def test_constructor(self):
"""Tests the proper constructor values are set"""
client = self._new_client()
self.assertEqual(client.baseurl['scheme'], 'http',
'Scheme not set to http as spected for baseurl!')
self.assertEqual(client.baseurl['host'], 'brutus.library.emory.edu',
'Host not correctly set for baseurl!')
self.assertEqual(client.baseurl['path'], '/pidman',
'Path not correctly set for baseurl!')
# url with trailing slash - treated same as without
client = PidmanRestClient('%s/' % self.baseurl)
self.assertEqual(
client.baseurl['path'], '/pidman',
'Path not correctly set when baseurl specified with trailing slash'
)
# validate that each arg starts with http and ends with a port number
validate(new_url_base, fedora_url)
else:
print '\nError: argument list incomplete. See usage example below.'
usage()
sys.exit()
global repo
repo = Repository(fedora_url,
username=fedora_username,
password=fedora_password)
#Pidman Client
global client
client = PidmanRestClient(db_baseurl, db_username, db_password)
connection = client._get_connection()
current_page = 1
count = 0
max = 10000
# search for existing arks by domain where type='ark', domain='LSDI'
search_results = client.search_pids(type='ark',
domain='Rushdie Collection',
count=max)
total_pages = search_results['page_count']
page_link_1 = search_results['first_page_link']
page_link = page_link_1[0:-1]
print "\n=> Processing page[%d] that contains [%d] of a total of [%d] pages ..." % (
# validate that each arg starts with http and ends with a port number
validate(new_url_base, fedora_url)
else:
print '\nError: argument list incomplete. See usage example below.'
usage()
sys.exit()
global repo
repo = Repository(fedora_url,
username=fedora_username, password=fedora_password)
#Pidman Client
global client
client = PidmanRestClient(db_baseurl, db_username, db_password)
connection = client._get_connection()
current_page = 1
count = 0
max = 10000
# search for existing arks by domain where type='ark', domain='LSDI'
search_results = client.search_pids(type='ark', domain='Rushdie Collection', count=max)
total_pages = search_results['page_count']
page_link_1 = search_results['first_page_link']
page_link = page_link_1[0:-1]
print "\n=> Processing page[%d] that contains [%d] of a total of [%d] pages ..." %(current_page, max, total_pages)
page_results = search_results['results']
count = process_page(current_page, page_results)
db_username = args[2]
db_password = args[3]
domain = args[4]
if (len(args) == 6):
db_baseurl = args[5]
else: # use the test pid manager if not specified
db_baseurl = 'https://testpid.library.emory.edu/'
else:
print '\nError: argument list incomplete. See usage example below.'
usage()
sys.exit()
global client
client = PidmanRestClient(db_baseurl, db_username, db_password)
current_page = 1
count = 0
max = 50000
search_results = client.search_pids(type='purl', domain=domain, count=max)
total_pages = search_results['page_count']
page_results = search_results['results']
print "\n=> Processing page[%d] that contains [%d] of a total of [%d] pages..." %(current_page, max, total_pages)
count = process_page(current_page, page_results)
current_page = current_page + 1
while (current_page <= total_pages):
def _new_client(self):
"""
Initialize client with configured settings for testing.
"""
return PidmanRestClient(self.baseurl, self.username, self.password)
new_netloc = args[1]
db_username = args[2]
db_password = args[3]
domain = args[4]
if (len(args) == 6):
db_baseurl = args[5]
else: # use the test pid manager if not specified
db_baseurl = 'https://testpid.library.emory.edu/'
else:
print '\nError: argument list incomplete. See usage example below.'
usage()
sys.exit()
global client
client = PidmanRestClient(db_baseurl, db_username, db_password)
current_page = 1
count = 0
max = 50000
search_results = client.search_pids(type='purl', domain=domain, count=max)
total_pages = search_results['page_count']
page_results = search_results['results']
print "\n=> Processing page[%d] that contains [%d] of a total of [%d] pages..." % (
current_page, max, total_pages)
count = process_page(current_page, page_results)
current_page = current_page + 1
