def test_replace_refs(app):
"""Test replace refs."""
app.config['INDEXER_REPLACE_REFS'] = False
app.extensions['invenio-records'].loader_cls = json_loader_factory(
JSONResolver(plugins=['demo.json_resolver']))
with app.app_context():
record = Record({'$ref': 'http://dx.doi.org/10.1234/foo'})
data = RecordIndexer._prepare_record(record, 'records', 'record')
assert '$ref' in data
app.config['INDEXER_REPLACE_REFS'] = True
with app.app_context():
record = Record({'$ref': 'http://dx.doi.org/10.1234/foo'})
data = RecordIndexer._prepare_record(record, 'records', 'record')
assert '$ref' not in data
assert json.dumps(data)
def test_replace_refs(app):
"""Test replace refs."""
app.config['INDEXER_REPLACE_REFS'] = False
app.extensions['invenio-records'].loader_cls = json_loader_factory(
JSONResolver(plugins=['demo.json_resolver']))
with app.app_context():
record = Record({'$ref': 'http://dx.doi.org/10.1234/foo'})
data = RecordIndexer._prepare_record(record, 'records', 'record')
assert '$ref' in data
app.config['INDEXER_REPLACE_REFS'] = True
with app.app_context():
record = Record({'$ref': 'http://dx.doi.org/10.1234/foo'})
data = RecordIndexer._prepare_record(record, 'records', 'record')
assert '$ref' not in data
assert json.dumps(data)
def test_records_serializers_marc(app, test_records_data):
with app.app_context():
pid, record = make_record(test_records_data)
rec = {
'_source':
RecordIndexer._prepare_record(record, 'records', 'record').copy(),
'_version':
record.revision_id
}
marcxml = oaipmh_marc21_v1(pid=pid, record=rec)
namespaces = {'m': 'http://www.loc.gov/MARC21/slim'}
def marc_controlfields(tag):
xpath = '//m:controlfield[@tag="{}"]'.format(tag)
elements = marcxml.xpath(xpath, namespaces=namespaces)
return [x.text for x in elements]
def marc_datafields(tag, subfield_code):
xpath = '//m:datafield[@tag="{}"]/m:subfield[@code="{}"]'.format(
tag, subfield_code)
elements = marcxml.xpath(xpath, namespaces=namespaces)
return [x.text for x in elements]
def marc_files():
xpath = '//m:datafield[@tag="856" and @ind1="4"]/m:subfield[@code="u"]'
elements = marcxml.xpath(xpath, namespaces=namespaces)
return [x.text for x in elements]
creators_and_contributors = [
r['creator_name'] for r in record['creators']
]
creators_and_contributors.extend(
[r['contributor_name'] for r in record['contributors']])
assert marc_controlfields('001') == [pid.pid_value]
assert marc_datafields('100', 'a') == creators_and_contributors[:1]
assert marc_datafields('245',
'a') == [r['title'] for r in record['titles']]
assert marc_datafields('260', 'b') == [record['publisher']]
assert marc_datafields('260', 'c') == [record['publication_date']]
assert marc_datafields('337', 'a') == [
r['resource_type_general'] for r in record['resource_types']
]
assert marc_datafields(
'520', 'a') == [r['description'] for r in record['descriptions']]
assert marc_datafields('526', 'a') == record.get('disciplines')
assert marc_datafields(
'540', 'a') == [record.get('license', {}).get('license')]
assert marc_datafields(
'542', 'l') == ['open' if record['open_access'] else 'closed']
assert marc_datafields('546', 'a') == [record['language']]
assert marc_datafields('653', 'a') == record.get('keywords')
assert marc_datafields('700', 'a') == creators_and_contributors[1:]
assert marc_files() == [f['ePIC_PID'] for f in record.get('_files')]
def create_index_op(record):
index, doc_type = current_record_to_index(record)
return {
'_op_type': 'index',
'_index': index,
'_type': doc_type,
'_id': str(record.id),
'_version': record.revision_id,
'_version_type': 'external_gte',
'_source': RecordIndexer._prepare_record(record, index, doc_type),
}
def create_index_op(record):
index, doc_type = current_record_to_index(record)
return {
'_op_type': 'index',
'_index': index,
'_type': doc_type,
'_id': str(record.id),
'_version': record.revision_id,
'_version_type': 'external_gte',
'_source': RecordIndexer._prepare_record(record, index, doc_type),
}
def test_records_serializers_dc(app, test_records_data):
with app.app_context():
pid, record = make_record(test_records_data)
rec = {
'_source':
RecordIndexer._prepare_record(record, 'records', 'record').copy(),
'_version':
record.revision_id
}
dcxml = oaipmh_oai_dc(pid=pid, record=rec)
namespaces = {'dc': 'http://purl.org/dc/elements/1.1/'}
identifiers = dcxml.xpath('//dc:identifier', namespaces=namespaces)
titles = dcxml.xpath('//dc:title', namespaces=namespaces)
creators = dcxml.xpath('//dc:creator', namespaces=namespaces)
descriptions = dcxml.xpath('//dc:description', namespaces=namespaces)
subjects = dcxml.xpath('//dc:subject', namespaces=namespaces)
contributors = dcxml.xpath('//dc:contributor', namespaces=namespaces)
rights = dcxml.xpath('//dc:rights', namespaces=namespaces)
publishers = dcxml.xpath('//dc:publisher', namespaces=namespaces)
languages = dcxml.xpath('//dc:language', namespaces=namespaces)
types = dcxml.xpath('//dc:type', namespaces=namespaces)
assert identifiers
for x in identifiers:
assert x.text.endswith(pid.pid_value)
assert [x.text
for x in titles] == [r['title'] for r in record['titles']]
assert [x.text for x in creators
] == [r['creator_name'] for r in record['creators']]
assert [x.text for x in descriptions
] == [r['description'] for r in record['descriptions']]
assert [x.text for x in types] == [
r['resource_type_general'] for r in record['resource_types']
]
assert [x.text for x in contributors
] == [r['contributor_name'] for r in record['contributors']]
assert [x.text for x in publishers] == [record['publisher']]
assert [x.text for x in languages] == [record['language']]
assert [x.text for x in subjects] == record.get('keywords')
rights = [x.text for x in rights]
access = 'info:eu-repo/semantics/closedAccess'
if record['open_access']:
access = 'info:eu-repo/semantics/openAccess'
assert access in rights
license = record.get('license', {}).get('license')
if license:
assert license in rights
def test_records_serializers_marc(app, test_records_data):
with app.app_context():
pid, record = make_record(test_records_data)
rec = {
'_source': RecordIndexer._prepare_record(
record, 'records', 'record'
).copy(),
'_version': record.revision_id
}
marcxml = oaipmh_marc21_v1(pid=pid, record=rec)
namespaces = {'m':'http://www.loc.gov/MARC21/slim'}
def marc_controlfields(tag):
xpath = '//m:controlfield[@tag="{}"]'.format(tag)
elements = marcxml.xpath(xpath, namespaces=namespaces)
return [x.text for x in elements]
def marc_datafields(tag, subfield_code):
xpath = '//m:datafield[@tag="{}"]/m:subfield[@code="{}"]'.format(
tag, subfield_code)
elements = marcxml.xpath(xpath, namespaces=namespaces)
return [x.text for x in elements]
def marc_files():
xpath = '//m:datafield[@tag="856" and @ind1="4"]/m:subfield[@code="u"]'
elements = marcxml.xpath(xpath, namespaces=namespaces)
return [x.text for x in elements]
creators_and_contributors = [r['creator_name'] for r in record['creators']]
creators_and_contributors.extend([r['contributor_name']
for r in record['contributors']])
assert marc_controlfields('001') == [pid.pid_value]
assert marc_datafields('100', 'a') == creators_and_contributors[:1]
assert marc_datafields('245', 'a') == [r['title'] for r in record['titles']]
assert marc_datafields('260', 'b') == [record['publisher']]
assert marc_datafields('260', 'c') == [record['publication_date']]
assert marc_datafields('337', 'a') == [
r['resource_type_general'] for r in record['resource_types']]
assert marc_datafields('520', 'a') == [r['description'] for r in record['descriptions']]
assert marc_datafields('526', 'a') == record.get('disciplines')
assert marc_datafields('540', 'a') == [record.get('license', {}).get('license')]
assert marc_datafields('542', 'l') == ['open' if record['open_access'] else 'closed']
assert marc_datafields('546', 'a') == [record['language']]
assert marc_datafields('653', 'a') == record.get('keywords')
assert marc_datafields('700', 'a') == creators_and_contributors[1:]
assert marc_files() == [f['ePIC_PID'] for f in record.get('_files')]
def create_index_op(record, version_type='external_gte'):
from inspirehep.modules.records.receivers import enhance_before_index
index, doc_type = current_record_to_index(record)
enhance_before_index(record)
return {
'_op_type': 'index',
'_index': index,
'_type': doc_type,
'_id': str(record.id),
'version': record.revision_id,
'version_type': version_type,
'_source': RecordIndexer._prepare_record(record, index, doc_type),
}
def create_index_op(record, version_type='external_gte'):
from inspirehep.modules.records.receivers import enhance_before_index
index, doc_type = current_record_to_index(record)
enhance_before_index(record)
return {
'_op_type': 'index',
'_index': index,
'_type': doc_type,
'_id': str(record.id),
'_version': record.revision_id,
'_version_type': version_type,
'_source': RecordIndexer._prepare_record(record, index, doc_type),
}
def test_records_serializers_dc(app, test_records_data):
with app.app_context():
pid, record = make_record(test_records_data)
rec = {
'_source': RecordIndexer._prepare_record(
record, 'records', 'record'
).copy(),
'_version': record.revision_id
}
dcxml = oaipmh_oai_dc(pid=pid, record=rec)
namespaces = {'dc':'http://purl.org/dc/elements/1.1/'}
identifiers = dcxml.xpath('//dc:identifier', namespaces=namespaces)
titles = dcxml.xpath('//dc:title', namespaces=namespaces)
creators = dcxml.xpath('//dc:creator', namespaces=namespaces)
descriptions = dcxml.xpath('//dc:description', namespaces=namespaces)
subjects = dcxml.xpath('//dc:subject', namespaces=namespaces)
contributors = dcxml.xpath('//dc:contributor', namespaces=namespaces)
rights = dcxml.xpath('//dc:rights', namespaces=namespaces)
publishers = dcxml.xpath('//dc:publisher', namespaces=namespaces)
languages = dcxml.xpath('//dc:language', namespaces=namespaces)
types = dcxml.xpath('//dc:type', namespaces=namespaces)
assert identifiers
for x in identifiers:
assert x.text.endswith(pid.pid_value)
assert [x.text for x in titles] == [r['title'] for r in record['titles']]
assert [x.text for x in creators] == [r['creator_name'] for r in record['creators']]
assert [x.text for x in descriptions] == [r['description'] for r in record['descriptions']]
assert [x.text for x in types] == [
r['resource_type_general'] for r in record['resource_types']]
assert [x.text for x in contributors] == [
r['contributor_name'] for r in record['contributors']]
assert [x.text for x in publishers] == [record['publisher']]
assert [x.text for x in languages] == [record['language']]
assert [x.text for x in subjects] == record.get('keywords')
rights = [x.text for x in rights]
access = 'info:eu-repo/semantics/closedAccess'
if record['open_access']:
access = 'info:eu-repo/semantics/openAccess'
assert access in rights
license = record.get('license', {}).get('license')
if license:
assert license in rights
