def test_whitespace_is_stripped_from_dois(self):
for doi in (' foo ', 'doi: foo ', ' doi:foo ', ' doi: foo '):
dc_dict = {'identifier': [doi]}
document_uris = parse_document_claims.document_uris_from_dc(
dc_dict,
claimant='http://example.com/example.html',
)
assert [d['uri'] for d in document_uris] == ['doi:foo']
def test_whitespace_only_dois_are_ignored(self):
for doi in (' ', 'doi: '):
dc_dict = {'identifier': [doi]}
document_uris = parse_document_claims.document_uris_from_dc(
dc_dict,
claimant='http://example.com/example.html',
)
assert document_uris == []
def test_doi_is_prepended_to_dc_identifiers(self):
"""If a dc identifier doesn't begin with 'doi:' it is prepended."""
dc_dict = {'identifier': ['10.10.1038/nphys1170']}
document_uris = parse_document_claims.document_uris_from_dc(
dc_dict,
claimant='http://example.com/example.html',
)
expected_uri = 'doi:' + dc_dict['identifier'][0]
one([d for d in document_uris if d.get('uri') == expected_uri])
def test_dc_identifiers_produce_dc_doi_document_uris(self):
"""Each 'identifier' list item in the 'dc' dict becomes a doc URI."""
dc_dict = {
'identifier': [
'doi:10.10.1038/nphys1170', 'doi:10.1002/0470841559.ch1',
'doi:10.1594/PANGAEA.726855'
]
}
document_uris = parse_document_claims.document_uris_from_dc(
dc_dict,
claimant='http://example.com/example.html',
)
for doi in dc_dict['identifier']:
document_uri = one(
[d for d in document_uris if d.get('uri') == doi])
assert document_uri == {
'claimant': 'http://example.com/example.html',
'uri': doi,
'type': 'dc-doi',
'content_type': '',
}
def test_dc_identifiers_produce_dc_doi_document_uris(self):
"""Each 'identifier' list item in the 'dc' dict becomes a doc URI."""
dc_dict = {
'identifier': [
'doi:10.10.1038/nphys1170',
'doi:10.1002/0470841559.ch1',
'doi:10.1594/PANGAEA.726855'
]
}
document_uris = parse_document_claims.document_uris_from_dc(
dc_dict,
claimant='http://example.com/example.html',
)
for doi in dc_dict['identifier']:
document_uri = one([d for d in document_uris
if d.get('uri') == doi])
assert document_uri == {
'claimant': 'http://example.com/example.html',
'uri': doi,
'type': 'dc-doi',
'content_type': '',
}
