def test_create(app, document_json):
"""Test creating a record."""
record = DocumentRecord.create(document_json)
assert DocumentRecord.get_record_by_pid(
record['pid'])['pid'] == record['pid']
DocumentRecord.create(document_json, dbcommit=True)
assert DocumentRecord.get_record_by_pid(
record['pid'])['pid'] == record['pid']
def test_create(app):
"""Test creating a record."""
DocumentRecord.create({"pid": "1", "title": "The title of the record"})
DocumentRecord.create({
"pid": "2",
"title": "The title of the record"
},
dbcommit=True)
def test_missing_pids(app, es_clear, document_json):
"""Test missing PIDs."""
document_json['pid'] = '1000'
document = DocumentRecord.create(data=document_json, dbcommit=True)
monitoring = DataIntegrityMonitoring()
# Only in DB
assert monitoring.missing_pids('doc') == {
'db': ['1000'],
'es': [],
'es_double': []
}
# OK
document.reindex()
assert monitoring.missing_pids('doc') == {
'db': [],
'es': [],
'es_double': []
}
# Only in ES
document.delete()
assert monitoring.missing_pids('doc') == {
'db': [],
'es': ['1000'],
'es_double': []
}
# With deleted
assert monitoring.missing_pids('doc', True) == {
'db': [],
'es': [],
'es_double': []
}
# Duplicate
document2 = DocumentRecord.create(data=document_json, dbcommit=True)
document2.reindex()
current_search.flush_and_refresh('documents')
assert monitoring.missing_pids('doc') == {
'db': [],
'es': ['1000'],
'es_double': ['1000']
}
# Index not configured
app.config.get('RECORDS_REST_ENDPOINTS')['doc'].pop('search_index', None)
with pytest.raises(Exception) as exception:
monitoring.missing_pids('doc')
assert str(
exception.value) == 'No "search_index" configured for resource "doc"'
app.config.get(
'RECORDS_REST_ENDPOINTS')['doc']['search_index'] = 'documents'
def _make_document(organisation='org', with_file=False, pid=None):
if organisation:
make_organisation(organisation)
document_json['organisation'] = {
'$ref': 'https://sonar.ch/api/organisations/org'
}
if pid:
document_json['pid'] = pid
else:
document_json.pop('pid', None)
record = DocumentRecord.create(document_json,
dbcommit=True,
with_bucket=True)
record.commit()
db.session.commit()
if with_file:
with open(pdf_file, 'rb') as file:
record.add_file(file.read(),
'test1.pdf',
order=1,
restricted='insitution',
embargo_date='2021-01-01')
record.commit()
db.session.commit()
record.reindex()
return record
def _make_document(organisation='org', with_file=False, pid=None):
if organisation:
make_organisation(organisation)
document_json['organisation'] = [{
'$ref':
'https://sonar.ch/api/organisations/org'
}]
if pid:
document_json['pid'] = pid
else:
document_json.pop('pid', None)
document_json.pop('_oai', None)
record = DocumentRecord.create(document_json,
dbcommit=True,
with_bucket=True)
record.commit()
db.session.commit()
if with_file:
with open(pdf_file, 'rb') as file:
record.add_file(file.read(),
'test1.pdf',
order=1,
access='coar:c_f1cf',
restricted_outside_organisation=False,
embargo_date=embargo_date.isoformat())
record.commit()
db.session.commit()
record.reindex()
return record
def test_dbcommit(app, document_json):
"""Test record commit to db."""
record = DocumentRecord.create(document_json)
record.dbcommit()
assert DocumentRecord.get_record_by_pid(
record['pid'])['pid'] == record['pid']
def test_detail(app, client):
"""Test document detail page."""
record = DocumentRecord.create({
"title": "The title of the record"
}, dbcommit=True)
# assert isinstance(views.detail('1', record, ir='sonar'), str)
assert client.get('/organization/sonar/documents/1').status_code == 200
def test_get_record_by_pid(app, document_json):
"""Test get record by PID."""
assert DocumentRecord.get_record_by_pid('not-existing') is None
record = DocumentRecord.create(document_json)
assert DocumentRecord.get_record_by_pid(
record['pid'])['pid'] == record['pid']
record.delete()
assert DocumentRecord.get_record_by_pid(record['pid']) is None
def test_get_record_by_pid(app):
"""Test get record by PID."""
assert DocumentRecord.get_record_by_pid('ABCD') is None
record = DocumentRecord.create({
"pid": "ABCD",
"title": "The title of the record"
})
assert DocumentRecord.get_record_by_pid('ABCD')['pid'] == 'ABCD'
record.delete()
assert DocumentRecord.get_record_by_pid('ABCD') is None
def test_institution_resolver(client):
"""Test institution resolver."""
InstitutionRecord.create({
"pid": "usi",
"name": "Università della Svizzera italiana"
})
record = DocumentRecord.create({
"title": "The title of the record",
"institution": {
"$ref": "https://sonar.ch/api/institutions/usi"
}
})
assert record.replace_refs().get('institution')['name'] == 'Università ' \
'della Svizzera italiana'
def test_index_record(client, db, document_json, superuser):
"""Test index a record."""
login_user_via_session(client, email=superuser['email'])
res = client.get(url_for('invenio_records_rest.doc_list'))
assert res.status_code == 200
total = res.json['hits']['total']['value']
record = DocumentRecord.create(document_json, dbcommit=True)
db.session.commit()
indexer = DocumentIndexer()
indexer.index(record)
res = client.get(url_for('invenio_records_rest.doc_list'))
assert res.status_code == 200
assert res.json['hits']['total']['value'] == (total + 1)
def test_reindex(app, db, client, document_json, superuser):
"""Test record reindex."""
record = DocumentRecord.create(document_json)
db.session.commit()
indexer = DocumentIndexer()
indexer.index(record)
headers = [('Content-Type', 'application/json')]
url = url_for('invenio_records_rest.doc_item', pid_value=record['pid'])
login_user_via_session(client, email=superuser['email'])
response = client.get(url, headers=headers)
data = response.json
assert response.status_code == 200
assert data['metadata']['pid'] == record['pid']
def minimal_document(db, bucket_location, organisation):
record = DocumentRecord.create(
{
'pid':
'1000',
'title': [{
'type':
'bf:Title',
'mainTitle': [{
'language': 'eng',
'value': 'Title of the document'
}]
}],
'organisation': [{
'$ref': 'https://sonar.ch/api/organisations/org'
}]
},
dbcommit=True,
with_bucket=True)
record.commit()
db.session.commit()
return record
def create_document(self):
"""Create document from deposit."""
metadata = {}
# Organisation
if current_user_record and current_user_record.get('organisation'):
metadata['organisation'] = [current_user_record['organisation']]
# Document type
metadata['documentType'] = self['metadata']['documentType']
# Language
language = self['metadata'].get('language', 'eng')
# Title
metadata['title'] = [{
'type':
'bf:Title',
'mainTitle': [{
'language': language,
'value': self['metadata']['title']
}]
}]
# Subtitle
if self['metadata'].get('subtitle'):
metadata['title'][0]['subtitle'] = [{
'language':
language,
'value':
self['metadata']['subtitle']
}]
# Other title
if self['metadata'].get('otherLanguageTitle', {}).get('title'):
metadata['title'][0]['mainTitle'].append({
'language':
self['metadata']['otherLanguageTitle'].get(
'language', language),
'value':
self['metadata']['otherLanguageTitle']['title']
})
# Languages
metadata['language'] = [{'value': language, 'type': 'bf:Language'}]
# Document date
metadata['provisionActivity'] = [{
'type':
'bf:Publication',
'startDate':
self['metadata']['documentDate']
}]
metadata['provisionActivity'][0]['statement'] = []
# Publication place
if self['metadata'].get('publicationPlace'):
metadata['provisionActivity'][0]['statement'].append({
'label': [{
'value': self['metadata']['publicationPlace']
}],
'type':
'bf:Place'
})
# Publisher
if self['metadata'].get('publisher'):
metadata['provisionActivity'][0]['statement'].append({
'label': [{
'value': self['metadata']['publisher']
}],
'type':
'bf:Agent'
})
# Add a statement for date
metadata['provisionActivity'][0]['statement'].append({
'label': [{
'value': self['metadata']['documentDate']
}],
'type':
'Date'
})
# Published in
if self['metadata'].get('publication'):
part_of = {
'numberingYear': self['metadata']['publication']['year'],
'document': {
'title': self['metadata']['publication']['publishedIn']
}
}
if self['metadata']['publication'].get('pages'):
part_of['numberingPages'] = self['metadata']['publication'][
'pages']
if self['metadata']['publication'].get('volume'):
part_of['numberingVolume'] = self['metadata']['publication'][
'volume']
if self['metadata']['publication'].get('number'):
part_of['numberingIssue'] = self['metadata']['publication'][
'number']
if self['metadata']['publication'].get('editors'):
part_of['document']['contribution'] = self['metadata'][
'publication']['editors']
if self['metadata']['publication'].get('publisher'):
part_of['document']['publication'] = {
'statement': self['metadata']['publication']['publisher']
}
metadata['partOf'] = [part_of]
# Other electronic versions
if self['metadata'].get('otherElectronicVersions'):
metadata['otherEdition'] = [{
'document': {
'electronicLocator': link['url']
},
'publicNote': link['publicNote']
} for link in self['metadata']['otherElectronicVersions']]
# Specific collections
if self['metadata'].get('specificCollections'):
metadata['specificCollections'] = self['metadata'][
'specificCollections']
# Classification
if self['metadata'].get('classification'):
metadata['classification'] = [{
'type':
'bf:ClassificationUdc',
'classificationPortion':
self['metadata']['classification']
}]
# Abstracts
if self['metadata'].get('abstracts'):
metadata['abstracts'] = [{
'language':
abstract.get('language', language),
'value':
abstract['abstract']
} for abstract in self['metadata']['abstracts']]
# Dissertation
if self['metadata'].get('dissertation'):
metadata['dissertation'] = self['metadata']['dissertation']
# Subjects
if self['metadata'].get('subjects'):
metadata['subjects'] = [{
'label': {
'language': subject.get('language', language),
'value': subject['subjects']
}
} for subject in self['metadata']['subjects']]
# Identifiers
identifiers = []
if self['metadata'].get('identifiedBy'):
for identifier in self['metadata']['identifiedBy']:
data = {
'type': identifier['type'],
'value': identifier['value'],
}
if identifier.get('source'):
data['source'] = identifier['source']
# Special for PMID
if identifier['type'] == 'pmid':
data['source'] = 'PMID'
data['type'] = 'bf:Local'
identifiers.append(data)
if identifiers:
metadata['identifiedBy'] = identifiers
# Contributors
contributors = []
for contributor in self.get('contributors', []):
data = {
'agent': {
'type': 'bf:Person',
'preferred_name': contributor['name']
},
'role': [contributor['role']]
}
if contributor.get('affiliation'):
data['affiliation'] = contributor['affiliation']
# ORCID for contributor
if contributor.get('orcid'):
data['agent']['identifiedBy'] = {
'type': 'bf:Local',
'source': 'ORCID',
'value': contributor['orcid']
}
contributors.append(data)
if contributors:
metadata['contribution'] = contributors
# Projects
if self.get('projects'):
projects = []
for project in self['projects']:
# Create a new project
if not project.get('$ref'):
data = project.copy()
# Store user
data['user'] = self['user']
# Store organisation
data['organisation'] = current_user_record['organisation']
# Project identifier
if project.get('identifier'):
data['identifiedBy'] = {
'type': 'bf:Identifier',
'value': project['identifier']
}
data.pop('identifier')
# Investigators
if project.get('investigators'):
data['investigators'] = []
for investigator in project['investigators']:
investigator_data = {
'agent': {
'preferred_name': investigator['name']
},
'role': [investigator['role']],
}
if investigator.get('affiliation'):
investigator_data[
'affiliation'] = investigator.get(
'affiliation')
if investigator.get('orcid'):
investigator_data['identifiedBy'] = {
'type': 'bf:Local',
'source': 'ORCID',
'value': investigator.get('orcid')
}
data['investigators'].append(investigator_data)
# Funding organisations
if project.get('funding_organisations'):
data['funding_organisations'] = []
for funding_organisation in project[
'funding_organisations']:
funding_organisation_data = {
'agent': {
'preferred_name':
funding_organisation['name']
}
}
if funding_organisation.get('identifier'):
funding_organisation_data['identifiedBy'] = {
'type': 'bf:Identifier',
'value': funding_organisation['identifier']
}
data['funding_organisations'].append(
funding_organisation_data)
project_record = ProjectRecord.create(data, dbcommit=True)
project_record.reindex()
project = {
'$ref':
project_record.get_ref_link('projects',
project_record['pid'])
}
projects.append(project)
if projects:
metadata['projects'] = projects
# License
metadata['usageAndAccessPolicy'] = {
'license': self['diffusion']['license']
}
document = DocumentRecord.create(metadata,
dbcommit=True,
with_bucket=True)
current_order = 2
for file in self.files:
with file.file.storage().open() as pdf_file:
content = pdf_file.read()
if file.get('category', 'main') == 'main':
order = 1
else:
order = current_order
current_order += 1
kwargs = {
'label': file.get('label', file['key']),
'order': order
}
if file.get('embargo', False) and file.get('embargoDate'):
kwargs['access'] = 'coar:c_f1cf' # Embargoed access
kwargs['embargo_date'] = file['embargoDate']
kwargs['restricted_outside_organisation'] = file.get(
'exceptInOrganisation', False)
document.add_file(content, file['key'], **kwargs)
document.commit()
document.reindex()
self['document'] = {
'$ref': DocumentRecord.get_ref_link('documents', document['pid'])
}
return document
def test_dbcommit(app):
"""Test record commit to db."""
record = DocumentRecord.create({"title": "The title of the record"})
record.dbcommit()
def create_document(self):
"""Create document from deposit."""
# TODO : Do this whole process with a marshmallow schema serializer.
metadata = {}
# Organisation
if current_user_record and current_user_record.get('organisation'):
metadata['organisation'] = [current_user_record['organisation']]
# Document type
metadata['documentType'] = self['metadata']['documentType']
# Language
language = self['metadata'].get('language', 'eng')
# Title
metadata['title'] = [{
'type':
'bf:Title',
'mainTitle': [{
'language': language,
'value': self['metadata']['title']
}]
}]
# Subtitle
if self['metadata'].get('subtitle'):
metadata['title'][0]['subtitle'] = [{
'language':
language,
'value':
self['metadata']['subtitle']
}]
# Other title
if self['metadata'].get('otherLanguageTitle', {}).get('title'):
metadata['title'][0]['mainTitle'].append({
'language':
self['metadata']['otherLanguageTitle'].get(
'language', language),
'value':
self['metadata']['otherLanguageTitle']['title']
})
# Languages
metadata['language'] = [{'value': language, 'type': 'bf:Language'}]
# Document date
metadata['provisionActivity'] = [{
'type':
'bf:Publication',
'startDate':
self['metadata']['documentDate']
}]
metadata['provisionActivity'][0]['statement'] = []
# Publication place
if self['metadata'].get('publicationPlace'):
metadata['provisionActivity'][0]['statement'].append({
'label': [{
'value': self['metadata']['publicationPlace']
}],
'type':
'bf:Place'
})
# Publisher
if self['metadata'].get('publisher'):
metadata['provisionActivity'][0]['statement'].append({
'label': [{
'value': self['metadata']['publisher']
}],
'type':
'bf:Agent'
})
# Add a statement for date
metadata['provisionActivity'][0]['statement'].append({
'label': [{
'value':
self['metadata']['statementDate']
if self['metadata'].get('statementDate') else
self['metadata']['documentDate']
}],
'type':
'Date'
})
# Published in
if self['metadata'].get('publication'):
year = self['metadata']['publication']['year'] if self['metadata'][
'publication'].get(
'year') else self['metadata']['documentDate']
part_of = {
'numberingYear': year,
'document': {
'title': self['metadata']['publication']['publishedIn']
}
}
if self['metadata']['publication'].get('pages'):
part_of['numberingPages'] = self['metadata']['publication'][
'pages']
if self['metadata']['publication'].get('volume'):
part_of['numberingVolume'] = self['metadata']['publication'][
'volume']
if self['metadata']['publication'].get('number'):
part_of['numberingIssue'] = self['metadata']['publication'][
'number']
if self['metadata']['publication'].get('editors'):
part_of['document']['contribution'] = self['metadata'][
'publication']['editors']
if self['metadata']['publication'].get('publisher'):
part_of['document']['publication'] = {
'statement': self['metadata']['publication']['publisher']
}
if self['metadata']['publication'].get('identifiedBy'):
part_of['document']['identifiedBy'] = self['metadata'][
'publication']['identifiedBy']
metadata['partOf'] = [part_of]
# Other electronic versions
if self['metadata'].get('otherElectronicVersions'):
metadata['otherEdition'] = [{
'document': {
'electronicLocator': link['url']
},
'publicNote': link['publicNote']
} for link in self['metadata']['otherElectronicVersions']]
# Collections
if self['metadata'].get('collections'):
collections = []
for collection in self['metadata'].get('collections'):
# Create a new project
if not collection.get('$ref'):
data = collection.copy()
# Store organisation
data['organisation'] = current_user_record['organisation']
collection_record = CollectionRecord.create(data)
collection_record.reindex()
collection = {
'$ref':
SonarRecord.get_ref_link('collections',
collection_record['pid'])
}
collections.append(collection)
if collections:
metadata['collections'] = collections
# Classification
if self['metadata'].get('classification'):
metadata['classification'] = [{
'type':
'bf:ClassificationUdc',
'classificationPortion':
self['metadata']['classification']
}]
# Abstracts
if self['metadata'].get('abstracts'):
metadata['abstracts'] = [{
'language':
abstract.get('language', language),
'value':
abstract['abstract']
} for abstract in self['metadata']['abstracts']]
# Dissertation
if self['metadata'].get('dissertation'):
metadata['dissertation'] = self['metadata']['dissertation']
# Subjects
if self['metadata'].get('subjects'):
metadata['subjects'] = [{
'label': {
'language': subject.get('language', language),
'value': subject['subjects']
}
} for subject in self['metadata']['subjects']]
# Identifiers
identifiers = []
if self['metadata'].get('identifiedBy'):
for identifier in self['metadata']['identifiedBy']:
data = {
'type': identifier['type'],
'value': identifier['value'],
}
if identifier.get('source'):
data['source'] = identifier['source']
# Special for PMID
if identifier['type'] == 'pmid':
data['source'] = 'PMID'
data['type'] = 'bf:Local'
identifiers.append(data)
if identifiers:
metadata['identifiedBy'] = identifiers
# Content note
if self['metadata'].get('contentNote'):
metadata['contentNote'] = self['metadata']['contentNote']
# Extent
if self['metadata'].get('extent'):
metadata['extent'] = self['metadata']['extent']
# Additional materials
if self['metadata'].get('additionalMaterials'):
metadata['additionalMaterials'] = self['metadata'][
'additionalMaterials']
# Formats
if self['metadata'].get('formats'):
metadata['formats'] = self['metadata']['formats']
# Other material characteristics
if self['metadata'].get('otherMaterialCharacteristics'):
metadata['otherMaterialCharacteristics'] = self['metadata'][
'otherMaterialCharacteristics']
# Edition statement
if self['metadata'].get('editionStatement'):
metadata['editionStatement'] = self['metadata']['editionStatement']
# Notes
if self['metadata'].get('notes'):
metadata['notes'] = self['metadata']['notes']
# Series
if self['metadata'].get('series'):
metadata['series'] = self['metadata']['series']
# Custom fields
for field_number in range(1, 4):
field = f'customField{field_number}'
document_field = self['metadata'].get(field)
if document_field:
metadata[field] = document_field
# Contributors
contributors = []
for contributor in self.get('contributors', []):
data = {
'agent': {
'type': 'bf:Person',
'preferred_name': contributor['name']
},
'role': [contributor['role']]
}
if contributor.get('date_of_birth'):
data['agent']['date_of_birth'] = contributor['date_of_birth']
if contributor.get('date_of_death'):
data['agent']['date_of_death'] = contributor['date_of_death']
if contributor.get('affiliation'):
data['affiliation'] = contributor['affiliation']
# ORCID for contributor
if contributor.get('orcid'):
data['agent']['identifiedBy'] = {
'type': 'bf:Local',
'source': 'ORCID',
'value': contributor['orcid']
}
contributors.append(data)
if contributors:
metadata['contribution'] = contributors
# Projects
if self.get('projects'):
projects = []
for project in self['projects']:
# Create a new project
if not project.get('$ref'):
data = project.copy()
# Store user
data['user'] = self['user']
# Store organisation
data['organisation'] = current_user_record['organisation']
project_record = sonar.service('projects').create(
g.identity, {'metadata': data})
project = {
'$ref':
SonarRecord.get_ref_link('projects',
project_record['id'])
}
projects.append(project)
if projects:
metadata['projects'] = projects
# License
metadata['usageAndAccessPolicy'] = {
'license': self['diffusion']['license']
}
# Open access status
if self['diffusion'].get('oa_status'):
metadata['oa_status'] = self['diffusion']['oa_status']
# Subdivisions
if self['diffusion'].get('subdivisions'):
metadata['subdivisions'] = self['diffusion']['subdivisions']
# Masked
if self['diffusion'].get('masked') is not None:
metadata['masked'] = self['diffusion']['masked']
document = DocumentRecord.create(metadata,
dbcommit=True,
with_bucket=True)
current_order = 2
for file in self.files:
with file.file.storage().open() as pdf_file:
content = pdf_file.read()
if file.get('category', 'main') == 'main':
order = 1
else:
order = current_order
current_order += 1
kwargs = {
'label': file.get('label', file['key']),
'order': order
}
if file.get('embargo', False) and file.get('embargoDate'):
kwargs['access'] = 'coar:c_f1cf' # Embargoed access
kwargs['embargo_date'] = file['embargoDate']
kwargs['restricted_outside_organisation'] = file.get(
'exceptInOrganisation', False)
document.add_file(content, file['key'], **kwargs)
document.commit()
document.reindex()
self['document'] = {
'$ref': DocumentRecord.get_ref_link('documents', document['pid'])
}
return document
def import_records(records_to_import):
"""Import records in database and index them.
Used as celery task. "ignore_result" flag means that we don't want to
get the status and/or the result of the task, execution is faster.
:param list records_to_import: List of records to import.
:returns: List of IDs.
"""
indexer = RecordIndexer()
ids = []
for data in records_to_import:
try:
files_data = data.pop('files', [])
record = DocumentRecord.get_record_by_identifier(
data.get('identifiedBy', []))
if not record:
record = DocumentRecord.create(data,
dbcommit=False,
with_bucket=True)
else:
record.update(data)
for file_data in files_data:
# Store url and key and remove it from dict to pass dict to
# kwargs in add_file_from_url method
url = file_data.pop('url')
key = file_data.pop('key')
try:
record.add_file_from_url(url, key, **file_data)
except Exception as exception:
current_app.logger.warning(
'Error during import of file {file} of record '
'{record}: {error}'.format(
file=key,
error=exception,
record=record['identifiedBy']))
# Merge record in database, at this time it's not saved into DB.
record.commit()
# Pushing record to database, not yet persisted into DB
db.session.flush()
# Add ID for bulk index in elasticsearch
ids.append(str(record.id))
current_app.logger.info(
'Record with reference "{reference}" imported successfully'.
format(reference=record['identifiedBy']))
except Exception as exception:
current_app.logger.error(
'Error during importation of record {record}: {exception}'.
format(record=data, exception=exception))
# Commit and index records
db.session.commit()
indexer.bulk_index(ids)
indexer.process_bulk_queue()
return ids
def create_document(self):
"""Create document from deposit."""
metadata = {}
# Organisation
if current_user_record and current_user_record.get('organisation'):
metadata['organisation'] = current_user_record['organisation']
# Document type
metadata['documentType'] = self['metadata']['documentType']
# Language
language = self['metadata'].get('language', 'eng')
# Title
metadata['title'] = [{
'type':
'bf:Title',
'mainTitle': [{
'language': language,
'value': self['metadata']['title']
}]
}]
# Subtitle
if self['metadata'].get('subtitle'):
metadata['title'][0]['subtitle'] = [{
'language':
language,
'value':
self['metadata']['subtitle']
}]
# Other title
if self['metadata'].get('otherLanguageTitle', {}).get('title'):
metadata['title'][0]['mainTitle'].append({
'language':
self['metadata']['otherLanguageTitle'].get(
'language', language),
'value':
self['metadata']['otherLanguageTitle']['title']
})
# Languages
metadata['language'] = [{'value': language, 'type': 'bf:Language'}]
# Document date
if self['metadata'].get('documentDate'):
metadata['provisionActivity'] = [{
'type':
'bf:Publication',
'startDate':
self['metadata']['documentDate']
}]
# Published in
if self['metadata'].get('publication'):
part_of = {
'numberingYear': self['metadata']['publication']['year'],
'document': {
'title': self['metadata']['publication']['publishedIn']
}
}
if self['metadata']['publication'].get('pages'):
part_of['numberingPages'] = self['metadata']['publication'][
'pages']
if self['metadata']['publication'].get('volume'):
part_of['numberingVolume'] = self['metadata']['publication'][
'volume']
if self['metadata']['publication'].get('number'):
part_of['numberingIssue'] = self['metadata']['publication'][
'number']
if self['metadata']['publication'].get('editors'):
part_of['document']['contribution'] = self['metadata'][
'publication']['editors']
if self['metadata']['publication'].get('publisher'):
part_of['document']['publication'] = {
'statement': self['metadata']['publication']['publisher']
}
metadata['partOf'] = [part_of]
# Other electronic versions
if self['metadata'].get('otherElectronicVersions'):
metadata['otherEdition'] = [{
'document': {
'electronicLocator': link['url']
},
'publicNote': link['publicNote']
} for link in self['metadata']['otherElectronicVersions']]
# Specific collections
if self['metadata'].get('specificCollections'):
metadata['specificCollections'] = self['metadata'][
'specificCollections']
# Classification
if self['metadata'].get('classification'):
metadata['classification'] = [{
'type':
'bf:ClassificationUdc',
'classificationPortion':
self['metadata']['classification']
}]
# Abstracts
if self['metadata'].get('abstracts'):
metadata['abstracts'] = [{
'language':
abstract.get('language', language),
'value':
abstract['abstract']
} for abstract in self['metadata']['abstracts']]
# Subjects
if self['metadata'].get('subjects'):
metadata['subjects'] = [{
'label': {
'language': subject.get('language', language),
'value': subject['subjects']
}
} for subject in self['metadata']['subjects']]
# Contributors
contributors = []
for contributor in self['contributors']:
data = {
'agent': {
'type': 'bf:Person',
'preferred_name': contributor['name']
},
'role': [contributor['role']],
'affiliation': contributor.get('affiliation')
}
# ORCID for contributor
if contributor.get('orcid'):
data['agent']['identifiedBy'] = {
'type': 'bf:Doi',
'source': 'ORCID',
'value': contributor['orcid']
}
# Resolve controlled affiliations
if data.get('affiliation'):
affiliations = DocumentRecord.get_affiliations(
data['affiliation'])
if affiliations:
data['controlledAffiliation'] = affiliations
else:
data.pop('affiliation', None)
contributors.append(data)
if contributors:
metadata['contribution'] = contributors
document = DocumentRecord.create(metadata,
dbcommit=True,
with_bucket=True)
current_order = 2
for file in self.files:
with file.file.storage().open() as pdf_file:
content = pdf_file.read()
if file.get('category', 'main') == 'main':
order = 1
else:
order = current_order
current_order += 1
kwargs = {
'label': file.get('label', file['key']),
'order': order
}
if file.get('embargo', False) and file.get('embargoDate'):
kwargs['embargo_date'] = file['embargoDate']
if file.get('exceptInOrganisation'):
kwargs['restricted'] = 'organisation'
document.add_file(content, file['key'], **kwargs)
document.commit()
document.reindex()
self['document'] = {
'$ref': DocumentRecord.get_ref_link('documents', document['pid'])
}
return document