_manifest.get('files')
seq_file = copy.deepcopy(seq_files[0])
seq_file['content']['file_core']['file_name'] = "R2.fastq.gz"
seq_files.append(seq_file)
mock_manifest.get_files = MagicMock(return_value=seq_files)
ingest_api = copy.deepcopy(self.ingest_api)
ingest_api.get_manifest_by_id = MagicMock(
return_value={'bundleUuid': 'dcp_uuid'})
archiver = IngestArchiver(ingest_api=ingest_api,
dsp_api=self.dsp_api,
ontology_api=self.ontology_api)
archiver.get_manifest = MagicMock(return_value=mock_manifest)
entity_map = archiver.convert(['bundle_uuid'])
archive_submission.converted_entities = list(
entity_map.get_converted_entities())
archive_submission.entity_map = entity_map
messages = archiver.notify_file_archiver(archive_submission)
expected = {
"dsp_api_url": 'dsp_url',
"dcp_bundle_uuid": 'dcp_uuid',
'submission_url': 'url',
'files': [{
'name': 'dummy_manifest_id.bam'
}],
'conversion': {
'output_name':
'dummy_manifest_id.bam',
'schema':
'10xV2',
'inputs': [{
'name':
'R1.fastq.gz',
'read_index':
'read1',
'cloud_url':
's3://org-humancellatlas-upload-dev/8cd91cfd-0374-454f-ac83-8db6581d2706/R1.fastq.gz'
}, {
'name':
'R2.fastq.gz',
'read_index':
'read1',
'cloud_url':
's3://org-humancellatlas-upload-dev/8cd91cfd-0374-454f-ac83-8db6581d2706/R1.fastq.gz'
}]
},
'manifest_id': 'dummy_manifest_id'
}
self.assertTrue(messages)
self.assertEqual(expected, messages[0])
def test_get_archivable_entities(self, expand_curie):
mock_manifest = self._mock_manifest(self.base_manifest)
archiver = IngestArchiver(ontology_api=self.ontology_api,
ingest_api=self.ingest_api,
dsp_api=self.dsp_api,
exclude_types=['sequencingRun'])
archiver.get_manifest = MagicMock(return_value=mock_manifest)
entity_map = archiver.convert(['manifest_id'])
entities_by_type = entity_map.entities_dict_type
self.assertTrue(entities_by_type.get('project'))
self.assertTrue(entities_by_type.get('study'))
self.assertTrue(entities_by_type.get('sample'))
self.assertTrue(entities_by_type.get('sequencingExperiment'))
def test_archive(self):
mock_manifest = self._mock_manifest(self.base_manifest)
archiver = IngestArchiver(ontology_api=self.ontology_api,
ingest_api=self.ingest_api,
dsp_api=self.dsp_api,
exclude_types=['sequencingRun'])
archiver.get_manifest = MagicMock(return_value=mock_manifest)
entity_map = archiver.convert(['bundle_uuid'])
archive_submission = archiver.archive(entity_map)
self.assertTrue(archive_submission.is_completed)
for entity in archive_submission.entity_map.get_entities():
self.assertTrue(archive_submission.accession_map.get(entity.id),
f"{entity.id} has no accession.")
def test_validate_and_complete_submission(self):
mock_manifest = self._mock_manifest(self.base_manifest)
archiver = IngestArchiver(ontology_api=self.ontology_api,
ingest_api=self.ingest_api,
dsp_api=self.dsp_api,
exclude_types=['sequencingRun'])
archiver.get_manifest = MagicMock(return_value=mock_manifest)
entity_map = archiver.convert(['bundle_uuid'])
archive_submission, _ = archiver.archive_metadata(entity_map)
url = archive_submission.get_url()
archive_submission = archiver.complete_submission(
dsp_submission_url=url)
self.assertTrue(archive_submission.is_completed)
self.assertTrue(archive_submission.accession_map)
def test_archive_skip_metadata_with_accessions(self):
with open(config.JSON_DIR + 'hca/biomaterial_with_accessions.json',
encoding=config.ENCODING) as data_file:
biomaterials = json.loads(data_file.read())
biomaterial_manifest = {'biomaterials': biomaterials}
mock_manifest = self._mock_manifest(biomaterial_manifest)
archiver = IngestArchiver(ontology_api=self.ontology_api,
ingest_api=self.ingest_api,
dsp_api=self.dsp_api,
exclude_types=['sequencingRun'])
archiver.get_manifest = MagicMock(return_value=mock_manifest)
entity_map = archiver.convert('')
archive_submission = archiver.archive(entity_map)
self.assertTrue(archive_submission.is_completed)
self.assertTrue(archive_submission.errors)
self.assertFalse(archive_submission.processing_result)
def async_archive(ingest_api: IngestAPI, archiver: IngestArchiver,
submission_uuid: str):
logger.info('Starting...')
start = time.time()
manifests = ingest_api.get_manifest_ids_from_submission(submission_uuid)
try:
entity_map: ArchiveEntityMap = archiver.convert(manifests)
dsp_submission, ingest_tracker = archiver.archive_metadata(entity_map)
archiver.notify_file_archiver(dsp_submission)
ingest_tracker.patch_archive_submission({
'submissionUuid':
submission_uuid,
'fileUploadPlan':
dsp_submission.file_upload_info
})
end = time.time()
logger.info(
f'Creating DSP submission for {submission_uuid} finished in {end - start}s'
)
except Exception as e:
logger.exception(e)
raise
class ArchiveCLI:
def __init__(self, alias_prefix, output_dir, exclude_types, no_validation):
self.manifests = []
self.ingest_api = IngestAPI(config.INGEST_API_URL)
self.dsp_api = DataSubmissionPortal(config.DSP_API_URL)
now = datetime.datetime.utcnow().strftime("%Y-%m-%dT%H%M%S")
self.output_dir = output_dir if output_dir else f"output/ARCHIVER_{now}"
self.archiver = IngestArchiver(ingest_api=self.ingest_api,
dsp_api=self.dsp_api,
exclude_types=self.split_exclude_types(exclude_types),
alias_prefix=alias_prefix,
dsp_validation=not no_validation)
def get_manifests_from_project(self, project_uuid):
logging.info(f'GETTING MANIFESTS FOR PROJECT: {project_uuid}')
self.manifests = self.ingest_api.get_manifest_ids_from_project(project_uuid=project_uuid)
def get_manifests_from_submission(self, submission_uuid):
logging.info(f'GETTING MANIFESTS FOR SUBMISSION: {submission_uuid}')
self.manifests = self.ingest_api.get_manifest_ids_from_submission(submission_uuid)
def get_manifests_from_list(self, manifest_list_file):
logging.info(f'GETTING MANIFESTS FROM FILE: {manifest_list_file}')
with open(manifest_list_file) as f:
content = f.readlines()
parsed_manifest_list = [x.strip() for x in content]
self.manifests = parsed_manifest_list
def complete_submission(self, dsp_submission_url):
logging.info(f'##################### COMPLETING DSP SUBMISSION {dsp_submission_url}')
archive_submission = ArchiveSubmission(dsp_api=self.archiver.dsp_api, dsp_submission_url=dsp_submission_url)
ingest_archive_submission = self.ingest_api.get_archive_submission_by_dsp_uuid(archive_submission.dsp_uuid)
ingest_entities = self.ingest_api.get_related_entity(ingest_archive_submission, 'entities', 'archiveEntities')
entity_map = ArchiveEntityMap.map_from_ingest_entities(ingest_entities)
archive_submission = self.archiver.complete_submission(dsp_submission_url, entity_map)
report = archive_submission.generate_report()
self.save_dict_to_file(f'COMPLETE_SUBMISSION_{archive_submission.dsp_uuid}', report)
def build_map(self):
logging.info(f'Processing {len(self.manifests)} manifests:\n' + "\n".join(map(str, self.manifests)))
entity_map: ArchiveEntityMap = self.archiver.convert(self.manifests)
summary = entity_map.get_conversion_summary()
logging.info(f'Entities to be converted: {json.dumps(summary)}')
report = entity_map.generate_report()
logging.info("Saving Report file...")
self.save_dict_to_file("REPORT", report)
return entity_map
def load_map(self, load_path):
logging.info(f'Loading Entity Map: {load_path}')
file_content: dict = self.load_dict_from_file(load_path)
if file_content.get('entities'):
return ArchiveEntityMap.map_from_report(file_content['entities'])
logging.error(f"--load_path files does not have an entities object: {file_content}")
exit(2)
def validate_submission(self, entity_map: ArchiveEntityMap, submit, ingest_submission_uuid=None):
archive_submission, ingest_archive_submission = self.archiver.archive_metadata(entity_map)
all_messages = self.archiver.notify_file_archiver(archive_submission)
ingest_archive_submission.patch_archive_submission({
'submissionUuid': ingest_submission_uuid,
'fileUploadPlan': archive_submission.file_upload_info
})
report = archive_submission.generate_report()
logging.info("Updating Report file...")
self.save_dict_to_file("REPORT", report)
logging.info("##################### FILE ARCHIVER NOTIFICATION")
self.save_dict_to_file("FILE_UPLOAD_INFO", {"jobs": all_messages})
if submit:
archive_submission.validate_and_submit()
else:
archive_submission.validate()
def generate_validation_error_report(self, dsp_submission_url):
submission = ArchiveSubmission(dsp_api=self.archiver.dsp_api, dsp_submission_url=dsp_submission_url)
self.save_dict_to_file("VALIDATION_ERROR_REPORT", submission.get_validation_error_report())
def save_dict_to_file(self, file_name, json_content):
if not self.output_dir:
return
directory = os.path.abspath(self.output_dir)
if not os.path.exists(directory):
os.makedirs(directory)
file = directory + "/" + file_name + ".json"
if os.path.exists(file):
os.remove(file)
with open(file, "w") as open_file:
json.dump(json_content, open_file, indent=4)
open_file.close()
logging.info(f"Saved to {directory}/{file_name}.json!")
@staticmethod
def load_dict_from_file(file_path):
path = os.path.abspath(file_path)
if os.path.exists(path) and os.path.isfile(path):
with open(path, 'r') as open_file:
content = open_file.read()
return json.loads(content)
else:
logging.error(f"--load_path does not exist or is not a file: {file_path}")
exit(2)
@staticmethod
def split_exclude_types(exclude_types):
if exclude_types:
exclude_types = [x.strip() for x in exclude_types.split(',')]
logging.warning(f"Excluding {', '.join(exclude_types)}")
return exclude_types