def check_ENCODE(self, idList, connection, otherIdList=[], bothDicts={}):
for pmid in idList:
extraData = bothDicts.get(pmid)
ENCODEvalue = encodedcc.get_ENCODE("/search/?type=publication&searchTerm=PMID:" + pmid, connection)
if ENCODEvalue.get("@graph"):
log = "PMID " + pmid + " is listed in ENCODE"
logger.info('%s' % log)
uuid = ENCODEvalue.get("@graph")[0].get("uuid")
if not self.CREATE_ONLY:
self.compare_entrez_ENCODE(uuid, pmid, connection, extraData)
else:
if self.CREATE_ONLY:
self.get_entrez([pmid])
titleEntrez = self.entrezDict[pmid].get("title")
found = False
for otherID in otherIdList:
titleENCODE = encodedcc.get_ENCODE("/search/?type=publication&searchTerm=" + otherID, connection)
if titleENCODE.get("title") == titleEntrez:
log = pmid + " is in ENCODE by a different name " + titleENCODE.get("uuid")
logger.warning('%s' % log)
self.compare_entrez_ENCODE(titleENCODE.get("uuid"), pmid, connection, extraData)
if self.UPDATE:
newIdent = titleENCODE.get("identifiers")
newIdent.append("PMID:" + pmid)
patch_dict = {"identifiers": newIdent}
encodedcc.patch_ENCODE(titleENCODE.get("uuid"), connection, patch_dict)
found = True
if found is False:
log = "This publication is not listed in ENCODE " + pmid
logger.warning('%s' % log)
if self.CREATE:
self.POST_COUNT += 1
pmidData = self.entrezDict[pmid]
log = "POSTing the new object: " + pmid
logger.info('%s' % log)
post_dict = {
"title": pmidData.get("title"),
"abstract": pmidData.get("abstract"),
"submitted_by": "/users/8b1f8780-b5d6-4fb7-a5a2-ddcec9054288/",
"lab": "/labs/encode-consortium/",
"award": "/awards/ENCODE/",
"categories": extraData.get("categories"),
"published_by": extraData.get("published_by"),
"date_published": pmidData.get("date_published"),
"authors": pmidData.get("authors"),
"identifiers": ["PMID:" + pmid],
"journal": pmidData.get("journal"),
"volume": pmidData.get("volume"),
"issue": pmidData.get("issue"),
"page": pmidData.get("page"),
"status": "published"
}
if extraData.get("data_used"):
post_dict["data_used"] = extraData.get("data_used")
encodedcc.new_ENCODE(connection, "publications", post_dict)
def check_ENCODE(self, idList, connection, otherIdList=[], bothDicts={}):
for pmid in idList:
extraData = bothDicts.get(pmid)
ENCODEvalue = encodedcc.get_ENCODE("/search/?type=publication&searchTerm=PMID:" + pmid, connection)
if ENCODEvalue.get("@graph"):
log = "PMID " + pmid + " is listed in ENCODE"
logger.info('%s' % log)
uuid = ENCODEvalue.get("@graph")[0].get("uuid")
if not self.CREATE_ONLY:
self.compare_entrez_ENCODE(uuid, pmid, connection, extraData)
else:
if self.CREATE_ONLY:
self.get_entrez([pmid])
titleEntrez = self.entrezDict[pmid].get("title")
found = False
for otherID in otherIdList:
titleENCODE = encodedcc.get_ENCODE("/search/?type=publication&searchTerm=" + otherID, connection)
if titleENCODE.get("title") == titleEntrez:
log = pmid + " is in ENCODE by a different name " + titleENCODE.get("uuid")
logger.warning('%s' % log)
self.compare_entrez_ENCODE(titleENCODE.get("uuid"), pmid, connection, extraData)
if self.UPDATE:
newIdent = titleENCODE.get("identifiers")
newIdent.append("PMID:" + pmid)
patch_dict = {"identifiers": newIdent}
encodedcc.patch_ENCODE(titleENCODE.get("uuid"), connection, patch_dict)
found = True
if found is False:
log = "This publication is not listed in ENCODE " + pmid
logger.warning('%s' % log)
if self.CREATE:
self.POST_COUNT += 1
pmidData = self.entrezDict[pmid]
log = "POSTing the new object: " + pmid
logger.info('%s' % log)
post_dict = {
"title": pmidData.get("title"),
"abstract": pmidData.get("abstract"),
"submitted_by": "/users/8b1f8780-b5d6-4fb7-a5a2-ddcec9054288/",
"lab": "/labs/encode-consortium/",
"award": "/awards/ENCODE/",
"categories": extraData.get("categories"),
"published_by": extraData.get("published_by"),
"date_published": pmidData.get("date_published"),
"authors": pmidData.get("authors"),
"identifiers": ["PMID:" + pmid],
"journal": pmidData.get("journal"),
"volume": pmidData.get("volume"),
"issue": pmidData.get("issue"),
"page": pmidData.get("page"),
"status": "published"
}
if extraData.get("data_used"):
post_dict["data_used"] = extraData.get("data_used")
encodedcc.new_ENCODE(connection, "publications", post_dict)
def file_manager(key, value, connection, obj_type):
filename = key.split("/")[-1]
print("Downloading {}".format(filename))
r = requests.get(key)
with open(filename, "wb") as outfile:
outfile.write(r.content)
if obj_type == "Biosample":
filepart = filename.split("-")[0]
else:
filepart = filename.split("-")[1]
attach = attachment(filename)
temp = "_".join(key.split("/")[-2:])
aliases = ["brenton-graveley:" + temp]
if (encodedcc.get_ENCODE(quote(aliases[0]),
connection)['status']) != 'error':
removing_patch = {'status': 'deleted', 'aliases': []}
print('DELETING ' + aliases[0] + ' ' + str(removing_patch))
encodedcc.patch_ENCODE(quote(aliases[0]), connection, removing_patch)
upload = {
"aliases":
aliases,
"attachment":
attach,
"award":
"U54HG007005",
"document_type":
"general protocol",
"lab":
"/labs/brenton-graveley/",
"status":
"released",
"description":
"{obj_type} protocol for {filepart} shRNA followed by RNA-seq".format(
obj_type=obj_type, filepart=filepart),
}
print("Uploading {} as {}".format(filename, aliases[0]))
encodedcc.new_ENCODE(connection, "Document", upload)
print("Patching {} with document {}".format(value, aliases[0]))
if obj_type == "Biosample":
docs = {"protocol_documents": aliases}
else:
docs = {"documents": aliases}
encodedcc.patch_ENCODE(quote(value), connection, docs)
print("Removing document {}".format(filename))
subprocess.run(["rm", filename])
'''
def file_manager(key, value, connection, obj_type):
filename = key.split("/")[-1]
print("Downloading {}".format(filename))
r = requests.get(key)
with open(filename, "wb") as outfile:
outfile.write(r.content)
if obj_type == "Biosample":
filepart = filename.split("-")[0]
else:
filepart = filename.split("-")[1]
attach = attachment(filename)
temp = "_".join(key.split("/")[-2:])
aliases = ["brenton-graveley:" + temp]
if (encodedcc.get_ENCODE(quote(aliases[0]), connection)['status']) != 'error':
removing_patch = {'status':'deleted',
'aliases': []}
print ('DELETING ' + aliases[0] + ' ' + str(removing_patch))
encodedcc.patch_ENCODE(quote(aliases[0]), connection, removing_patch)
upload = {"aliases": aliases,
"attachment": attach,
"award": "U54HG007005",
"document_type": "general protocol",
"lab": "/labs/brenton-graveley/",
"status": "released",
"description": "{obj_type} protocol for {filepart} shRNA followed by RNA-seq".format(obj_type=obj_type, filepart=filepart),
}
print("Uploading {} as {}".format(filename, aliases[0]))
encodedcc.new_ENCODE(connection, "Document", upload)
print("Patching {} with document {}".format(value, aliases[0]))
if obj_type == "Biosample":
docs = {"protocol_documents": aliases}
else:
docs = {"documents": aliases}
encodedcc.patch_ENCODE(quote(value), connection, docs)
print("Removing document {}".format(filename))
subprocess.run(["rm", filename])
'''
def excel_reader(datafile, sheet, update, connection, patchall):
row = reader(datafile, sheetname=sheet)
keys = next(row) # grab the first row of headers
total = 0
error = 0
success = 0
patch = 0
for values in row:
total += 1
post_json = dict(zip(keys, values))
post_json = dict_patcher(post_json)
# add attchments here
if post_json.get("attachment"):
attach = attachment(post_json["attachment"])
post_json["attachment"] = attach
print(post_json)
temp = {}
if post_json.get("uuid"):
temp = encodedcc.get_ENCODE(post_json["uuid"], connection)
elif post_json.get("aliases"):
temp = encodedcc.get_ENCODE(quote(post_json["aliases"][0]),
connection)
elif post_json.get("accession"):
temp = encodedcc.get_ENCODE(post_json["accession"], connection)
elif post_json.get("@id"):
temp = encodedcc.get_ENCODE(post_json["@id"], connection)
if temp.get("uuid"):
if patchall:
e = encodedcc.patch_ENCODE(temp["uuid"], connection, post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
patch += 1
else:
print("Object {} already exists. Would you like to patch it instead?".format(temp["uuid"]))
i = input("PATCH? y/n ")
if i.lower() == "y":
e = encodedcc.patch_ENCODE(temp["uuid"], connection, post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
patch += 1
else:
if update:
print("POSTing data!")
e = encodedcc.new_ENCODE(connection, sheet, post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
print("{sheet}: {success} out of {total} posted, {error} errors, {patch} patched".format(
sheet=sheet.upper(), success=success, total=total, error=error, patch=patch))
def excel_reader(datafile, sheet, update, connection, patchall):
row = reader(datafile, sheetname=sheet)
keys = next(row) # grab the first row of headers
total = 0
error = 0
success = 0
patch = 0
json_properties = encodedcc.get_ENCODE('/profiles/{}.json'.format(sheet),
connection)['properties']
new_accessions_aliases = []
failed_postings = []
for values in row:
total += 1
post_json = dict(zip(keys, values))
post_json = dict_patcher(post_json)
post_json = expose_objects(post_json, json_properties)
# add attchments here
if post_json.get("attachment"):
attach = attachment(post_json["attachment"])
post_json["attachment"] = attach
print(post_json)
temp = {}
# Silence get_ENCODE failures.
with encodedcc.print_muted():
if post_json.get("uuid"):
temp = encodedcc.get_ENCODE(post_json["uuid"], connection)
elif post_json.get("aliases"):
temp = encodedcc.get_ENCODE(quote(post_json["aliases"][0]),
connection)
elif post_json.get("accession"):
temp = encodedcc.get_ENCODE(post_json["accession"], connection)
elif post_json.get("@id"):
temp = encodedcc.get_ENCODE(post_json["@id"], connection)
if temp.get("uuid"):
if patchall:
e = encodedcc.patch_ENCODE(temp["uuid"], connection, post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
patch += 1
else:
print(
"Object {} already exists. Would you like to patch it instead?"
.format(temp["uuid"]))
i = input("PATCH? y/n ")
if i.lower() == "y":
e = encodedcc.patch_ENCODE(temp["uuid"], connection,
post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
patch += 1
else:
if update:
print("POSTing data!")
e = encodedcc.new_ENCODE(connection, sheet, post_json)
if e["status"] == "error":
error += 1
failed_postings.append(
post_json.get('aliases', 'alias not specified'))
elif e["status"] == "success":
new_object = e['@graph'][0]
# Print now and later.
print('New accession/UUID: {}'.format(
(new_object.get('accession', new_object.get('uuid')))))
new_accessions_aliases.append(
(new_object.get('accession', new_object.get('uuid')),
new_object.get('aliases')))
success += 1
print(
"{sheet}: {success} out of {total} posted, {error} errors, {patch} patched"
.format(sheet=sheet.upper(),
success=success,
total=total,
error=error,
patch=patch))
if new_accessions_aliases:
print('New accession/UUID and alias:' if len(new_accessions_aliases) ==
1 else 'New accessions/UUIDs and aliases:')
for (accession, alias) in new_accessions_aliases:
if len(alias) == 0:
alias = 'alias not specified'
else:
alias = ', '.join(alias) if isinstance(alias, list) else alias
print(accession, alias)
if failed_postings:
print('Posting failed for {} object(s):'.format(len(failed_postings)))
for alias in failed_postings:
print(', '.join(alias) if isinstance(alias, list) else alias)
def excel_reader(datafile, sheet, update, connection, patchall):
row = reader(datafile, sheetname=sheet)
keys = next(row) # grab the first row of headers
total = 0
error = 0
success = 0
patch = 0
for values in row:
total += 1
post_json = dict(zip(keys, values))
post_json = dict_patcher(post_json)
# add attchments here
if post_json.get("attachment"):
attach = attachment(post_json["attachment"])
post_json["attachment"] = attach
print(post_json)
temp = {}
if post_json.get("uuid"):
temp = encodedcc.get_ENCODE(post_json["uuid"], connection)
elif post_json.get("aliases"):
temp = encodedcc.get_ENCODE(quote(post_json["aliases"][0]),
connection)
elif post_json.get("accession"):
temp = encodedcc.get_ENCODE(post_json["accession"], connection)
elif post_json.get("@id"):
temp = encodedcc.get_ENCODE(post_json["@id"], connection)
if temp.get("uuid"):
if patchall:
e = encodedcc.patch_ENCODE(temp["uuid"], connection, post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
patch += 1
else:
print(
"Object {} already exists. Would you like to patch it instead?"
.format(temp["uuid"]))
i = input("PATCH? y/n ")
if i.lower() == "y":
e = encodedcc.patch_ENCODE(temp["uuid"], connection,
post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
patch += 1
else:
if update:
print("POSTing data!")
e = encodedcc.new_ENCODE(connection, sheet, post_json)
if e["status"] == "error":
error += 1
elif e["status"] == "success":
success += 1
print(
"{sheet}: {success} out of {total} posted, {error} errors, {patch} patched"
.format(sheet=sheet.upper(),
success=success,
total=total,
error=error,
patch=patch))
def main():
import argparse
parser = argparse.ArgumentParser(
description=__doc__,
epilog=EPILOG,
formatter_class=argparse.RawDescriptionHelpFormatter,
)
parser.add_argument(
'--infile',
'-i',
help="File containing the JSON object as a JSON string.")
parser.add_argument('--server', help="Full URL of the server.")
parser.add_argument('--key',
default='default',
help="The keypair identifier from the keyfile. \
Default is --key=default")
parser.add_argument('--keyfile',
default=os.path.expanduser("~/keypairs.json"),
help="The keypair file. Default is --keyfile\
=%s" % (os.path.expanduser("~/keypairs.json")))
parser.add_argument('--authid', help="The HTTP auth ID.")
parser.add_argument('--authpw', help="The HTTP auth PW.")
parser.add_argument(
'--force-put',
default=False,
action='store_true',
help="Force the object to be PUT rather than PATCHed. \
Default is False.")
parser.add_argument('--get-only',
default=False,
action='store_true',
help="Do nothing but get the object and print it. \
Default is False.")
parser.add_argument('--id', help="URI for an object"),
parser.add_argument('--debug',
default=False,
action='store_true',
help="Print debug messages. Default is False.")
parser.add_argument(
'--frame',
help=
"define a frame to get back the JSON object, for use with --id. Default is frame=object",
default="object")
parser.add_argument('--type', help="the object's type")
parser.add_argument(
'--update',
default=False,
action='store_true',
help="Let the script PATCH/POST the data. Default is False")
args = parser.parse_args()
global DEBUG_ON
DEBUG_ON = args.debug
if args.get_only:
GET_ONLY = True
else:
GET_ONLY = False
key = encodedcc.ENC_Key(args.keyfile, args.key)
if args.server and args.authpw and args.authid:
key.server = args.server
key.authid = args.authid
key.authpw = args.authpw
print("Creating authorization data from command line inputs")
connection = encodedcc.ENC_Connection(key)
print("Running on {}".format(connection.server))
if args.update:
print(
"This is an UPDATE run! Data will be PATCHed or POSTed accordingly"
)
else:
print("This is a dry run, no data will be changed")
new_object = False
if args.id:
GET_ONLY = True
print("Taking id to get from --id")
new_json = {}
uuid_response = {}
accession_response = {}
try:
id_response = encodedcc.get_ENCODE(args.id,
connection,
frame=args.frame)
except:
id_response = {}
new_object = True
else:
if args.infile:
infile = open(args.infile, 'r')
else:
infile = sys.stdin
new_json_string = infile.read()
new_json = json.loads(new_json_string)
if args.debug:
encodedcc.pprint_ENCODE(new_json)
if '@id' in new_json:
id_response = encodedcc.get_ENCODE(new_json['@id'], connection)
if id_response.get("code") == 404:
id_response = {}
new_object = True
else:
id_response = {}
new_object = True
if 'uuid' in new_json:
uuid_response = encodedcc.get_ENCODE(new_json['uuid'], connection)
if uuid_response.get("code") == 404:
uuid_response = {}
new_object = True
else:
uuid_response = {}
new_object = True
if 'accession' in new_json:
accession_response = encodedcc.get_ENCODE(new_json['accession'],
connection)
if accession_response.get("code") == 404:
accession_response = {}
new_object = True
else:
accession_response = {}
new_object = True
if new_object:
print(
"No identifier in new JSON object. Assuming POST or PUT with auto-accessioning."
)
object_exists = False
if id_response:
object_exists = True
print("Found matching @id:")
encodedcc.pprint_ENCODE(id_response)
if uuid_response:
object_exists = True
print("Found matching uuid:")
encodedcc.pprint_ENCODE(uuid_response)
if accession_response:
object_exists = True
print("Found matching accession")
encodedcc.pprint_ENCODE(accession_response)
if id_response and uuid_response and (id_response != uuid_response):
print("Existing id/uuid mismatch")
if id_response and accession_response and (id_response !=
accession_response):
print("Existing id/accession mismatch")
if uuid_response and accession_response and (uuid_response !=
accession_response):
print("Existing uuid/accession mismatch")
if new_object and object_exists:
print(
"Conflict: At least one identifier already exists and at least one does not exist"
)
profiles = encodedcc.get_ENCODE("/profiles/", connection)
supported_collections = list(profiles.keys())
if "Dataset" not in supported_collections:
supported_collections.append("Dataset")
type_list = new_json.pop('@type', [])
if args.type:
type_list = [args.type]
if any(type_list):
findit = False
for x in supported_collections:
if x.lower() == type_list[0].lower():
type_list = [x]
findit = True
if findit:
if args.debug:
print("Object will have type of", type_list[0])
else:
print(
"Error! JSON object does not contain one of the supported types"
)
print("Provided type:", type_list[0])
print(
"Please either change the JSON file or define the type with the --type feature"
)
sys.exit(1)
else:
print("No type found for JSON object!")
sys.exit(1)
possible_collections = [x for x in type_list if x in supported_collections]
if possible_collections:
# collection = possible_collections[0] + 's/'
collection = possible_collections[0]
else:
collection = []
if '@id' in new_json:
identifier = new_json.pop('@id')
elif 'uuid' in new_json:
if collection:
identifier = '/' + collection + '/' + new_json['uuid'] + '/'
else:
identifier = '/' + new_json['uuid'] + '/'
elif 'accession' in new_json:
if collection:
identifier = '/' + collection + '/' + new_json['accession'] + '/'
else:
identifier = '/' + new_json['accession'] + '/'
if 'attachment' in new_json:
if 'href' in new_json['attachment']:
pass
else:
try:
filename = new_json['attachment']['download']
print("Setting filename to %s" % (filename))
except:
print("Must specify either href or filename for attachment",
file=sys.stderr)
if new_json['attachment'].get('type'):
mime_type = new_json['attachment'].get('type')
else:
try:
mime_type, encoding = mimetypes.guess_type(filename)
major, minor = mime_type.split('/')
#detected_type = magic.from_file(filename, mime=True)
print("Detected mime type %s" % (mime_type))
except:
print("Failed to detect mime type in file %s" % (filename),
file=sys.stderr)
try:
with open(filename, 'rb') as stream:
print("opened")
newvalue = {
'download':
filename, # Just echoes the given filename as the download name
'type':
mime_type,
'href':
'data:%s;base64,%s' %
(mime_type, b64encode(stream.read()))
}
f = open('tmp', 'w')
print(f, newvalue)
new_json.update({'attachment': newvalue}) # add
except:
print("Cannot open file %s" % (filename), file=sys.stderr)
if object_exists:
if args.force_put:
if not GET_ONLY:
print("Replacing existing object")
if args.update:
e = encodedcc.replace_ENCODE(identifier, connection,
new_json)
print(e)
else:
if not GET_ONLY:
print("PATCHing existing object")
if args.update:
e = encodedcc.patch_ENCODE(identifier, connection,
new_json)
print(e)
elif new_object:
if args.force_put:
if not GET_ONLY:
print("PUT'ing new object")
if args.update:
e = encodedcc.replace_ENCODE(identifier, connection,
new_json)
print(e)
else:
if not GET_ONLY:
print("POST'ing new object")
if not any(collection):
print(
"ERROR: Unable to POST to non-existing collection {}".
format(collection))
sys.exit(1)
if args.update:
e = encodedcc.new_ENCODE(connection, collection, new_json)
print(e)
def main():
import argparse
parser = argparse.ArgumentParser(
description=__doc__, epilog=EPILOG,
formatter_class=argparse.RawDescriptionHelpFormatter,
)
parser.add_argument('--infile', '-i',
help="File containing the JSON object as a JSON string.")
parser.add_argument('--server',
help="Full URL of the server.")
parser.add_argument('--key',
default='default',
help="The keypair identifier from the keyfile. \
Default is --key=default")
parser.add_argument('--keyfile',
default=os.path.expanduser("~/keypairs.json"),
help="The keypair file. Default is --keyfile\
=%s" % (os.path.expanduser("~/keypairs.json")))
parser.add_argument('--authid',
help="The HTTP auth ID.")
parser.add_argument('--authpw',
help="The HTTP auth PW.")
parser.add_argument('--force-put',
default=False,
action='store_true',
help="Force the object to be PUT rather than PATCHed. \
Default is False.")
parser.add_argument('--get-only',
default=False,
action='store_true',
help="Do nothing but get the object and print it. \
Default is False.")
parser.add_argument('--id',
help="URI for an object"),
parser.add_argument('--debug',
default=False,
action='store_true',
help="Print debug messages. Default is False.")
parser.add_argument('--frame',
help="define a frame to get back the JSON object, for use with --id. Default is frame=object",
default="object")
parser.add_argument('--type',
help="the object's type")
args = parser.parse_args()
global DEBUG_ON
DEBUG_ON = args.debug
if args.get_only:
GET_ONLY = True
else:
GET_ONLY = False
key = encodedcc.ENC_Key(args.keyfile, args.key)
connection = encodedcc.ENC_Connection(key)
new_object = False
if args.id:
GET_ONLY = True
print("Taking id to get from --id")
new_json = {}
uuid_response = {}
accession_response = {}
try:
id_response = encodedcc.get_ENCODE(args.id, connection, frame=args.frame)
except:
id_response = {}
new_object = True
else:
if args.infile:
infile = open(args.infile, 'r')
else:
infile = sys.stdin
new_json_string = infile.read()
new_json = json.loads(new_json_string)
if '@id' in new_json:
try:
id_response = encodedcc.get_ENCODE(new_json['@id'], connection)
except:
id_response = {}
new_object = True
else:
id_response = {}
if 'uuid' in new_json:
try:
uuid_response = encodedcc.get_ENCODE(new_json['uuid'], connection)
except:
uuid_response = {}
new_object = True
else:
uuid_response = {}
if 'accession' in new_json:
try:
accession_response = encodedcc.get_ENCODE(new_json['accession'], connection)
except:
accession_response = {}
new_object = True
else:
print("No identifier in new JSON object. Assuming POST or PUT with auto-accessioning.")
new_object = True
accession_response = {}
object_exists = False
if id_response:
object_exists = True
print("Found matching @id:")
encodedcc.pprint_ENCODE(id_response)
if uuid_response:
object_exists = True
print("Found matching uuid:")
encodedcc.pprint_ENCODE(uuid_response)
if accession_response:
object_exists = True
print("Found matching accession")
encodedcc.pprint_ENCODE(accession_response)
if id_response and uuid_response and (id_response != uuid_response):
print("Existing id/uuid mismatch")
if id_response and accession_response and (id_response != accession_response):
print("Existing id/accession mismatch")
if uuid_response and accession_response and (uuid_response != accession_response):
print("Existing uuid/accession mismatch")
if new_object and object_exists:
print("Conflict: At least one identifier already exists and at least one does not exist")
profiles = encodedcc.get_ENCODE("/profiles/", connection)
supported_collections = list(profiles.keys())
if "Dataset" not in supported_collections:
supported_collections.append("Dataset")
type_list = new_json.pop('@type', [])
if args.type:
type_list = [args.type]
if any(type_list):
findit = False
for x in supported_collections:
if x.lower() == type_list[0].lower():
type_list = [x]
findit = True
if findit:
if args.debug:
print("Object will have type of", type_list[0])
else:
print("Error! JSON object does not contain one of the supported types")
print("Provided type:", type_list[0])
print("Please either change the JSON file or define the type with the --type feature")
sys.exit(1)
else:
print("No type found for JSON object!")
sys.exit(1)
possible_collections = [x for x in type_list if x in supported_collections]
if possible_collections:
# collection = possible_collections[0] + 's/'
collection = possible_collections[0]
else:
collection = []
if '@id' in new_json:
identifier = new_json.pop('@id')
elif 'uuid' in new_json:
if collection:
identifier = '/' + collection + '/' + new_json['uuid'] + '/'
else:
identifier = '/' + new_json['uuid'] + '/'
elif 'accession' in new_json:
if collection:
identifier = '/' + collection + '/' + new_json['accession'] + '/'
else:
identifier = '/' + new_json['accession'] + '/'
if 'attachment' in new_json:
if 'href' in new_json['attachment']:
pass
else:
try:
filename = new_json['attachment']['download']
print("Setting filename to %s" % (filename))
except:
print("Must specify either href or filename for attachment", file=sys.stderr)
if new_json['attachment'].get('type'):
mime_type = new_json['attachment'].get('type')
else:
try:
mime_type, encoding = mimetypes.guess_type(filename)
major, minor = mime_type.split('/')
#detected_type = magic.from_file(filename, mime=True)
print("Detected mime type %s" % (mime_type))
except:
print("Failed to detect mime type in file %s" % (filename), file=sys.stderr)
try:
with open(filename, 'rb') as stream:
print("opened")
newvalue = {
'download': filename, # Just echoes the given filename as the download name
'type': mime_type,
'href': 'data:%s;base64,%s' % (mime_type, b64encode(stream.read()))
}
f = open('tmp', 'w')
print(f, newvalue)
new_json.update({'attachment': newvalue}) # add
except:
print("Cannot open file %s" % (filename), file=sys.stderr)
if object_exists:
if args.force_put:
if not GET_ONLY:
print("Replacing existing object")
e = encodedcc.replace_ENCODE(identifier, connection, new_json)
print(e)
else:
if not GET_ONLY:
print("Patching existing object")
e = encodedcc.patch_ENCODE(identifier, connection, new_json)
print(e)
elif new_object:
if args.force_put:
if not GET_ONLY:
print("PUT'ing new object")
e = encodedcc.replace_ENCODE(identifier, connection, new_json)
print(e)
else:
if not GET_ONLY:
print("POST'ing new object")
if not any(collection):
print("ERROR: Unable to POST to non-existing collection {}".format(collection))
sys.exit(1)
e = encodedcc.new_ENCODE(connection, collection, new_json)
print(e)