def test_institutions_from_110__double_a_z():
snippet = (
'<datafield tag="110" ind1=" " ind2=" ">'
' <subfield code="a">Indiana U.</subfield>'
' <subfield code="a">NIST, Wash., D.C.</subfield>'
' <subfield code="z">902874</subfield>'
' <subfield code="z">903056</subfield>'
"</datafield>"
) # record/1328021/export/xme
expected = [
{
"curated_relation": True,
"name": "Indiana U.",
"record": {"$ref": "http://localhost:5000/api/institutions/902874"},
},
{
"curated_relation": True,
"name": "NIST, Wash., D.C.",
"record": {"$ref": "http://localhost:5000/api/institutions/903056"},
},
]
result = clean_record(jobs.do(create_record(snippet)))
assert expected == result["institutions"]
def test_address_from_marcxml_371__a_b_c_d_e_double_g():
snippet = ('<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">Philosophenweg 16</subfield>'
' <subfield code="b">Heidelberg</subfield>'
' <subfield code="c">Baden-Wuerttemberg</subfield>'
' <subfield code="d">Germany</subfield>'
' <subfield code="e">69120</subfield>'
' <subfield code="g">DE</subfield>'
' <subfield code="g">DE</subfield>'
'</datafield>')
expected = [
{
"city": "Heidelberg",
"country": "Germany",
"country_code": "DE",
"state": "Baden-Wuerttemberg",
"original_address": [
"Philosophenweg 16",
],
"postal_code": "69120",
},
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['address']
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 test_positions_from_371__a_m_r_z():
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 = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['positions']
def test_advisors_from_701__a_g_i():
snippet = (
'<datafield tag="701" ind1=" " ind2=" ">'
' <subfield code="a">Rivelles, Victor O.</subfield>'
' <subfield code="g">PhD</subfield>'
' <subfield code="i">INSPIRE-00120420</subfield>'
' <subfield code="x">991627</subfield>'
' <subfield code="y">1</subfield>'
'</datafield>'
) # record/1474091
expected = [
{
'name': 'Rivelles, Victor O.',
'degree_type': 'PhD',
'_degree_type': 'PhD',
'record': {
'$ref': 'http://localhost:5000/api/authors/991627',
},
'curated_relation': True
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['advisors']
def test_positions_from_371__a_double_m_z():
snippet = (
'<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">Argonne</subfield>'
' <subfield code="m">[email protected]</subfield>'
' <subfield code="m">[email protected]</subfield>'
' <subfield code="z">current</subfield>'
'</datafield>'
) # record/1408378
expected = [
{
'current': True,
'emails': [
'*****@*****.**',
'*****@*****.**',
],
'institution': {
'curated_relation': False,
'name': 'Argonne',
},
}
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['positions']
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_ids_from_double_035__a_9_with_kaken():
snippet = (
'<record>'
' <datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="9">BAI</subfield>'
' <subfield code="a">Toshio.Suzuki.2</subfield>'
' </datafield>'
' <datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="9">KAKEN</subfield>'
' <subfield code="a">70139070</subfield>'
' </datafield>'
'</record>'
) # record/1474271/export/xme
expected = [
{
'type': 'INSPIRE BAI',
'value': 'Toshio.Suzuki.2',
},
{
'type': 'KAKEN',
'value': 'KAKEN-70139070',
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['ids']
def test_dois_from_2472_a_2_and_247_a_2_9():
snippet = ('<record>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="a">10.1103/PhysRevD.89.072002</subfield>'
' </datafield>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="9">bibmatch</subfield>'
' <subfield code="a">10.1103/PhysRevD.91.019903</subfield>'
' </datafield>'
'</record>')
expected = [
{
'value': '10.1103/PhysRevD.89.072002',
},
{
'source': 'bibmatch',
'value': '10.1103/PhysRevD.91.019903',
},
]
result = clean_record(hep.do(create_record(snippet)))
assert expected == result['dois']
def test_thesis_supervisors_from_701__a_double_u():
snippet = (
'<datafield tag="701" ind1=" " ind2=" ">'
' <subfield code="a">Mnich, Joachim</subfield>'
' <subfield code="u">DESY</subfield>'
' <subfield code="u">U. Hamburg (main)</subfield>'
'</datafield>'
) # record/1462486
expected = [
{
'affiliations': [
{
'curated_relation': False,
'value': 'DESY',
},
{
'curated_relation': False,
'value': 'U. Hamburg (main)',
},
],
'full_name': 'Mnich, Joachim',
},
]
result = clean_record(hep.do(create_record(snippet)))
assert expected == result['thesis_supervisors']
def test_institutions_from_110__double_a_z():
snippet = ('<datafield tag="110" ind1=" " ind2=" ">'
' <subfield code="a">Indiana U.</subfield>'
' <subfield code="a">NIST, Wash., D.C.</subfield>'
' <subfield code="z">902874</subfield>'
' <subfield code="z">903056</subfield>'
'</datafield>') # record/1328021/export/xme
expected = [
{
'curated_relation': True,
'name': 'Indiana U.',
'record': {
'$ref': 'http://localhost:5000/api/institutions/902874',
},
},
{
'curated_relation': True,
'name': 'NIST, Wash., D.C.',
'record': {
'$ref': 'http://localhost:5000/api/institutions/903056',
},
},
]
result = clean_record(jobs.do(create_record(snippet)))
assert expected == result['institutions']
def test_superseded_institutions_from_110__x_z():
snippet = ('<datafield tag="110" ind1=" " ind2=" ">'
' <subfield code="a">University of Pittsburgh</subfield>'
' <subfield code="t">U. Pittsburgh</subfield>'
' <subfield code="u">U. Pittsburgh (main)</subfield>'
' <subfield code="x">Pittsburgh U., Dept. Phil.</subfield>'
' <subfield code="x">Pittsburgh U., Med. School</subfield>'
' <subfield code="z">908047</subfield>'
' <subfield code="z">905042</subfield>'
'</datafield>') # record/1272953
expected = [
{
'curated_relation': True,
'name': 'Pittsburgh U., Dept. Phil.',
'record': {
'$ref': 'http://localhost:5000/api/institutions/908047',
},
'relation_type': 'superseded',
},
{
'curated_relation': True,
'name': 'Pittsburgh U., Med. School',
'record': {
'$ref': 'http://localhost:5000/api/institutions/905042',
},
'relation_type': 'superseded',
},
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['related_institutes']
def test_dois_from_0247_a_2_and_0247_a_2_9():
snippet = (
'<record>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="9">bibmatch</subfield>'
' <subfield code="a">10.1088/1475-7516/2015/03/044</subfield>'
' </datafield>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="a">10.1088/1475-7516/2015/03/044</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'source': 'bibmatch',
'value': '10.1088/1475-7516/2015/03/044',
},
{
'value': '10.1088/1475-7516/2015/03/044',
},
]
result = clean_record(hep.do(create_record(snippet)))
assert expected == result['dois']
def test_dois_from_2472_a_2_and_247_a_2_9():
snippet = (
'<record>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="a">10.1103/PhysRevD.89.072002</subfield>'
' </datafield>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="9">bibmatch</subfield>'
' <subfield code="a">10.1103/PhysRevD.91.019903</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'value': '10.1103/PhysRevD.89.072002',
},
{
'source': 'bibmatch',
'value': '10.1103/PhysRevD.91.019903',
},
]
result = clean_record(hep.do(create_record(snippet)))
assert expected == result['dois']
def test_related_experiments_from_double_510__a_w_0():
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 = [
{
'name': 'XENON',
'record': {
'$ref': 'http://localhost:5000/api/experiments/1108293'
},
'relation': 'predecessor',
'curated_relation': True,
},
{
'name': 'XENON100',
'record': {
'$ref': 'http://localhost:5000/api/experiments/1386527'
},
'relation': 'predecessor',
'curated_relation': True,
},
]
result = clean_record(experiments.do(create_record(snippet)))
assert expected == result['related_experiments']
def test_description_from_multiple_520__a():
snippet = (
'<record>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">DAMA is an observatory for rare processes which develops and uses several low-background set-ups at the Gran Sasso National Laboratory of the I.N.F.N. (LNGS). The main experimental set-ups are: i) DAMA/NaI (about 100 kg of highly radiopure NaI(Tl)), which completed its data taking on July 2002</subfield>'
' </datafield>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">ii) DAMA/LXe (about 6.5 kg liquid Kr-free Xenon enriched either in 129Xe or in 136Xe)</subfield>'
' </datafield>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">iii) DAMA/R&D, devoted to tests on prototypes and to small scale experiments, mainly on the investigations of double beta decay modes in various isotopes. iv) the second generation DAMA/LIBRA set-up (about 250 kg highly radiopure NaI(Tl)) in operation since March 2003</subfield>'
' </datafield>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">v) the low background DAMA/Ge detector mainly devoted to sample measurements: in some measurements on rare processes the low-background Germanium detectors of the LNGS facility are also used. Moreover, a third generation R&D is in progress towards a possible 1 ton set-up, DAMA proposed in 1996. In particular, the DAMA/NaI and the DAMA/LIBRA set-ups have investigated the presence of Dark Matter particles in the galactic halo by exploiting the Dark Matter annual modulation signature.</subfield>'
' </datafield>'
'</record>') # record/1110568
expected = [
'DAMA is an observatory for rare processes which develops and uses several low-background set-ups at the Gran Sasso National Laboratory of the I.N.F.N. (LNGS). The main experimental set-ups are: i) DAMA/NaI (about 100 kg of highly radiopure NaI(Tl)), which completed its data taking on July 2002',
'ii) DAMA/LXe (about 6.5 kg liquid Kr-free Xenon enriched either in 129Xe or in 136Xe)',
'iii) DAMA/R&D, devoted to tests on prototypes and to small scale experiments, mainly on the investigations of double beta decay modes in various isotopes. iv) the second generation DAMA/LIBRA set-up (about 250 kg highly radiopure NaI(Tl)) in operation since March 2003',
'v) the low background DAMA/Ge detector mainly devoted to sample measurements: in some measurements on rare processes the low-background Germanium detectors of the LNGS facility are also used. Moreover, a third generation R&D is in progress towards a possible 1 ton set-up, DAMA proposed in 1996. In particular, the DAMA/NaI and the DAMA/LIBRA set-ups have investigated the presence of Dark Matter particles in the galactic halo by exploiting the Dark Matter annual modulation signature.',
]
result = clean_record(experiments.do(create_record(snippet)))
assert expected == result['description']
def test_experiment_names_and_affiliations_from_marcxml_multiple_119():
snippet = ('<record>'
' <datafield tag="119" ind1=" " ind2=" ">'
' <subfield code="a">LATTICE-UKQCD</subfield>'
' </datafield>'
' <datafield tag="119" ind1=" " ind2=" ">'
' <subfield code="u">Cambridge U.</subfield>'
' </datafield>'
' <datafield tag="119" ind1=" " ind2=" ">'
' <subfield code="u">Edinburgh U.</subfield>'
' <subfield code="z">902787</subfield>'
' </datafield>'
' <datafield tag="119" ind1=" " ind2=" ">'
' <subfield code="u">Swansea U.</subfield>'
' </datafield>'
'</record>') # record/1228417
result = clean_record(experiments.do(create_record(snippet)))
assert result['experiment_names'] == [{'title': 'LATTICE-UKQCD'}]
assert result['affiliations'] == [{
'curated_relation': False,
'name': 'Cambridge U.'
}, {
'curated_relation': True,
'name': 'Edinburgh U.',
'record': {
'$ref': 'http://localhost:5000/api/institutions/902787',
},
}, {
'curated_relation': False,
'name': 'Swansea U.'
}]
def test_ids_from_double_035__a_9():
snippet = (
'<record>'
' <datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="a">INSPIRE-00134135</subfield>'
' <subfield code="9">INSPIRE</subfield>'
' </datafield>'
' <datafield tag="035" ind1=" " ind2=" ">'
' <subfield code="a">H.Vogel.1</subfield>'
' <subfield code="9">BAI</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'type': 'INSPIRE ID',
'value': 'INSPIRE-00134135',
},
{
'type': 'INSPIRE BAI',
'value': 'H.Vogel.1',
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['ids']
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_dois_from_0247_a_2_and_0247_a_2_9():
snippet = (
'<record>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="9">bibmatch</subfield>'
' <subfield code="a">10.1088/1475-7516/2015/03/044</subfield>'
' </datafield>'
' <datafield tag="024" ind1="7" ind2=" ">'
' <subfield code="2">DOI</subfield>'
' <subfield code="a">10.1088/1475-7516/2015/03/044</subfield>'
' </datafield>'
'</record>')
expected = [
{
'source': 'bibmatch',
'value': '10.1088/1475-7516/2015/03/044',
},
{
'value': '10.1088/1475-7516/2015/03/044',
},
]
result = clean_record(hep.do(create_record(snippet)))
assert expected == result['dois']
def test_multiple_issn_from_marcxml_022():
"""Test multiple ISSNs."""
snippet = (
'<record>'
' <datafield tag="022" ind1=" " ind2=" ">'
' <subfield code="a">2349-2716</subfield>'
' <subfield code="b">Online</subfield>'
' </datafield>'
' <datafield tag="022" ind1=" " ind2=" ">'
' <subfield code="a">2349-6088</subfield>'
' <subfield code="b">Print</subfield>'
' </datafield>'
'</record>'
)
expected = [
{
'medium': 'online',
'value': '2349-2716',
},
{
'medium': 'print',
'value': '2349-6088',
},
]
result = clean_record(journals.do(create_record(snippet)))
assert expected == result['issn']
def test_hidden_notes_from_595__a_9_and_595__double_a_9():
snippet = (
'<record>'
' <datafield tag="595" ind1=" " ind2=" ">'
' <subfield code="9">SPIRES-HIDDEN</subfield>'
' <subfield code="a">Title changed from ALLCAPS</subfield>'
' </datafield>'
' <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>'
) # record/109310
expected = [
{
'source': 'SPIRES-HIDDEN',
'value': 'Title changed from ALLCAPS',
},
{
'source': 'SPIRES-HIDDEN',
'value': 'TeXtitle from script',
},
{
'source': 'SPIRES-HIDDEN',
'value': 'no affiliation (not clear pn the fulltext)',
},
]
result = clean_record(hep.do(create_record(snippet)))
assert expected == result['hidden_notes']
def test_institution_from_double_110__a():
snippet = (
'<record>'
' <datafield tag="110" ind1=" " ind2=" ">'
' <subfield code="a">Coll. William and Mary</subfield>'
' </datafield>'
' <datafield tag="110" ind1=" " ind2=" ">'
' <subfield code="a">Jefferson Lab</subfield>'
' </datafield>'
'</record>'
) # record/1427342
expected = [
{
'curated_relation': False,
'name': 'Coll. William and Mary',
},
{
'curated_relation': False,
'name': 'Jefferson Lab',
},
]
result = clean_record(jobs.do(create_record(snippet)))
assert expected == result['institution']
def test_address_from_marcxml_371__a_double_b_c_d_e_g():
snippet = ('<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">Philosophenweg 16</subfield>'
' <subfield code="b">Altstadt</subfield>'
' <subfield code="b">Heidelberg</subfield>'
' <subfield code="c">Baden-Wuerttemberg</subfield>'
' <subfield code="d">Germany</subfield>'
' <subfield code="e">69120</subfield>'
' <subfield code="g">DE</subfield>'
'</datafield>')
expected = [
{
'city': 'Altstadt, Heidelberg',
'country': 'Germany',
'country_code': 'DE',
'state': 'Baden-Wuerttemberg',
'original_address': [
'Philosophenweg 16',
],
'postal_code': '69120',
},
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['address']
def test_regions_from_043__a_corrects_misspellings():
snippet = '<datafield tag="043" ind1=" " ind2=" ">' ' <subfield code="a">United States</subfield>' "</datafield>"
expected = ["North America"]
result = clean_record(jobs.do(create_record(snippet)))
assert expected == result["regions"]
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_extra_words_from_410__decuple_g():
snippet = (
'<datafield tag="410" ind1=" " ind2=" ">'
' <subfield code="g">Institut Theoretische Physik,</subfield>'
' <subfield code="g">RWTH, Inst.</subfield>'
' <subfield code="g">institute A</subfield>'
' <subfield code="g">III. Physikalisches Institut, Technische Hochschule Aachen, Aachen, West</subfield>'
' <subfield code="g">physics</subfield>'
' <subfield code="g">52056</subfield>'
' <subfield code="g">D-52056</subfield>'
' <subfield code="g">DE-52056</subfield>'
' <subfield code="g">phys</subfield>'
' <subfield code="g">I. Physikalisches Institut</subfield>'
'</datafield>'
) # record/902624
expected = [
'Institut Theoretische Physik,',
'RWTH, Inst.',
'institute A',
'III. Physikalisches Institut, Technische Hochschule Aachen, Aachen, West',
'physics',
'52056',
'D-52056',
'DE-52056',
'phys',
'I. Physikalisches Institut',
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['extra_words']
def test_regions_from_043__a():
snippet = '<datafield tag="043" ind1=" " ind2=" ">' ' <subfield code="a">Asia</subfield>' "</datafield>"
expected = ["Asia"]
result = clean_record(jobs.do(create_record(snippet)))
assert expected == result["regions"]
def test_positions_from_371__a_m_r_z():
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 = [
{
'curated_relation': False,
'email': '*****@*****.**',
'institution': {
'name': 'Antwerp U.',
},
'rank': 'SENIOR',
'_rank': 'SENIOR',
'status': 'Current',
},
]
result = clean_record(hepnames.do(create_record(snippet)))
assert expected == result['positions']
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_spokespersons_from_702__a_i_z():
snippet = (
'<datafield tag="702" ind1=" " ind2=" ">'
' <subfield code="a">Hogan, Craig J.</subfield>'
' <subfield code="i">INSPIRE-00090662</subfield>'
' <subfield code="z">Current</subfield>'
'</datafield>'
) # record/1108189
expected = [
{
'ids': [
{
'type': 'INSPIRE ID',
'value': 'INSPIRE-00090662',
},
],
'name': 'Hogan, Craig J.',
'current': True,
'curated_relation': False,
},
]
result = clean_record(experiments.do(create_record(snippet)))
assert expected == result['spokespersons']
def test_related_experiments_from_double_510__a_w_0():
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 = [
{
'name': 'XENON',
'record': {'$ref': 'http://localhost:5000/api/experiments/1108293'},
'relation': 'predecessor',
'curated_relation': True,
},
{
'name': 'XENON100',
'record': {'$ref': 'http://localhost:5000/api/experiments/1386527'},
'relation': 'predecessor',
'curated_relation': True,
},
]
result = clean_record(experiments.do(create_record(snippet)))
assert expected == result['related_experiments']
def test_extra_words_from_410__decuple_g():
snippet = (
'<datafield tag="410" ind1=" " ind2=" ">'
' <subfield code="g">Institut Theoretische Physik,</subfield>'
' <subfield code="g">RWTH, Inst.</subfield>'
' <subfield code="g">institute A</subfield>'
' <subfield code="g">III. Physikalisches Institut, Technische Hochschule Aachen, Aachen, West</subfield>'
' <subfield code="g">physics</subfield>'
' <subfield code="g">52056</subfield>'
' <subfield code="g">D-52056</subfield>'
' <subfield code="g">DE-52056</subfield>'
' <subfield code="g">phys</subfield>'
' <subfield code="g">I. Physikalisches Institut</subfield>'
'</datafield>') # record/902624
expected = [
'Institut Theoretische Physik,',
'RWTH, Inst.',
'institute A',
'III. Physikalisches Institut, Technische Hochschule Aachen, Aachen, West',
'physics',
'52056',
'D-52056',
'DE-52056',
'phys',
'I. Physikalisches Institut',
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['extra_words']
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 test_address_from_marcxml_371__a_b_c_d_double_e_g():
snippet = (
'<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">Philosophenweg 16</subfield>'
' <subfield code="b">Heidelberg</subfield>'
' <subfield code="c">Baden-Wuerttemberg</subfield>'
' <subfield code="d">Germany</subfield>'
' <subfield code="e">69120</subfield>'
' <subfield code="e">DE-119</subfield>'
' <subfield code="g">DE</subfield>'
'</datafield>'
)
expected = [
{
'city': 'Heidelberg',
'country': 'Germany',
'country_code': 'DE',
'state': 'Baden-Wuerttemberg',
'original_address': [
'Philosophenweg 16',
],
'postal_code': '69120, DE-119',
}
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['address']
def test_address_from_marcxml_371__a_b_c_d_e_double_g():
snippet = (
'<datafield tag="371" ind1=" " ind2=" ">'
' <subfield code="a">Philosophenweg 16</subfield>'
' <subfield code="b">Heidelberg</subfield>'
' <subfield code="c">Baden-Wuerttemberg</subfield>'
' <subfield code="d">Germany</subfield>'
' <subfield code="e">69120</subfield>'
' <subfield code="g">DE</subfield>'
' <subfield code="g">DE</subfield>'
'</datafield>'
)
expected = [
{
"city": "Heidelberg",
"country": "Germany",
"country_code": "DE",
"state": "Baden-Wuerttemberg",
"original_address": [
"Philosophenweg 16",
],
"postal_code": "69120",
},
]
result = clean_record(institutions.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_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_related_institutes_from__double_510_a_w_0_predecessor():
snippet = ('<record>'
' <datafield tag="510" ind1=" " ind2=" ">'
' <subfield code="0">903276</subfield>'
' <subfield code="a">INS, Tokyo</subfield>'
' <subfield code="w">a</subfield>'
' </datafield>'
' <datafield tag="510" ind1=" " ind2=" ">'
' <subfield code="0">905439</subfield>'
' <subfield code="a">U. Tokyo, Meson Sci. Lab.</subfield>'
' <subfield code="w">a</subfield>'
' </datafield>'
'</record>') # record/902916
expected = [
{
'curated_relation': True,
'name': 'INS, Tokyo',
'relation_type': 'predecessor',
'record': {
'$ref': 'http://localhost:5000/api/institutions/903276',
},
},
{
'curated_relation': True,
'name': 'U. Tokyo, Meson Sci. Lab.',
'relation_type': 'predecessor',
'record': {
'$ref': 'http://localhost:5000/api/institutions/905439',
},
},
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['related_institutes']
def test_related_institutes_from__double_510_a_w_0():
snippet = ('<record>'
' <datafield tag="510" ind1=" " ind2=" ">'
' <subfield code="0">1385404</subfield>'
' <subfield code="a">U. Caen (main)</subfield>'
' <subfield code="w">t</subfield>'
' </datafield>'
' <datafield tag="510" ind1=" " ind2=" ">'
' <subfield code="0">926589</subfield>'
' <subfield code="a">CNRS, France</subfield>'
' <subfield code="w">t</subfield>'
' </datafield>'
'</record>') # record/1430106
expected = [
{
'curated_relation': True,
'name': 'U. Caen (main)',
'relation_type': 'parent',
'record': {
'$ref': 'http://localhost:5000/api/institutions/1385404',
},
},
{
'curated_relation': True,
'name': 'CNRS, France',
'relation_type': 'parent',
'record': {
'$ref': 'http://localhost:5000/api/institutions/926589',
},
},
]
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['related_institutes']
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_description_from_multiple_520__a():
snippet = (
'<record>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">DAMA is an observatory for rare processes which develops and uses several low-background set-ups at the Gran Sasso National Laboratory of the I.N.F.N. (LNGS). The main experimental set-ups are: i) DAMA/NaI (about 100 kg of highly radiopure NaI(Tl)), which completed its data taking on July 2002</subfield>'
' </datafield>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">ii) DAMA/LXe (about 6.5 kg liquid Kr-free Xenon enriched either in 129Xe or in 136Xe)</subfield>'
' </datafield>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">iii) DAMA/R&D, devoted to tests on prototypes and to small scale experiments, mainly on the investigations of double beta decay modes in various isotopes. iv) the second generation DAMA/LIBRA set-up (about 250 kg highly radiopure NaI(Tl)) in operation since March 2003</subfield>'
' </datafield>'
' <datafield tag="520" ind1=" " ind2=" ">'
' <subfield code="a">v) the low background DAMA/Ge detector mainly devoted to sample measurements: in some measurements on rare processes the low-background Germanium detectors of the LNGS facility are also used. Moreover, a third generation R&D is in progress towards a possible 1 ton set-up, DAMA proposed in 1996. In particular, the DAMA/NaI and the DAMA/LIBRA set-ups have investigated the presence of Dark Matter particles in the galactic halo by exploiting the Dark Matter annual modulation signature.</subfield>'
' </datafield>'
'</record>'
) # record/1110568
expected = [
'DAMA is an observatory for rare processes which develops and uses several low-background set-ups at the Gran Sasso National Laboratory of the I.N.F.N. (LNGS). The main experimental set-ups are: i) DAMA/NaI (about 100 kg of highly radiopure NaI(Tl)), which completed its data taking on July 2002',
'ii) DAMA/LXe (about 6.5 kg liquid Kr-free Xenon enriched either in 129Xe or in 136Xe)',
'iii) DAMA/R&D, devoted to tests on prototypes and to small scale experiments, mainly on the investigations of double beta decay modes in various isotopes. iv) the second generation DAMA/LIBRA set-up (about 250 kg highly radiopure NaI(Tl)) in operation since March 2003',
'v) the low background DAMA/Ge detector mainly devoted to sample measurements: in some measurements on rare processes the low-background Germanium detectors of the LNGS facility are also used. Moreover, a third generation R&D is in progress towards a possible 1 ton set-up, DAMA proposed in 1996. In particular, the DAMA/NaI and the DAMA/LIBRA set-ups have investigated the presence of Dark Matter particles in the galactic halo by exploiting the Dark Matter annual modulation signature.',
]
result = clean_record(experiments.do(create_record(snippet)))
assert expected == result['description']
def test_no_location_from_034__f():
snippet = ('<datafield tag="034" ind1=" " ind2=" ">'
' <subfield code="f">50.7736</subfield>'
'</datafield>') # synthetic data
result = clean_record(institutions.do(create_record(snippet)))
assert 'location' not in result
def test_core_from_690c_a_noncore():
snippet = ('<datafield tag="690" ind1="C" ind2=" ">'
' <subfield code=a">NONCORE</subfield>'
'</datafield>') # record/916025
result = clean_record(institutions.do(create_record(snippet)))
assert not result['core']
def test_date_closed_from_046__l():
snippet = (
'<datafield tag="046" ind1=" " ind2=" ">' ' <subfield code="l">2008-02-11</subfield>' "</datafield>"
) # record/934304
expected = "2008-02-11"
result = clean_record(jobs.do(create_record(snippet)))
assert expected == result["date_closed"]
def test_timezone_from_043__t():
snippet = ('<datafield tag="043" ind1=" " ind2=" ">'
' <subfield code="t">+05</subfield>'
'</datafield>') # record/902635
expected = ['+05']
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['timezone']
def test_no_location_from_034__double_d():
snippet = ('<datafield tag="034" ind1=" " ind2=" ">'
' <subfield code="d">32.540776</subfield>'
' <subfield code="d">15.561010</subfield>'
'</datafield>') # record/1442294
result = clean_record(institutions.do(create_record(snippet)))
assert 'location' not in result
def test_non_public_notes_from_667__a():
snippet = ('<datafield tag="667" ind1=" " ind2=" ">'
' <subfield code="a">Former ICN = Negev U.</subfield>'
'</datafield>') # record/902663
expected = ['Former ICN = Negev U.']
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['non_public_notes']
def test_field_activity_from_372__a():
snippet = ('<datafield tag="372" ind1=" " ind2=" ">'
' <subfield code="a">Research center</subfield>'
'</datafield>')
expected = ['Research Center']
result = clean_record(institutions.do(create_record(snippet)))
assert expected == result['field_activity']
def test_position_from_245__a():
snippet = (
'<datafield tag="245" ind1=" " ind2=" ">' ' <subfield code="a">Neutrino Physics</subfield>' "</datafield>"
) # record/1467312
expected = "Neutrino Physics"
result = clean_record(jobs.do(create_record(snippet)))
assert expected == result["position"]
