def _is_valid_oai_pmh_record(self, xmldict, metadata_prefix=''):
site_url = config.get('ckan.site_url', '')
if not metadata_prefix:
metadata_prefix = 'oai_dc'
try:
xml_record = unparse(xmldict)
oai_pmh_record = XMLRecord(
MetadataFormats().get_metadata_formats('oai_pmh')[0],
xml_record)
# get the format
metadata_format = MetadataFormats().get_metadata_formats(
metadata_prefix)[0]
metadata_schema = metadata_format.get_xsd_url()
# local xsd for gcmd_dif (nasa hosted is not always available)
if metadata_prefix == 'gcmd_dif':
metadata_schema = metadata_schema.replace(
'http://gcmd.gsfc.nasa.gov/Aboutus/xml/dif/',
site_url + '/package_converter_xsd/')
# modify xsd due to library bug
fixed_xsd = '''<xs:schema xmlns="http://www.openarchives.org/OAI/2.0/"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" >
<xs:import namespace="http://www.openarchives.org/OAI/2.0/" schemaLocation="http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd" />
<xs:import namespace="{namespace}" schemaLocation="{schema}" />
</xs:schema>'''.format(
namespace=metadata_format.get_namespace(),
schema=metadata_schema)
return oai_pmh_record.validate(custom_xsd=fixed_xsd)
except Exception as e:
print(e)
log.error('Failed to validate OAI-PMH for format {0}'.format(
metadata_prefix))
except:
log.error('Failed to validate OAI-PMH for format {0}'.format(
metadata_prefix))
return False
def test_list_metadata_formats(self):
request_content = OAIPMHRepository().handle_request('ListMetadataFormats', {}, 'REQUEST_URL')
oaipmh_record = XMLRecord(MetadataFormats().get_metadata_formats('oai_pmh')[0], request_content)
# validate the XML
assert_true(oaipmh_record.validate())
assert_false(OAIPMHRepository()._is_error_oai_pmh_record(oaipmh_record.get_xml_dict()))