def test_process_legal(self):
raw_doc = RawDocument({
'doc': json.dumps({'Hello': 'world'}),
'source': 'TEST',
'doc_id': 37,
'filetype': 'json'
})
ts = str(process_docs.process_raw(raw_doc, 'test-version'))
timestamp = None
for dirname, dirnames, filenames in os.walk('archive/TEST/{0}'.format(raw_doc.get('doc_id'))):
if os.path.isfile(dirname + '/raw.json'):
timestamp = dirname.split('/')[-1]
assert timestamp == ts
doc = NormalizedDocument({
'title': "TEST PROJECT",
'contributors': [
{
'full_name': 'Me, Myself',
'email': '*****@*****.**'
},
{
'full_name': 'And I',
'email': '*****@*****.**'
}
],
'properties': {
},
'meta': {},
'id': {
'service_id': raw_doc.get('doc_id'),
'doi': 'Not available',
'url': 'fake.stuff.org/{}'.format(raw_doc.get('doc_id')),
},
'source': raw_doc.get('source'),
'timestamp': str(timestamp),
'tags': ['1', '2', '3'],
'date_created': str(timestamp),
'description': 'science stuff',
})
assert process_docs.process(doc, timestamp)
found = False
for dirname, dirnames, filenames in os.walk('archive/TEST/{0}'.format(raw_doc.get('doc_id'))):
if os.path.isfile(dirname + '/normalized.json'):
found = True
assert found
def test_process_raw(self):
raw_file = RawDocument({
'doc': json.dumps({'Hello': 'world'}),
'source': "TEST",
'doc_id': 37,
'filetype': "json"
})
assert process_docs.process_raw(raw_file, 'test-version')
found = False
for dirname, dirnames, filenames in os.walk('archive/TEST/{0}'.format(raw_file.get('doc_id'))):
if os.path.isfile(dirname + '/raw.json'):
found = True
assert found
