class ReferenceItemSchemaV1(Schema):
authors = ListWithLimit(NestedWithoutEmptyObjects(AuthorSchemaV1,
dump_only=True,
default=[]),
limit=10)
control_number = fields.Raw()
label = fields.Raw()
publication_info = fields.List(
NestedWithoutEmptyObjects(PublicationInfoItemSchemaV1, dump_only=True))
titles = fields.Method('get_titles')
@pre_dump(pass_many=True)
def filter_references(self, data, many):
reference_records = self.get_resolved_references_by_control_number(
data)
if not many:
reference_record_id = self.get_reference_record_id(data)
reference_record = reference_records.get(reference_record_id)
reference = self.get_reference_or_linked_reference_with_label(
data, reference_record)
return reference
references = []
for reference in data:
reference_record_id = self.get_reference_record_id(reference)
reference_record = reference_records.get(reference_record_id)
reference = self.get_reference_or_linked_reference_with_label(
reference, reference_record)
references.append(reference)
return references
def get_reference_record_id(self, data):
return get_recid_from_ref(data.get('record'))
def get_resolved_references_by_control_number(self, data):
data = force_list(data)
resolved_records = get_linked_records_in_field({'references': data},
'references.record')
return {
record['control_number']: record
for record in resolved_records
}
def get_reference_or_linked_reference_with_label(self, data,
reference_record):
if reference_record:
reference_record.update(
{'label': data.get('reference', {}).get('label')})
return reference_record
return data.get('reference')
def get_titles(self, data):
title = data.pop('title', None)
if title:
data['titles'] = force_list(title)
return data.get('titles', missing)
class CitationItemSchemaV1(Schema):
authors = ListWithLimit(NestedWithoutEmptyObjects(AuthorSchemaV1,
dump_only=True),
limit=10)
control_number = fields.Raw()
publication_info = fields.List(
NestedWithoutEmptyObjects(PublicationInfoItemSchemaV1, dump_only=True))
titles = fields.Raw()
@post_dump
def strip_empty(self, data):
return strip_empty_values(data)
class CitationItemSchemaV1(Schema):
authors = ListWithLimit(NestedWithoutEmptyObjects(AuthorSchemaV1,
dump_only=True),
limit=10)
collaborations = fields.List(fields.Nested(CollaborationSchemaV1,
dump_only=True),
attribute="collaborations")
collaborations_with_suffix = fields.List(fields.Nested(
CollaborationWithSuffixSchemaV1, dump_only=True),
attribute="collaborations")
control_number = fields.Raw()
publication_info = fields.List(
NestedWithoutEmptyObjects(PublicationInfoItemSchemaV1, dump_only=True))
titles = fields.Raw()
earliest_date = fields.Raw()
@post_dump
def strip_empty(self, data):
return strip_empty_values(data)
class ReferenceItemSchemaV1(Schema):
authors = ListWithLimit(NestedWithoutEmptyObjects(AuthorSchemaV1,
dump_only=True,
default=[]),
limit=10)
collaborations = fields.List(fields.Nested(CollaborationSchemaV1,
dump_only=True),
attribute="collaborations")
collaborations_with_suffix = fields.List(fields.Nested(
CollaborationWithSuffixSchemaV1, dump_only=True),
attribute="collaborations")
control_number = fields.Raw()
label = fields.Raw()
urls = fields.Raw()
publication_info = fields.List(
NestedWithoutEmptyObjects(PublicationInfoItemSchemaV1, dump_only=True))
titles = fields.Method('get_titles')
misc = fields.Method('get_misc')
arxiv_eprint = fields.Method('get_arxiv_eprints')
dois = fields.Method('get_dois')
@pre_dump(pass_many=True)
def filter_references(self, data, many):
reference_records = self.get_resolved_references_by_control_number(
data)
if not many:
return self.get_resolved_reference(data, reference_records)
references = []
for reference in data:
resolved_reference = self.get_resolved_reference(
reference, reference_records)
references.append(resolved_reference)
return references
@pre_dump
def force_each_collaboration_to_be_object(self, data):
if not data.get('record'):
collaborations = get_value(data, 'reference.collaborations')
if collaborations:
data['reference']['collaborations'] = [{
'value': collaboration
} for collaboration in collaborations]
return data
def get_resolved_reference(self, data, reference_records):
reference_record_id = self.get_reference_record_id(data)
reference_record = reference_records.get(reference_record_id)
reference = self.get_reference_or_linked_reference_with_label(
data, reference_record)
return reference
def get_reference_record_id(self, data):
return get_recid_from_ref(data.get('record'))
def get_resolved_references_by_control_number(self, data):
data = force_list(data)
resolved_records = get_linked_records_in_field({'references': data},
'references.record')
return {
record['control_number']: record
for record in resolved_records
}
def get_reference_or_linked_reference_with_label(self, data,
reference_record):
if reference_record:
reference_record.update(
{'label': data.get('reference', {}).get('label', missing)})
return reference_record
return data.get('reference')
def get_titles(self, data):
title = data.pop('title', None)
if title:
data['titles'] = force_list(title)
return data.get('titles', missing)
def get_dois(self, data):
dois = data.get('dois', None)
control_number = data.get('control_number')
if dois and not control_number:
data['dois'] = force_list(
{'value': get_value(data, 'dois[0]', default=missing)})
elif dois:
data['dois'] = force_list(
{'value': get_value(data, 'dois[0].value', default=missing)})
return data.get('dois', missing)
def get_arxiv_eprints(self, data):
arxiv_eprint = data.pop('arxiv_eprint', None)
arxiv_eprints = data.get('arxiv_eprints')
if arxiv_eprint:
data['arxiv_eprint'] = force_list({'value': arxiv_eprint})
elif arxiv_eprints:
data['arxiv_eprint'] = force_list({
'value':
get_value(data, 'arxiv_eprints[0].value', default=missing)
})
data.pop('arxiv_eprints', None)
return data.get('arxiv_eprint', missing)
def get_misc(self, data):
titles = data.get('titles')
title = data.get('title')
misc = data.get('misc')
if not title and not titles and misc:
return misc[0]
return missing
@post_dump
def strip_empty(self, data):
return strip_empty_values(data)
class RecordMetadataSchemaV1(Schema):
_collections = fields.Raw()
abstracts = fields.Raw()
accelerator_experiments = fields.Nested(AcceleratorExperimentSchemaV1, dump_only=True, many=True)
acquisition_source = fields.Raw()
arxiv_eprints = fields.Raw()
authors = ListWithLimit(fields.Nested(
AuthorSchemaV1, dump_only=True), limit=10)
book_series = fields.Raw()
# citeable = fields.Raw()
citation_count = fields.Raw()
collaborations = fields.List(fields.Nested(CollaborationSchemaV1, dump_only=True), attribute="collaborations")
collaborations_with_suffix = fields.List(fields.Nested(CollaborationWithSuffixSchemaV1, dump_only=True), attribute="collaborations")
conference_info = fields.Nested(
ConferenceInfoItemSchemaV1,
dump_only=True,
attribute='publication_info',
many=True)
control_number = fields.Raw()
# copyright = fields.Raw()
# core = fields.Raw()
corporate_author = fields.Raw()
# curated = fields.Raw()
date = fields.Method('get_formatted_date')
# deleted = fields.Raw()
# deleted_records = fields.Raw()
document_type = fields.Raw()
# documents = fields.Raw()
dois = fields.Nested(DOISchemaV1, dump_only=True, many=True)
# editions = fields.Raw()
# energy_ranges = fields.Raw()
external_system_identifiers = fields.Nested(
ExternalSystemIdentifierSchemaV1, dump_only=True, many=True)
# figures = fields.Raw()
# funding_info = fields.Raw()
imprints = fields.Raw()
inspire_categories = fields.Raw()
isbns = fields.List(fields.Nested(IsbnSchemaV1, dump_only=True))
keywords = fields.Raw()
languages = fields.Raw()
# legacy_creation_date = fields.Raw()
# license = fields.Raw()
# new_record = fields.Raw()
number_of_authors = fields.Method('get_number_of_authors')
number_of_pages = fields.Raw()
number_of_references = fields.Method('get_number_of_references')
persistent_identifiers = fields.Raw()
preprint_date = fields.Raw()
# public_notes = fields.Raw()
publication_info = fields.Nested(
PublicationInfoItemSchemaV1, dump_only=True, many=True)
# publication_type = fields.Raw()
# record_affiliations = fields.Raw()
# refereed = fields.Raw()
# related_records = fields.Raw()
report_numbers = fields.Raw()
# self = fields.Raw()
texkeys = fields.Raw()
thesis_info = fields.Nested(ThesisInfoSchemaV1, dump_only=True)
# title_translations = fields.Raw()
titles = fields.Raw()
# urls = fields.Raw()
# withdrawn = fields.Raw()
def get_formatted_date(self, data):
earliest_date = data.get('earliest_date')
if earliest_date is None:
return missing
return format_date(earliest_date)
def get_number_of_authors(self, data):
authors = data.get('authors')
return self.get_len_or_missing(authors)
def get_number_of_references(self, data):
number_of_references = data.get('number_of_references')
if number_of_references is not None:
return number_of_references
references = data.get('references')
return self.get_len_or_missing(references)
@staticmethod
def get_len_or_missing(maybe_none_list):
if maybe_none_list is None:
return missing
return len(maybe_none_list)
@post_dump
def strip_empty(self, data):
return strip_empty_values(data)