def test_list_records(self):
raw_cs_xml = open(os.path.join(
os.path.dirname(__file__),
"data/sample_arxiv_response_listrecords_cs.xml"
)).read()
raw_physics_xml = open(os.path.join(
os.path.dirname(__file__),
"data/sample_arxiv_response_listrecords_physics.xml"
)).read()
responses.add(
responses.GET,
re.compile(r'http?://export.arxiv.org/oai2.*set=cs&.*'),
body=raw_cs_xml,
content_type='text/xml'
)
responses.add(
responses.GET,
re.compile(r'http?://export.arxiv.org/oai2.*set=physics&.*'),
body=raw_physics_xml,
content_type='text/xml'
)
_, records = list_records(
metadata_prefix='arXiv',
from_date='2015-01-15',
until_date='2015-01-20',
url='http://export.arxiv.org/oai2',
name=None,
setspecs='cs physics'
)
# 46 cs + 150 physics - 6 dupes == 190
self.assertTrue(len(records) == 190)
def test_model_based_harvesting_list(self):
"""Test harvesting using model."""
from invenio_oaiharvester.utils import get_oaiharvest_object
source = get_oaiharvest_object('arXiv')
last_updated = source.lastrun
raw_physics_xml = open(os.path.join(
os.path.dirname(__file__), "data/sample_arxiv_response_listrecords_physics.xml"
)).read()
responses.add(
responses.GET,
re.compile(r'http?://export.arxiv.org/oai2.*set=physics&.*'),
body=raw_physics_xml,
content_type='text/xml'
)
_, records = list_records(name='arXiv')
self.assertTrue(len(records) == 150)
self.assertTrue(last_updated < get_oaiharvest_object('arXiv').lastrun)
