def print_protocol_info(self,
entity,
entity_type,
include_uuid=False,
include_test_group=False):
group_id = self.get_dict_attrib(
entity, "provenance_group_uuid").strip().lower()
if string_helper.isBlank(group_id):
return
if not include_test_group:
if self.test_group_id == group_id:
return
group_name = self.get_dict_attrib(entity, "provenance_group_name")
display_doi = self.get_dict_attrib(entity, "display_doi")
uuid = self.get_dict_attrib(entity, "uuid")
display_id = self.get_dict_attrib(entity, "hubmap_identifier")
protocols = self.get_dict_attrib(entity, "protocols")
prot_files = []
prot_globus_urls = []
prot_dois = []
if not string_helper.isBlank(protocols):
prots = json.loads(protocols.replace("'", '"'))
for prot in prots:
if "protocol_file" in prot and not string_helper.isBlank(
prot['protocol_file']):
prot_files.append(prot['protocol_file'])
prot_globus_urls.append(
self.convert_to_globus_url(prot['protocol_file']))
if "protocol_url" in prot and not string_helper.isBlank(
prot['protocol_url']):
prot_dois.append(prot['protocol_url'])
protocol = self.get_dict_attrib(entity, "protocol")
if not string_helper.isBlank(protocol):
prot_dois.append(protocol)
protocol_file = self.get_dict_attrib(entity, "protocol_file")
if not string_helper.isBlank(protocol_file):
prot_files.append(protocol_file)
prot_globus_urls.append(self.convert_to_globus_url(protocol_file))
vals = []
vals.append(entity_type)
vals.append(group_name)
vals.append(display_id)
vals.append(display_doi)
if include_uuid:
vals.append(uuid)
vals.append(string_helper.listToDelimited(prot_dois,
delimitChar=" | "))
vals.append(
string_helper.listToDelimited(prot_globus_urls, delimitChar=" | "))
vals.append(
string_helper.listToDelimited(prot_files, delimitChar=" | "))
print(string_helper.listToCommaSeparated(vals))
def update_collection(self, uuid, record):
if (HubmapConst.UUID_ATTRIBUTE in record
or HubmapConst.DOI_ATTRIBUTE in record
or HubmapConst.DISPLAY_DOI_ATTRIBUTE in record
or HubmapConst.ENTITY_TYPE_ATTRIBUTE in record):
raise HTTPException("ID attributes cannot be changed", 400)
not_allowed = []
for attrib in record.keys():
if not attrib in self.allowed_collection_update_attributes:
not_allowed.append(attrib)
if len(not_allowed) > 0:
raise HTTPException(
"Attribute(s) not allowed: " +
string_helper.listToDelimited(not_allowed, " "), 400)
if HubmapConst.COLLECTION_CREATORS_ATTRIBUTE in record:
creators = record[HubmapConst.COLLECTION_CREATORS_ATTRIBUTE]
for creator in creators:
for attrib in creator.keys():
if not attrib in self.allowed_creator_attributes and not attrib in not_allowed:
not_allowed.append(attrib)
if len(not_allowed) > 0:
raise HTTPException(
"Creator Aattribute(s) not allowed: " +
string_helper.listToDelimited(not_allowed, " "), 400)
save_record = {}
for attrib in record.keys():
if attrib == HubmapConst.COLLECTION_CREATORS_ATTRIBUTE:
save_record[attrib] = json.dumps(record[attrib])
else:
save_record[attrib] = record[attrib]
rval = self.get_py2neo_conn().run(
"match(c:Collection {uuid: {uuid}}) set c += {params} return c.uuid",
uuid=uuid,
params=save_record).data()
if len(rval) == 0:
raise HTTPException(
"Update failed for collection with uuid " + uuid +
". UUID possibly not found.", 400)
else:
if rval[0]['c.uuid'] != uuid:
raise HTTPException(
"Update failed, wrong uuid returned while trying to update "
+ uuid + " returned: " + rval[0]['c.uuid'])
def write_tsv(row, datatype):
uuid = row['hmuuid']
if string_helper.isBlank(uuid):
print("ERROR: no uuid for row in datatype: " + datatype)
return
output_path = output_dir + "/" + row['hmuuid'] + "-" + datatype + ".tsv"
with open(output_path, 'w') as writer:
keys = []
data = []
base_submission_path = None
if not uuid in dataset_info_by_uuid:
print("WARNING: dataset information not found for " + uuid)
else:
base_submission_path = dataset_info_by_uuid[uuid]['local_path']
if not base_submission_path.lower().startswith('/hive/hubmap/lz'):
print(
"WARNING: dataset local path doesn't start with /hive/hubmap/lz: "
+ uuid)
else:
base_submission_path = base_submission_path[15:].lower()
for key in row.keys():
if not key == 'hmuuid':
val = row[key]
keyl = key.lower()
if keyl == 'metadata_path' or key == 'data_path':
if base_submission_path is None:
print("ERROR: no base_submittion_path set on " + key +
": " + val)
if val is None:
print("WARNING: no path found for " + key +
" for type: " + datatype + " on uuid: " + uuid)
elif not val.lower().startswith(base_submission_path):
print("WARNING: path " + key + ": " + val +
" does not start with base path: " +
base_submission_path)
val = val[len(base_submission_path):]
keys.append(key)
data.append(val)
writer.write(
string_helper.listToDelimited(keys, delimitChar='\t') + '\n')
writer.write(
string_helper.listToDelimited(data, delimitChar='\t') + '\n')
def resolveToMultipleUUIDs(hmids):
underscore_idx = hmids.rfind("_")
dash_idx = hmids.rfind("-")
if underscore_idx == -1 or dash_idx == -1 or dash_idx > underscore_idx:
return "No UUIDs Found"
baseId = getDisplayId(hmids)
idx1 = hmids[dash_idx + 1:underscore_idx]
idx2 = hmids[underscore_idx + 1:]
if not idx1.isdigit() or not idx2.isdigit():
return "No UUIDs Found"
uuids = []
for idx in range(int(idx1), int(idx2) + 1):
uuids.append(resolveToUUID(baseId + "-" + str(idx)))
suuids = string_helper.listToDelimited(uuids, "|")
return suuids
last_dot = output_base.rfind(".")
if not last_dot == -1:
numeric = output_base[last_dot + 1:]
if numeric.isdigit():
next_file = int(numeric) + 1
output_base = output_base[:last_dot]
else:
next_file = 1
else:
next_file = 1
output_path = output_base + "." + str(next_file) +".tsv"
while os.path.isfile(output_path):
next_file = next_file + 1
output_path = output_base + "." + str(next_file) +".tsv"
with open(output_path, 'w') as writer:
first = True
for info_line in ingest_worker.dataset_info:
if first:
first = False
line_keys = info_line.keys()
writer.write(string_helper.listToDelimited(line_keys, delimitChar='\t') + '\n')
line = []
for key in line_keys:
val = info_line[key]
if val is None: val = ''
line.append(val)
writer.write(string_helper.listToDelimited(line, delimitChar='\t') + '\n')