def test_get_ref_link(app):
"""Test ref link."""
assert DocumentRecord.get_ref_link('document', '1') == 'https://sonar.ch' \
'/api/document/1'
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
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 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
