def test_get_dataset_uuid(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
uuid = getDataSetUuid(ds_file)
assert uuid == ds.uuid
with open(ds_file, "w") as out:
out.write("hello world!")
uuid = getDataSetUuid(ds_file)
assert uuid is None
def test_get_dataset_uuid(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
uuid = getDataSetUuid(ds_file)
self.assertEqual(uuid, ds.uuid)
with open(ds_file, "w") as out:
out.write("hello world!")
uuid = getDataSetUuid(ds_file)
self.assertEqual(uuid, None)
def _get_or_create_uuid_from_file(path, file_type):
"""
Extract the uuid from the DataSet or Report, or assign a new UUID
:param path: Path to file
:rtype: str
:return: uuid string
"""
if file_type.file_type_id == FileTypes.REPORT.file_type_id:
return _get_report_uuid(path)
elif file_type.file_type_id in FileTypes.ALL_DATASET_TYPES():
return getDataSetUuid(path)
else:
return uuid.uuid4()
def _get_or_create_uuid_from_file(path, file_type):
"""
Extract the uuid from the DataSet or Report, or assign a new UUID
:param path: Path to file
:rtype: str
:return: uuid string
"""
if file_type.file_type_id == FileTypes.REPORT.file_type_id:
return _get_report_uuid(path)
elif file_type.file_type_id in FileTypes.ALL_DATASET_TYPES():
return getDataSetUuid(path)
else:
return uuid.uuid4()
def test_datastore_dataset_file_uuid(self):
FILE_TYPE_IDS = ["DS_SUBREADS_H5", "DS_SUBREADS", "DS_CCS", "DS_REF",
"DS_ALIGN", "DS_CONTIG", "DS_BARCODE", "DS_ALIGN_CCS"]
DATASET_FILE_TYPES = set([getattr(FileTypes, t).file_type_id
for t in FILE_TYPE_IDS])
p = os.path.join(self.job_dir, "workflow", "datastore.json")
with open(p, 'r') as r:
d = json.loads(r.read())
n_tested = 0
for file_info in d['files']:
if file_info['fileTypeId'] in DATASET_FILE_TYPES:
uuid = getDataSetUuid(file_info['path'])
self.assertEqual(uuid, file_info['uniqueId'],
"{p}: {u1} != {u2}".format(
p=file_info['path'],
u1=uuid,
u2=file_info['uniqueId']))
n_tested += 1
if n_tested == 0:
raise unittest.SkipTest("No DataSet XML files in datastore.")
def test_datastore_dataset_file_uuid(self):
"""Test that the DataStore file and the Underlying Report have the same UUID"""
dataset_type_ids = FileTypes.ALL_DATASET_TYPES().keys()
ds = DataStore.load_from_json(_to_ds_json(self.job_dir))
n_tested = 0
for ds_file in ds.files.values():
if ds_file.file_type_id in dataset_type_ids:
path = ds_file.path
dsf_uuid = ds_file.uuid
uuid = getDataSetUuid(path)
self.assertEqual(
uuid, dsf_uuid, "{p}: {u1} != {u2}".format(p=path,
u1=uuid,
u2=dsf_uuid))
n_tested += 1
if n_tested == 0:
raise unittest.SkipTest(
"Warning. No DataSet XML files in datastore.")
def test_datastore_dataset_file_uuid(self):
FILE_TYPE_IDS = [
"DS_SUBREADS_H5", "DS_SUBREADS", "DS_CCS", "DS_REF", "DS_ALIGN",
"DS_CONTIG", "DS_BARCODE", "DS_ALIGN_CCS"
]
DATASET_FILE_TYPES = set(
[getattr(FileTypes, t).file_type_id for t in FILE_TYPE_IDS])
p = os.path.join(self.job_dir, "workflow", "datastore.json")
with open(p, 'r') as r:
d = json.loads(r.read())
n_tested = 0
for file_info in d['files']:
if file_info['fileTypeId'] in DATASET_FILE_TYPES:
uuid = getDataSetUuid(file_info['path'])
self.assertEqual(
uuid, file_info['uniqueId'],
"{p}: {u1} != {u2}".format(p=file_info['path'],
u1=uuid,
u2=file_info['uniqueId']))
n_tested += 1
if n_tested == 0:
raise unittest.SkipTest("No DataSet XML files in datastore.")