from pyDataverse.api import Api
import json
import dvconfig
base_url = dvconfig.base_url
api_token = dvconfig.api_token
api = Api(base_url, api_token)
print(api.status)
dataset_json = 'data/dataverses/open-source-at-harvard/datasets/open-source-at-harvard/open-source-at-harvard.json'
with open(dataset_json) as f:
metadata = json.load(f)
dataverse = 'open-source-at-harvard'
resp = api.create_dataset(dataverse, json.dumps(metadata))
print(resp)
dataset_pid = resp.json()['data']['persistentId']
tabular_file = 'data/dataverses/open-source-at-harvard/datasets/open-source-at-harvard/files/2019-02-25.tsv'
resp = api.upload_file(dataset_pid, tabular_file)
print(resp)
if UPLOAD_DATA:
CREATE_DV = False
DELETE_DV = False
CREATE_DS = False
ADD_FILE = False
DELETE_DS = False
CREATE_DF = False
api_token_up = os.environ["API_TOKEN_UP"]
api_host_up = os.environ["API_HOST_UP"]
api_up = Api(api_host_up, api_token=api_token_up, use_https=False)
# create dataverse
if CREATE_DV:
dv_json = read_json_file(
'data/down/dv_AUSSDA/dv_AUSSDA_metadata.json')
api_up.create_dataverse(dv_json['alias'], dict_to_json(dv_json))
time.sleep(0.2)
# create dataset
if CREATE_DS:
ds_json = read_json_file(
'data/down/dv_AUSSDA/ds_VKYZPD/ds_VKYZPD_metadata.json')
resp = api_up.create_dataset('science', dict_to_json(ds_json))
time.sleep(0.2)
if ADD_FILE:
doi = 'doi:10.5072/FK2/PF6EMS'
filename = 'dev/cat.jpg'
resp = api_up.upload_file(doi, filename)
metadata = json.load(f)
dataverse = parent
resp = api.create_dataset(dataverse, json.dumps(metadata))
print(resp)
dataset_pid = resp.json()['data']['persistentId']
dataset_dbid = resp.json()['data']['id']
files_dir = path.replace(json_file, '') + 'files'
filemetadata_dir = path.replace(json_file, '') + '.filemetadata'
print(files_dir)
for path, subdir, files in os.walk(files_dir):
for name in files:
filepath = os.path.join(path, name)
relpath = os.path.relpath(filepath, files_dir)
# "directoryLabel" is used to populate "File Path"
directoryLabel, filename = os.path.split(relpath)
resp = api.upload_file(dataset_pid, "'" + filepath + "'")
print(resp)
file_id = resp['data']['files'][0]['dataFile']['id']
## This lock check and sleep is here to prevent the dataset from being permanently
## locked because a tabular file was uploaded first.
check_dataset_lock(dataset_dbid)
# TODO: Think more about where the description comes from. A "sidecar" file as proposed at https://github.com/IQSS/dataverse/issues/5924#issuecomment-499605672 ?
# L.A.: I implemented something along these lines - an (optional) directory called ".filemetadata"
# in the dataset directory, where files containing extra json filemetadata records may be
# placed for each of the files in the "files" directory.
# check for optional filemetadata file:
filemetadatapath = os.path.join(filemetadata_dir, relpath)
if (os.path.exists(filemetadatapath)):
with open(filemetadatapath) as m:
file_metadata = json.load(m)
else: