def test_legacy_export_marcxml(self):
"""Record - legacy export marxml."""
# FIXME: use a better way to compare
from invenio_record.models import Record
from invenio.legacy.bibrecord import create_record, records_identical
blob = '''
<record>
<controlfield tag="001">8</controlfield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Efstathiou, G P</subfield>
<subfield code="u">Cambridge University</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">Title</subfield>
<subfield code="b">SubTitle</subfield>
</datafield>
<datafield tag="700" ind1=" " ind2=" ">
<subfield code="a">Lasenby, A N</subfield>
</datafield>
<datafield tag="980" ind1=" " ind2=" ">
<subfield code="a">Articles</subfield>
</datafield>
</record>
'''
rec = Record.create(blob, master_format='marc', namespace='testsuite')
recstruct, _, _ = create_record(blob)
json_recstruct, _, _ = create_record(rec.legacy_export_as_marc())
self.assertTrue(records_identical(json_recstruct, recstruct,
ignore_subfield_order=True))
def setUp(self):
self.marcxml = pkg_resources.resource_string('tests',
os.path.join(
'fixtures',
'test_hep_formats.xml')
)
self.marcxml_publi_info = pkg_resources.resource_string('tests',
os.path.join(
'fixtures',
'test_hep_publi_info.xml')
)
record = create_record(self.marcxml)
record_publi_info = create_record(self.marcxml_publi_info)
self.hep_record = hep.do(record)
self.hep_record_publi_info = hep.do(record_publi_info)
self.sample_cv_latex = {
'author': 'G.~Aad',
'title': "{\\bf ``\nSearch for supersymmetry in events containing a same-flavour opposite-sign dilepton pair, jets, and large missing transverse momentum in $\sqrt{s}=8$ TeV $pp$ collisions with the ATLAS detector\n''}",
'publi_info': ['Eur.\ Phys.\ J.\ C {\\bf 75}, no. 7, 318 (2015)', '[Eur.\ Phys.\ J.\ C {\\bf 75}, no. 10, 463 (2015)]'],
'url': cfg['CFG_SITE_URL'] + '/record/1351762',
'date': 'Mar 11, 2015'
}
self.sample_cv_latex_publi_info = {
'publi_info': ['Class.\\ Quant.\\ Grav.\\ {\\bf 15}, 2153 (1998)']
}
def test_image(self):
"""Test image model from XML into JSONi."""
from dojson.contrib.marc21.utils import create_record
from cds_dojson.marc21.models.image import (
model as marc21
)
match = query_matcher(create_record(CDS_IMAGE))
assert isinstance(match, marc21.__class__)
blob = create_record(CDS_IMAGE)
data = marc21.do(blob)
# Check the control number (doJSON)
assert data.get('control_number') == '1782445'
# Check the parent album (CDSImage)
assert data['album_parent'][0]['album_id'] == '2054964'
# Check the imprint (CDSMarc21)
assert data['imprint'][0]['place_of_publication'] == 'Geneva'
# Check that no fields are missing their model
assert marc21.missing(blob) == []
def test_identity_check():
"""Test image model from XML into JSON."""
blob = create_record(CDS_VIDEO_PROJECT)
data = marc21.do(blob)
back_blob = to_marc21.do(data)
assert blob == back_blob
blob = create_record(CDS_VIDEO_CLIP)
data = marc21.do(blob)
back_blob = to_marc21.do(data)
assert blob == back_blob
def setUp(self):
self.marcxml = pkg_resources.resource_string('tests',
os.path.join(
'fixtures',
'test_hep_formats.xml')
)
self.marcxml_publi_info = pkg_resources.resource_string('tests',
os.path.join(
'fixtures',
'test_hep_publi_info.xml')
)
record = create_record(self.marcxml)
record_publi_info = create_record(self.marcxml_publi_info)
self.hep_record = hep.do(record)
self.hep_record_publi_info = hep.do(record_publi_info)
self.latex_eu = Latex(self.hep_record, 'latex_eu')
self.latex_us = Latex(self.hep_record, 'latex_us')
self.latex_eu_publi_info = Latex(
self.hep_record_publi_info, 'latex_eu')
self.sample_latex_eu = {
'citation_key': 'Aad:2015wqa',
'author': 'G.~Aad',
'title': '\nSearch for supersymmetry in events containing a same-flavour opposite-sign dilepton pair, jets, and large missing transverse momentum in $\sqrt{s}=8$ TeV pp collisions with the ATLAS detector\n',
'publi_info': ['Eur.\ Phys.\ J.\ C {\\bf 75} (2015) 7, 318', '[Eur.\ Phys.\ J.\ C {\\bf 75} (2015) 10, 463]'],
'arxiv': 'arXiv:1503.03290 [hep-ex]',
'report_number': '',
'SLACcitation': '%%CITATION = ARXIV:1503.03290;%%',
}
self.sample_latex_publi_info = {
'publi_info': ['Class.\\ Quant.\\ Grav.\\ {\\bf 15} (1998) 2153']
}
self.sample_latex_us = {
'citation_key': 'Aad:2015wqa',
'author': 'G.~Aad',
'title': '\nSearch for supersymmetry in events containing a same-flavour opposite-sign dilepton pair, jets, and large missing transverse momentum in $\sqrt{s}=8$ TeV pp collisions with the ATLAS detector\n',
'publi_info': ['Eur.\ Phys.\ J.\ C {\\bf 75}, no. 7, 318 (2015)', '[Eur.\ Phys.\ J.\ C {\\bf 75}, no. 10, 463 (2015)]'],
'arxiv': 'arXiv:1503.03290 [hep-ex]',
'report_number': '',
'SLACcitation': '%%CITATION = ARXIV:1503.03290;%%',
}
def test_marc21_856_indicators():
"""Test MARC21 856 field special indicator values."""
from dojson.contrib.marc21 import marc21
from dojson.contrib.marc21.utils import create_record
from dojson.contrib.to_marc21 import to_marc21
RECORD_8564 = '''
<datafield tag="856" ind1="4" ind2=" ">
<subfield code="s">272681</subfield>
<subfield code="u">https://zenodo.org/record/17575/files/...</subfield>
<subfield code="z">0</subfield>
</datafield>
'''
RECORD_8567 = '''
<datafield tag="856" ind1="7" ind2=" ">
<subfield code="s">272681</subfield>
<subfield code="u">https://zenodo.org/record/17575/files/...</subfield>
<subfield code="z">0</subfield>
<subfield code="2">Awesome access method</subfield>
</datafield>
'''
expected_8564 = {
'electronic_location_and_access': [
{'public_note': ('0',),
'access_method': 'HTTP',
'uniform_resource_identifier': (
'https://zenodo.org/record/17575/files/...',),
'file_size': ('272681',)}
]
}
expected_8567 = {
'electronic_location_and_access': [
{'public_note': ('0',),
'access_method': 'Awesome access method',
'uniform_resource_identifier': (
'https://zenodo.org/record/17575/files/...',),
'file_size': ('272681',)}
]
}
blob = create_record(RECORD_8564)
data = marc21.do(blob)
assert expected_8564 == data
back_blob = to_marc21.do(data)
assert blob == back_blob
blob = create_record(RECORD_8567)
data = marc21.do(blob)
assert expected_8567 == data
back_blob = to_marc21.do(data)
assert blob == back_blob
def test_urls_from_marcxml_multiple_8564():
snippet = (
'<record>'
' <datafield tag="856" ind1="4" ind2="">'
' <subfield code="u">http://www.physics.unlv.edu/labastro/</subfield>'
' <subfield code="y">Conference web page</subfield>'
' </datafield>'
' <datafield tag="856" ind1="4" ind2="">'
' <subfield code="u">http://www.cern.ch/</subfield>'
' <subfield code="y">CERN web page</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'description': 'Conference web page',
'value': 'http://www.physics.unlv.edu/labastro/',
},
{
'description': 'CERN web page',
'value': 'http://www.cern.ch/',
},
]
result = clean_record(hep.do(create_record(snippet)))
assert expected == result['urls']
def test_field_from_marcxml_650_with_two_2():
"""Two '2' subfields in one datafield.
The first will be taken (this time it's correct).
"""
snippet = (
'<record>'
' <datafield tag="650" ind1="1" ind2="7">'
' <subfield code="2">arXiv</subfield>'
' <subfield code="2">INSPIRE</subfield>'
' <subfield code="a">hep-ex</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'_scheme': 'arXiv',
'scheme': 'INSPIRE',
'_term': 'hep-ex',
'term': 'Experiment-HEP',
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['field_categories']
def records():
"""Load records."""
import pkg_resources
import uuid
from dojson.contrib.marc21 import marc21
from dojson.contrib.marc21.utils import create_record, split_blob
from invenio_pidstore import current_pidstore
from invenio_records.api import Record
# pkg resources the demodata
data_path = pkg_resources.resource_filename(
'invenio_records', 'data/marc21/bibliographic.xml'
)
with open(data_path) as source:
indexer = RecordIndexer()
with db.session.begin_nested():
for index, data in enumerate(split_blob(source.read()), start=1):
# create uuid
rec_uuid = uuid.uuid4()
# do translate
record = marc21.do(create_record(data))
# create PID
current_pidstore.minters['recid_minter'](
rec_uuid, record
)
# create record
indexer.index(Record.create(record, id_=rec_uuid))
db.session.commit()
def test_field_from_multiple_marcxml_650():
"""Two datafields.
Both are arXiv field codes, but the other is incorrectly labeled as INSPIRE.
"""
snippet = (
'<record>'
' <datafield tag="650" ind1="1" ind2="7">'
' <subfield code="2">arXiv</subfield>'
' <subfield code="a">HEP-PH</subfield>'
' </datafield>'
' <datafield tag="650" ind1="1" ind2="7">'
' <subfield code="2">INSPIRE</subfield>'
' <subfield code="a">astro-ph.IM</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'_scheme': 'arXiv',
'scheme': 'INSPIRE',
'_term': 'HEP-PH',
'term': 'Phenomenology-HEP',
},
{
'_scheme': 'INSPIRE',
'scheme': 'INSPIRE',
'_term': 'astro-ph.IM',
'term': 'Instrumentation',
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['field_categories']
def test_address_from_111__a_c_e_g_x_y_and_270__b():
snippet = (
'<record>'
' <datafield tag="111" ind1=" " ind2=" ">'
' <subfield code="a">2017 International Workshop on Baryon and Lepton Number Violation: From the Cosmos to the LHC</subfield>'
' <subfield code="c">Cleveland, Ohio, USA</subfield>'
' <subfield code="e">BLV 2017</subfield>'
' <subfield code="g">C17-05-15</subfield>'
' <subfield code="x">2017-05-15</subfield>'
' <subfield code="y">2017-05-18</subfield>'
' </datafield>'
' <datafield tag="270" ind1=" " ind2=" ">'
' <subfield code="b">Case Western Reserve University</subfield>'
' </datafield>'
'</record>'
) # record/1353313
expected = [
{
'original_address': 'Cleveland, Ohio, USA',
'country_code': 'US',
'state': 'US-OH',
},
{
'original_address': 'Case Western Reserve University',
},
]
result = clean_record(conferences.do(create_record(snippet)))
assert expected == result['address']
def test_field_from_marcxml_650_with_single_a_and_9():
"""Simple case.
One arXiv fieldcode that will be mapped to an INSPIRE category. Source
will also be mapped to a standard term.
"""
snippet = (
'<record>'
' <datafield tag="650" ind1="1" ind2="7">'
' <subfield code="2">INSPIRE</subfield>'
' <subfield code="a">HEP-PH</subfield>'
' <subfield code="9">automatically added based on DCC, PPF, DK </subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'source': 'INSPIRE',
'_scheme': 'INSPIRE',
'scheme': 'INSPIRE',
'_term': 'HEP-PH',
'term': 'Phenomenology-HEP',
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['field_categories']
def test_address_from_multiple_marcxml__111_c():
snippet = (
'<record>'
' <datafield tag="111" ind1=" " ind2=" ">'
' <subfield code="c">Austin, Tex.</subfield>'
' </datafield>'
' <datafield tag="111" ind1=" " ind2=" ">'
' <subfield code="c">Den Haag, Nederlands</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'country_code': 'US',
'state': 'US-TX',
'original_address': 'Austin, Tex.'
},
{
'country_code': 'NL',
'original_address': 'Den Haag, Nederlands'
},
]
result = clean_record(conferences.do(create_record(snippet)))
assert expected == result['address']
def record_not_yet_deleted(app):
snippet = (
'<record>'
' <controlfield tag="001">333</controlfield>'
' <controlfield tag="005">20160913214552.0</controlfield>'
' <datafield tag="980" ind1=" " ind2=" ">'
' <subfield code="a">HEP</subfield>'
' </datafield>'
'</record>'
)
with app.app_context():
json_record = hep.do(create_record(snippet))
json_record['$schema'] = 'http://localhost:5000/schemas/records/hep.json'
with db.session.begin_nested():
record = record_upsert(json_record)
if record:
ri = RecordIndexer()
ri.index(record)
db.session.commit()
yield
with app.app_context():
_delete_record_from_everywhere('literature', 333)
def test_contact_details_from_multiple_marcxml_270():
snippet = (
'<record> '
' <datafield tag="270" ind1=" " ind2=" ">'
' <subfield code="m">[email protected]</subfield>'
' <subfield code="p">Manfred Lindner</subfield>'
' </datafield>'
' <datafield tag="270" ind1=" " ind2=" ">'
' <subfield code="p">Wynton Marsalis</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'name': 'Manfred Lindner',
'email': '*****@*****.**',
},
{
'name': 'Wynton Marsalis',
},
]
result = clean_record(conferences.do(create_record(snippet)))
assert expected == result['contact_details']
def test_languages_from_041__a_handles_multiple_languages_in_one_a():
schema = load_schema('hep')
subschema = schema['properties']['languages']
snippet = (
'<datafield tag="041" ind1=" " ind2=" ">'
' <subfield code="a">Russian / English</subfield>'
'</datafield>'
) # record/116959
expected = [
'ru',
'en',
]
result = hep.do(create_record(snippet))
assert validate(result['languages'], subschema) is None
assert expected == result['languages']
expected = [
{'a': 'russian'},
{'a': 'english'},
]
result = hep2marc.do(result)
assert expected == result['041']
def test_languages_from_double_041__a():
schema = load_schema('hep')
subschema = schema['properties']['languages']
snippet = (
'<record>'
' <datafield tag="041" ind1=" " ind2=" ">'
' <subfield code="a">French</subfield>'
' </datafield>'
' <datafield tag="041" ind1=" " ind2=" ">'
' <subfield code="a">German</subfield>'
' </datafield>'
'</record>'
) # record/1231408
expected = [
'fr',
'de',
]
result = hep.do(create_record(snippet))
assert validate(result['languages'], subschema) is None
assert expected == result['languages']
expected = [
{'a': 'french'},
{'a': 'german'},
]
result = hep2marc.do(result)
assert expected == result['041']
def test_report_numbers_from_037__z_9():
schema = load_schema('hep')
subschema = schema['properties']['report_numbers']
snippet = (
'<datafield tag="037" ind1=" " ind2=" ">'
' <subfield code="9">SLAC</subfield>'
' <subfield code="a">SLAC-PUB-16140</subfield>'
'</datafield>'
) # record/1326454
expected = [
{
'source': 'SLAC',
'value': 'SLAC-PUB-16140',
},
]
result = hep.do(create_record(snippet))
assert validate(result['report_numbers'], subschema) is None
assert expected == result['report_numbers']
expected = [
{
'9': 'SLAC',
'a': 'SLAC-PUB-16140',
},
]
result = hep2marc.do(result)
assert expected == result['037']
def test_isbns_from_020__a_b_normalizes_online():
schema = load_schema('hep')
subschema = schema['properties']['isbns']
snippet = (
'<datafield tag="020" ind1=" " ind2=" ">'
' <subfield code="a">978-94-024-0999-4</subfield>'
' <subfield code="b">Online</subfield>'
'</datafield>'
) # record/1504286
expected = [
{
'value': '9789402409994',
'medium': 'online',
},
]
result = hep.do(create_record(snippet))
assert validate(result['isbns'], subschema) is None
assert expected == result['isbns']
expected = [
{
'a': '9789402409994',
'b': 'online',
},
]
result = hep2marc.do(result)
assert expected == result['020']
def test_report_numbers_from_two_037__a():
schema = load_schema('hep')
subschema = schema['properties']['report_numbers']
snippet = (
'<record>'
' <datafield tag="037" ind1=" " ind2=" ">'
' <subfield code="a">UTPT-89-27</subfield>'
' </datafield>'
' <datafield tag="037" ind1=" " ind2=" ">'
' <subfield code="a">CALT-68-1585</subfield>'
' </datafield>'
'</record>'
) # record/26564
expected = [
{
'value': 'UTPT-89-27',
},
{
'value': 'CALT-68-1585',
},
]
result = hep.do(create_record(snippet))
assert validate(result['report_numbers'], subschema) is None
assert expected == result['report_numbers']
expected = [
{'a': 'UTPT-89-27'},
{'a': 'CALT-68-1585'},
]
result = hep2marc.do(result)
assert expected == result['037']
def test_report_numbers_hidden_from_037__z():
schema = load_schema('hep')
subschema = schema['properties']['report_numbers']
snippet = (
'<datafield tag="037" ind1=" " ind2=" ">'
' <subfield code="z">FERMILAB-PUB-17-011-CMS</subfield>'
'</datafield>'
) # record/1508174
expected = [
{
'hidden': True,
'value': 'FERMILAB-PUB-17-011-CMS',
},
]
result = hep.do(create_record(snippet))
assert validate(result['report_numbers'], subschema) is None
assert expected == result['report_numbers']
expected = [
{'z': 'FERMILAB-PUB-17-011-CMS'}
]
result = hep2marc.do(result)
assert expected == result['037']
def test_external_system_numbers_from_035__a_d_h_m_9():
schema = load_schema('hep')
subschema = schema['properties']['external_system_identifiers']
snippet = (
'<datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="9">http://cds.cern.ch/oai2d</subfield>'
' <subfield code="a">oai:cds.cern.ch:325030</subfield>'
' <subfield code="d">2015-06-05T13:24:42Z</subfield>'
' <subfield code="h">2015-11-09T16:22:48Z</subfield>'
' <subfield code="m">marcxml</subfield>'
'</datafield>'
) # record/1403324
expected = [
{
'value': 'oai:cds.cern.ch:325030',
'schema': 'http://cds.cern.ch/oai2d',
}
]
result = hep.do(create_record(snippet))
assert validate(result['external_system_identifiers'], subschema) is None
assert expected == result['external_system_identifiers']
expected = [
{
'9': 'http://cds.cern.ch/oai2d',
'a': 'oai:cds.cern.ch:325030',
},
]
result = hep2marc.do(result)
assert expected == result['035']
def test_texkeys_from_035__a_9():
schema = load_schema('hep')
subschema = schema['properties']['texkeys']
snippet = (
'<datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="9">INSPIRETeX</subfield>'
' <subfield code="a">Hagedorn:1963hdh</subfield>'
'</datafield>'
) # record/1403324
expected = [
'Hagedorn:1963hdh',
]
result = hep.do(create_record(snippet))
assert validate(result['texkeys'], subschema) is None
assert expected == result['texkeys']
expected = [
{
'9': 'INSPIRETeX',
'a': 'Hagedorn:1963hdh',
}
]
result = hep2marc.do(result)
assert expected == result['035']
def test_dois_from_0247_a_2_double_9_ignores_curator_source():
schema = load_schema('hep')
subschema = schema['properties']['dois']
snippet = (
'<datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="9">bibcheck</subfield>'
' <subfield code="9">CURATOR</subfield>'
' <subfield code="a">10.1590/S1806-11172008005000006</subfield>'
'</datafield>'
) # record/1117362
expected = [
{
'source': 'bibcheck',
'value': '10.1590/S1806-11172008005000006',
},
]
result = hep.do(create_record(snippet)) # no roundtrip
assert validate(result['dois'], subschema) is None
assert expected == result['dois']
expected = [
{
'a': '10.1590/S1806-11172008005000006',
'9': 'bibcheck',
'2': 'DOI',
},
]
result = hep2marc.do(result)
assert expected == result['0247']
def test_dois_from_0247_a_2():
schema = load_schema('hep')
subschema = schema['properties']['dois']
snippet = (
'<datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="a">10.1088/0264-9381/31/24/245004</subfield>'
'</datafield>'
) # record/1302395
expected = [
{'value': '10.1088/0264-9381/31/24/245004'},
]
result = hep.do(create_record(snippet))
assert validate(result['dois'], subschema) is None
assert expected == result['dois']
expected = [
{
'a': '10.1088/0264-9381/31/24/245004',
'2': 'DOI',
},
]
result = hep2marc.do(result)
assert expected == result['0247']
def test_field_from_marcxml_650_with_two_a():
"""Two 'a' subfields in one datafield.
The first is an arXiv fieldcode an the second an INSPIRE category.
"""
snippet = (
'<record>'
' <datafield tag="650" ind1="1" ind2="7">'
' <subfield code="2">INSPIRE</subfield>'
' <subfield code="a">hep-ex</subfield>'
' <subfield code="a">Gravitation and Cosmology</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'_scheme': 'INSPIRE',
'scheme': 'INSPIRE',
'_term': 'hep-ex',
'term': 'Experiment-HEP',
},
{
'_scheme': 'INSPIRE',
'scheme': 'INSPIRE',
'_term': 'Gravitation and Cosmology',
'term': 'Gravitation and Cosmology',
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['field_categories']
def test_isbns_from_020__a_b_normalizes_hardcover():
schema = load_schema('hep')
subschema = schema['properties']['isbns']
snippet = (
'<datafield tag="020" ind1=" " ind2=" ">'
' <subfield code="a">978-981-4571-66-1</subfield>'
' <subfield code="b">hardcover</subfield>'
'</datafield>'
) # record/1351311
expected = [
{
'value': '9789814571661',
'medium': 'hardcover',
},
]
result = hep.do(create_record(snippet))
assert validate(result['isbns'], subschema) is None
assert expected == result['isbns']
expected = [
{
'a': '9789814571661',
'b': 'hardcover',
},
]
result = hep2marc.do(result)
assert expected == result['020']
def test_arxiv_eprints_from_037__a_c_9():
schema = load_schema('hep')
subschema = schema['properties']['arxiv_eprints']
snippet = (
'<datafield tag="037" ind1=" " ind2=" ">'
' <subfield code="9">arXiv</subfield>'
' <subfield code="a">arXiv:1505.01843</subfield>'
' <subfield code="c">hep-ph</subfield>'
'</datafield>'
) # record/1368891
expected = [
{
'categories': [
'hep-ph',
],
'value': '1505.01843',
},
]
result = hep.do(create_record(snippet))
assert validate(result['arxiv_eprints'], subschema) is None
assert expected == result['arxiv_eprints']
expected = [
{
'9': 'arXiv',
'a': 'arXiv:1505.01843',
'c': 'hep-ph',
},
]
result = hep2marc.do(result)
assert expected == result['037']
def test_external_system_identifiers_from_035__z_9_handles_cernkey():
schema = load_schema('hep')
subschema = schema['properties']['external_system_identifiers']
snippet = (
'<datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="9">CERNKEY</subfield>'
' <subfield code="z">0263439</subfield>'
'</datafield>'
) # record/451647
expected = [
{
'schema': 'CERNKEY',
'value': '0263439',
},
]
result = hep.do(create_record(snippet))
assert validate(result['external_system_identifiers'], subschema) is None
assert expected == result['external_system_identifiers']
expected = [
{
'9': 'CERNKEY',
'z': '0263439',
},
]
result = hep2marc.do(result)
assert expected == result['035']
def test_harvesting_arxiv_workflow_accepted(
mocked, db_only_app, record_oai_arxiv_plots):
"""Test a full harvesting workflow."""
from invenio_workflows import (
start, WorkflowEngine, ObjectStatus, workflow_object_class
)
from dojson.contrib.marc21.utils import create_record
from invenio_db import db
from inspirehep.dojson.hep import hep
from inspirehep.modules.converter.xslt import convert
# Convert to MARCXML, then dict, then HEP JSON
record_oai_arxiv_plots_marcxml = convert(
record_oai_arxiv_plots,
"oaiarXiv2marcxml.xsl"
)
record_marc = create_record(record_oai_arxiv_plots_marcxml)
record_json = hep.do(record_marc)
workflow_uuid = None
with db_only_app.app_context():
workflow_uuid = start('article', [record_json])
eng = WorkflowEngine.from_uuid(workflow_uuid)
obj = eng.processed_objects[0]
assert obj.status == ObjectStatus.HALTED
assert obj.data_type == "hep"
# Files should have been attached (tarball + pdf)
assert obj.files["1407.7587.pdf"]
assert obj.files["1407.7587.tar.gz"]
# A publication note should have been extracted
pub_info = obj.data.get('publication_info')
assert pub_info
assert pub_info[0]
assert pub_info[0].get('year') == "2014"
assert pub_info[0].get('journal_title') == "J. Math. Phys."
# This record should not have been touched yet
assert "approved" not in obj.extra_data
# Now let's resolve it as accepted and continue
# FIXME Should be accept, but record validation prevents us.
obj.remove_action()
obj.extra_data["approved"] = True
obj.extra_data["core"] = True
obj.save()
db.session.commit()
with db_only_app.app_context():
eng = WorkflowEngine.from_uuid(workflow_uuid)
obj = eng.processed_objects[0]
obj_id = obj.id
obj.continue_workflow()
obj = workflow_object_class.get(obj_id)
# It was accepted
assert obj.status == ObjectStatus.COMPLETED
def test_issn_from_marcxml_022_with_a_and_b_and_comment():
"""Test ISSN with medium normalization.
The original 'b' value will be stored in 'comment'.
"""
snippet = ('<record>'
' <datafield tag="022" ind1=" " ind2=" ">'
' <subfield code="a">2213-1337</subfield>'
' <subfield code="b">ebook</subfield>'
' </datafield>'
'</record>')
expected = [
{
'medium': 'online',
'value': '2213-1337',
'comment': 'ebook',
},
]
result = journals.do(create_record(snippet))
assert expected == result['issn']
def deleted_record(app):
snippet = ('<record>'
' <controlfield tag="001">111</controlfield>'
' <datafield tag="245" ind1=" " ind2=" ">'
' <subfield code="a">deleted</subfield>'
' </datafield>'
' <datafield tag="980" ind1=" " ind2=" ">'
' <subfield code="a">HEP</subfield>'
' <subfield code="c">DELETED</subfield>'
' </datafield>'
'</record>')
record = hep.do(create_record(snippet))
record['$schema'] = 'http://localhost:5000/schemas/records/hep.json'
with db.session.begin_nested():
record_insert_or_replace(record)
db.session.commit()
yield
_delete_record('lit', 111)
def test_deleted_records_from_981__a():
schema = load_schema('hep')
subschema = schema['properties']['deleted_records']
snippet = ('<datafield tag="981" ind1=" " ind2=" ">'
' <subfield code="a">1508668</subfield>'
'</datafield>') # record/1508886
expected = [{'$ref': 'http://localhost:5000/api/literature/1508668'}]
result = hep.do(create_record(snippet))
assert validate(result['deleted_records'], subschema) is None
assert expected == result['deleted_records']
expected = [
{
'a': 1508668
},
]
result = hep2marc.do(result)
assert expected == result['981']
def test_thesis_info_defense_date_from_500__a_incomplete_human_date():
schema = load_schema('hep')
subschema = schema['properties']['thesis_info']
snippet = ('<datafield tag="500" ind1=" " ind2=" ">'
' <subfield code="a">Presented on Dec 1992</subfield>'
'</datafield>') # record/887715
expected = {'defense_date': '1992-12'}
result = hep.do(create_record(snippet))
assert validate(result['thesis_info'], subschema) is None
expected == result['thesis_info']
expected = [
{
'a': 'Presented on 1992-12'
},
]
result = hep2marc.do(result)
assert expected == result['500']
def test_thesis_info_defense_date_from_500__a():
schema = load_schema('hep')
subschema = schema['properties']['thesis_info']
snippet = ('<datafield tag="500" ind1=" " ind2=" ">'
' <subfield code="a">Presented on 2016-09-30</subfield>'
'</datafield>') # record/1517362
expected = {'defense_date': '2016-09-30'}
result = hep.do(create_record(snippet))
assert validate(result['thesis_info'], subschema) is None
assert expected == result['thesis_info']
expected = [
{
'a': 'Presented on 2016-09-30'
},
]
result = hep2marc.do(result)
assert expected == result['500']
def test_curated_from_500__a():
schema = load_schema('hep')
subschema = schema['properties']['curated']
snippet = ('<datafield tag="500" ind1=" " ind2=" ">'
' <subfield code="a">* Brief entry *</subfield>'
'</datafield>') # record/1184775
expected = False
result = hep.do(create_record(snippet))
assert validate(result['curated'], subschema) is None
assert expected == result['curated']
expected = [
{
'a': '* Brief entry *'
},
]
result = hep2marc.do(result)
assert expected == result['500']
def test_export_to_from_595__c_hal():
schema = load_schema('hep')
subschema = schema['properties']['_export_to']
snippet = ('<datafield tag="595" ind1=" " ind2=" ">'
' <subfield code="c">HAL</subfield>'
'</datafield>') # record/1623281
expected = {'HAL': True}
result = hep.do(create_record(snippet))
assert validate(result['_export_to'], subschema) is None
assert expected == result['_export_to']
expected = [
{
'c': 'HAL'
},
]
result = hep2marc.do(result)
assert expected == result['595']
def transform_harvested_records(sender=None, records=None, **kwargs):
"""Harvest records and transform them and send to the import queue.
This function is called when the oaiharvester command is finished.
:param sender: Sender of the signal.
:param list records: Liste of records to harvest.
"""
start_time = time.time()
max_records = kwargs.get('max', None)
if kwargs.get('name'):
print('Harvesting records from "{set}"'.format(set=kwargs.get('name')))
harvested_records = list(records)
# Reduce array to max records
if max_records:
harvested_records = harvested_records[:int(max_records)]
records = []
for harvested_record in harvested_records:
# Convert from Marc XML to JSON
data = create_record(harvested_record.xml)
# Transform JSON
data = marc21tojson.do(data)
# Add transformed data to list
records.append(data)
# Chunk record list and send celery task
for chunk in list(chunks(records, CHUNK_SIZE)):
import_records.delay(chunk)
print('{count} records harvested in {time} seconds'.format(
count=len(records), time=time.time() - start_time))
def test_experiments_from_693__e__0():
schema = load_schema('jobs')
subschema = schema['properties']['experiments']
snippet = ('<datafield tag="693" ind1=" " ind2=" ">'
' <subfield code="e">CERN-LHC-ATLAS</subfield>'
' <subfield code="0">1108541</subfield>'
'</datafield>') # record/1332138
expected = [
{
'curated_relation': True,
'name': 'CERN-LHC-ATLAS',
'record': {
'$ref': 'http://localhost:5000/api/experiments/1108541',
},
},
]
result = jobs.do(create_record(snippet))
assert validate(result['experiments'], subschema) is None
assert expected == result['experiments']
def test_marc21_to_provision_activity_ebooks_from_field_264_2():
"""Test provision activity Place and Date from field 264_2 transform."""
marc21xml = """
<record>
<datafield tag="264" ind1=" " ind2="2">
<subfield code="a">Lausanne :</subfield>
<subfield code="b">Payot,</subfield>
<subfield code="c">[2006-2010]</subfield>
</datafield>
</record>
"""
marc21json = create_record(marc21xml)
data = marc21.do(marc21json)
assert data.get('provisionActivity') == [
{
'type': 'bf:Distribution',
'statement': [
{
'label': [
{'value': 'Lausanne'}
],
'type': 'bf:Place'
},
{
'label': [
{'value': 'Payot'}
],
'type': 'bf:Agent'
},
{
'label': [
{'value': '[2006-2010]'}
],
'type': 'Date'
}
]
}
]
def test_stub_from_980__a_not_useful():
schema = load_schema('authors')
subschema = schema['properties']['stub']
snippet = (
'<datafield tag="980" ind1=" " ind2=" ">'
' <subfield code="a">HEPNAMES</subfield>'
'</datafield>'
) # record/1019103
expected = True
result = hepnames.do(create_record(snippet))
assert validate(result['stub'], subschema) is None
assert expected == result['stub']
expected = [
{'a': 'HEPNAMES'},
]
result = hepnames2marc.do(result)
assert expected == result['980']
def test_marc21subjects():
"""Test dojson subjects."""
unimarcxml = """
<record>
<datafield tag="600" ind1=" " ind2=" ">
<subfield code="a">subjects 600</subfield>
</datafield>
<datafield tag="616" ind1=" " ind2=" ">
<subfield code="a">Capet</subfield>
<subfield code="b">Louis</subfield>
<subfield code="c">Jr.</subfield>
<subfield code="d">III</subfield>
<subfield code="f">1700-1780</subfield>
</datafield>
</record>
"""
unimarcjson = create_record(unimarcxml)
data = unimarctojson.do(unimarcjson)
assert data.get('subjects') == [
'subjects 600', 'Capet, Louis III, Jr., 1700-1780'
]
def test_positions_from_371__a_r_t():
schema = load_schema('authors')
subschema = schema['properties']['positions']
snippet = (
'<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">Case Western Reserve U.</subfield>'
' <subfield code="r">UNDERGRADUATE</subfield>'
' <subfield code="t">2011</subfield>'
'</datafield>'
) # record/1590188
expected = [
{
'_rank': 'UNDERGRADUATE',
'current': False,
'end_date': '2011',
'institution': {
'curated_relation': False,
'name': 'Case Western Reserve U.',
},
'rank': 'UNDERGRADUATE',
},
]
result = hepnames.do(create_record(snippet))
assert validate(result['positions'], subschema) is None
assert expected == result['positions']
expected = [
{
'a': 'Case Western Reserve U.',
'r': 'UG',
't': '2011',
},
]
result = hepnames2marc.do(result)
assert expected == result['371']
def test_urls_from_8564_u_and_8564_g_u_y():
schema = load_schema('authors')
subschema = schema['properties']['urls']
snippet = (
'<record>'
' <datafield tag="856" ind1="4" ind2=" ">'
' <subfield code="u">http://www.haydenplanetarium.org/tyson/</subfield>'
' </datafield>'
' <datafield tag="856" ind1="4" ind2=" ">'
' <subfield code="g">active</subfield>'
' <subfield code="u">https://twitter.com/neiltyson</subfield>'
' <subfield code="y">TWITTER</subfield>'
' </datafield>'
'</record>'
) # record/1073331
expected = [
{'value': 'http://www.haydenplanetarium.org/tyson/'},
{
'description': 'TWITTER',
'value': 'https://twitter.com/neiltyson',
},
]
result = hepnames.do(create_record(snippet))
assert validate(result['urls'], subschema) is None
assert expected == result['urls']
expected = [
{'u': 'http://www.haydenplanetarium.org/tyson/'},
{
'u': 'https://twitter.com/neiltyson',
'y': 'TWITTER',
},
]
result = hepnames2marc.do(result)
assert expected == result['8564']
def test_deleted_from_980__c():
schema = load_schema('hep')
subschema = schema['properties']['deleted']
snippet = ('<datafield tag="980" ind1=" " ind2=" ">'
' <subfield code="c">DELETED</subfield>'
'</datafield>') # record/1508668/export/xme
expected = True
result = hep.do(create_record(snippet))
assert validate(result['deleted'], subschema) is None
assert expected == result['deleted']
expected = [
{
'c': 'DELETED'
},
]
result = hep2marc.do(result)
assert expected == result['980']
def test_marc21_to_edition_statement_one_field_250():
"""Test dojson edition statement.
- 1 edition designation and 1 responsibility from field 250
"""
marc21xml = """
<record>
<datafield tag="250" ind1=" " ind2=" ">
<subfield code="a">2e ed.</subfield>
<subfield code="b">avec un avant-propos par Jean Faret</subfield>
</datafield>
</record>
"""
marc21json = create_record(marc21xml)
data = marc21.do(marc21json)
assert data.get('editionStatement') == [{
'editionDesignation': [{
'value': '2e ed.'
}],
'responsibility': [{
'value': 'avec un avant-propos par Jean Faret'
}]
}]
def test_old_single_email_from_371__a():
schema = load_schema('authors')
subschema = schema['properties']['positions']
snippet = ('<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">IMSc, Chennai</subfield>'
' <subfield code="o">[email protected]</subfield>'
' <subfield code="r">PD</subfield>'
' <subfield code="s">2012</subfield>'
' <subfield code="t">2013</subfield>'
'</datafield>') # record/1060782
expected = [{
"current": False,
"old_emails": ["*****@*****.**"],
"end_date": "2013",
"rank": "POSTDOC",
"institution": {
"name": "IMSc, Chennai",
"curated_relation": False
},
"_rank": "PD",
"start_date": "2012"
}]
result = hepnames.do(create_record(snippet))
assert validate(result['positions'], subschema) is None
assert expected == result['positions']
expected = [{
"a": "IMSc, Chennai",
"o": ["*****@*****.**"],
"s": "2012",
"r": "PD",
"t": "2013"
}]
result = hepnames2marc.do(result)
assert expected == result['371']
def test_positions_from_371__a_m_r_z():
schema = load_schema('authors')
subschema = schema['properties']['positions']
snippet = ('<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">Antwerp U.</subfield>'
' <subfield code="m">[email protected]</subfield>'
' <subfield code="r">SENIOR</subfield>'
' <subfield code="z">Current</subfield>'
'</datafield>') # record/997958
expected = [
{
'current': True,
'emails': [
'*****@*****.**',
],
'institution': {
'curated_relation': False,
'name': 'Antwerp U.',
},
'rank': 'SENIOR',
'_rank': 'SENIOR',
},
]
result = hepnames.do(create_record(snippet))
assert validate(result['positions'], subschema) is None
assert expected == result['positions']
expected = [{
'a': 'Antwerp U.',
'm': ['*****@*****.**'],
'r': 'SENIOR',
'z': 'Current'
}]
result = hepnames2marc.do(result)
assert expected == result['371']
def test_historical_data_from_6781_multiple_a():
schema = load_schema('institutions')
subschema = schema['properties']['historical_data']
snippet = (
'<datafield tag="678" ind1="1" ind2=" ">'
' <subfield code="a">Conseil européen pour la Recherche Nucléaire (1952-1954)</subfield>'
' <subfield code="a">Organisation européenne pour la Recherche nucléaire (1954-now)</subfield>'
' <subfield code="a">Sub title: Laboratoire européen pour la Physique des Particules (1984-now)</subfield>'
' <subfield code="a">Sub title: European Laboratory for Particle Physics (1984-now)</subfield>'
'</datafield>') # record/902725
expected = [
u'Conseil européen pour la Recherche Nucléaire (1952-1954)',
u'Organisation européenne pour la Recherche nucléaire (1954-now)',
u'Sub title: Laboratoire européen pour la Physique des Particules (1984-now)',
u'Sub title: European Laboratory for Particle Physics (1984-now)',
]
result = institutions.do(create_record(snippet))
assert validate(result['historical_data'], subschema) is None
assert expected == result['historical_data']
def test_publication_info_from_7731_c_p_v_y():
schema = load_schema('hep')
subschema = schema['properties']['publication_info']
snippet = ('<datafield tag="773" ind1="1" ind2=" ">'
' <subfield code="c">948-979</subfield>'
' <subfield code="p">Adv.Theor.Math.Phys.</subfield>'
' <subfield code="v">12</subfield>'
' <subfield code="y">2008</subfield>'
'</datafield>') # record/697133
expected = [
{
'hidden': True,
'journal_title': 'Adv.Theor.Math.Phys.',
'journal_volume': '12',
'page_end': '979',
'page_start': '948',
'year': 2008,
},
]
result = hep.do(create_record(snippet))
assert validate(result['publication_info'], subschema) is None
assert expected == result['publication_info']
expected = [
{
'c': [
'948-979',
],
'p': 'Adv.Theor.Math.Phys.',
'v': '12',
'y': 2008,
},
]
result = hep2marc.do(result)
assert expected == result['7731']
def test_collaboration_from_710__g_0():
schema = load_schema('experiments')
subschema = schema['properties']['collaboration']
snippet = (
'<datafield tag="710" ind1=" " ind2=" ">'
' <subfield code="g">DarkSide</subfield>'
' <subfield code="0">1108199</subfield>'
'</datafield>'
) # record/1108199
expected = {
'curated_relation': True,
'record': {
'$ref': 'http://localhost:5000/api/experiments/1108199',
},
'value': 'DarkSide',
}
result = experiments.do(create_record(snippet))
assert validate(result['collaboration'], subschema) is None
assert expected == result['collaboration']
def test_related_records_from_double_510__a_w_0_accepts_predecessors():
schema = load_schema('experiments')
subschema = schema['properties']['related_records']
snippet = (
'<record>'
' <datafield tag="510" ind1=" " ind2=" ">'
' <subfield code="0">1108293</subfield>'
' <subfield code="a">XENON</subfield>'
' <subfield code="w">a</subfield>'
' </datafield>'
' <datafield tag="510" ind1=" " ind2=" ">'
' <subfield code="0">1386527</subfield>'
' <subfield code="a">XENON100</subfield>'
' <subfield code="w">a</subfield>'
' </datafield>'
'</record>'
) # record/1386519
expected = [
{
'curated_relation': True,
'record': {
'$ref': 'http://localhost:5000/api/experiments/1108293',
},
'relation': 'predecessor',
},
{
'curated_relation': True,
'record': {
'$ref': 'http://localhost:5000/api/experiments/1386527',
},
'relation': 'predecessor',
},
]
result = experiments.do(create_record(snippet))
assert validate(result['related_records'], subschema) is None
assert expected == result['related_records']
def test_address_from_111__a_double_c_d_e_g_x_y():
schema = load_schema('conferences')
subschema = schema['properties']['address']
snippet = (
'<datafield tag="111" ind1=" " ind2=" ">'
' <subfield code="a">16th High-Energy Physics International Conference in Quantum Chromodynamics</subfield>'
' <subfield code="c">QCD 12</subfield>'
' <subfield code="c">Montpellier, France</subfield>'
' <subfield code="d">2-7 Jul 2012</subfield>'
' <subfield code="e">QCD 12</subfield>'
' <subfield code="g">C12-07-02</subfield>'
' <subfield code="x">2012-07-02</subfield>'
' <subfield code="y">2012-07-07</subfield>'
'</datafield>') # record/1085463
expected = [
{
'cities': [
'QCD 12',
],
'postal_address': [
'QCD 12',
],
}, # XXX: Wrong, but the best we can do.
{
'cities': [
'Montpellier',
],
'country_code': 'FR',
'postal_address': [
'Montpellier, France',
],
},
]
result = conferences.do(create_record(snippet))
assert validate(result['address'], subschema) is None
assert expected == result['address']
def test_texkeys_from_035__z_9_and_035__a_9():
schema = load_schema('hep')
subschema = schema['properties']['texkeys']
snippet = (
'<record>'
' <datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="9">SPIRESTeX</subfield>'
' <subfield code="z">N.Cartiglia:2015cn</subfield>'
' </datafield>'
' <datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="9">INSPIRETeX</subfield>'
' <subfield code="a">Akiba:2016ofq</subfield>'
' </datafield>'
'</record>'
) # record/1498308
expected = [
'Akiba:2016ofq', # XXX: the first one is the one coming
'N.Cartiglia:2015cn', # from the "a" field.
]
result = hep.do(create_record(snippet))
assert validate(result['texkeys'], subschema) is None
assert expected == result['texkeys']
expected = [
{
'9': 'INSPIRETeX',
'a': 'Akiba:2016ofq',
},
{
'9': 'INSPIRETeX',
'z': 'N.Cartiglia:2015cn',
}
]
result = hep2marc.do(result)
assert expected == result['035']
def test_alternative_titles_from_711__a_b():
schema = load_schema('conferences')
subschema = schema['properties']['alternative_titles']
snippet = (
'<datafield tag="711" ind1=" " ind2=" ">'
' <subfield code="a">XX Riunione Nazionale di Elettromagnetismo</subfield>'
' <subfield code="b">Padova</subfield>'
'</datafield>') # record/1403856
expected = [
{
'title': 'XX Riunione Nazionale di Elettromagnetismo'
},
{
'title': 'Padova'
},
]
result = conferences.do(create_record(snippet))
assert validate(result['alternative_titles'], subschema) is None
assert expected == result['alternative_titles']
def test_unimarc_edition():
"""Test dojson edition statement.
- 1 edition designation and 1 responsibility from field 205
"""
unimarcxml = """
<record>
<datafield tag="205" ind1=" " ind2=" ">
<subfield code="a">2e ed.</subfield>
<subfield code="f">avec un avant-propos par Jean Faret</subfield>
</datafield>
</record>
"""
unimarcjson = create_record(unimarcxml)
data = unimarc.do(unimarcjson)
assert data.get('editionStatement') == [{
'editionDesignation': [{
'value': '2e ed.'
}],
'responsibility': [{
'value': 'avec un avant-propos par Jean Faret'
}]
}]
def test_private_notes_from_595__double_a_9():
schema = load_schema('hep')
subschema = schema['properties']['_private_notes']
snippet = (
'<datafield tag="595" ind1=" " ind2=" ">'
' <subfield code="9">SPIRES-HIDDEN</subfield>'
' <subfield code="a">TeXtitle from script</subfield>'
' <subfield code="a">no affiliation (not clear pn the fulltext)</subfield>'
'</datafield>') # record/109310
expected = [
{
'source': 'SPIRES-HIDDEN',
'value': 'TeXtitle from script',
},
{
'source': 'SPIRES-HIDDEN',
'value': 'no affiliation (not clear pn the fulltext)',
},
]
result = hep.do(create_record(snippet))
assert validate(result['_private_notes'], subschema) is None
assert expected == result['_private_notes']
expected = [
{
'9': 'SPIRES-HIDDEN',
'a': 'TeXtitle from script',
},
{
'9': 'SPIRES-HIDDEN',
'a': 'no affiliation (not clear pn the fulltext)',
},
]
result = hep2marc.do(result)
assert expected == result['595']
def test_multiple_title_variants_from_marcxml_730():
snippet = (
'<record>'
' <datafield tag="730" ind1=" " ind2=" ">'
' <subfield code="a">PHYS REV SPECIAL TOPICS ACCELERATORS BEAMS</subfield>'
' </datafield>'
' <datafield tag="730" ind1=" " ind2=" ">'
' <subfield code="a">PHYSICS REVIEW ST ACCEL BEAMS</subfield>'
' </datafield>'
'</record>')
expected = [
{
'title': 'PHYS REV SPECIAL TOPICS ACCELERATORS BEAMS',
},
{
'title': 'PHYSICS REVIEW ST ACCEL BEAMS',
},
]
result = journals.do(create_record(snippet))
assert expected == result['title_variants']
def test_public_notes_from_500__double_a_9():
schema = load_schema('hep')
subschema = schema['properties']['public_notes']
snippet = (
'<datafield tag="500" ind1=" " ind2=" ">'
' <subfield code="9">arXiv</subfield>'
' <subfield code="a">11 pages, 8 figures. Submitted to MNRAS</subfield>'
' <subfield code="a">preliminary entry</subfield>'
'</datafield>') # record/1380257
expected = [
{
'source': 'arXiv',
'value': '11 pages, 8 figures. Submitted to MNRAS',
},
{
'source': 'arXiv',
'value': 'preliminary entry',
},
]
result = hep.do(create_record(snippet))
assert validate(result['public_notes'], subschema) is None
assert expected == result['public_notes']
expected = [
{
'9': 'arXiv',
'a': '11 pages, 8 figures. Submitted to MNRAS',
},
{
'9': 'arXiv',
'a': 'preliminary entry',
},
]
result = hep2marc.do(result)
assert expected == result['500']
def test_name_variants_from_410__double_a():
schema = load_schema('institutions')
subschema = schema['properties']['name_variants']
snippet = (
'<datafield tag="410" ind1=" " ind2=" ">'
' <subfield code="a">Theoretische Teilchenphysik und Kosmologie</subfield>'
' <subfield code="a">Elementarteilchenphysik</subfield>'
'</datafield>') # record/902624
expected = [
{
'value': 'Theoretische Teilchenphysik und Kosmologie'
},
{
'value': 'Elementarteilchenphysik'
},
]
result = institutions.do(create_record(snippet))
assert validate(result['name_variants'], subschema) is None
assert expected == result['name_variants']
