def setup_static_instances(self):
'''
These are instances that are used statically in the code. For example, when we
provide attribution of an identifier to Getty, or use a Lugt number, we need to
serialize the related Group or Person record for that attribution, even if it does
not appear in the source data.
'''
lugt_ulan = 500321736
gri_ulan = 500115990
gci_ulan = 500115991
GETTY_GRI_URI = self.helper.make_proj_uri('ORGANIZATION',
'LOCATION-CODE', 'JPGM')
GETTY_GCI_URI = self.helper.make_shared_uri(
'STATIC', 'ORGANIZATION', 'Getty Conservation Institute')
LUGT_URI = self.helper.make_proj_uri('PERSON', 'ULAN', lugt_ulan)
gci = model.Group(ident=GETTY_GCI_URI,
label='Getty Conservation Institute')
gci.identified_by = vocab.PrimaryName(
ident='', content='Getty Conservation Institute')
gci.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{gci_ulan}')
gri = model.Group(ident=GETTY_GRI_URI,
label='Getty Research Institute')
gri.identified_by = vocab.PrimaryName(
ident='', content='Getty Research Institute')
gri.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{gri_ulan}')
lugt = model.Person(ident=LUGT_URI, label='Frits Lugt')
lugt.identified_by = vocab.PrimaryName(ident='', content='Frits Lugt')
lugt.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{lugt_ulan}')
instances = defaultdict(dict)
instances.update({
'Group': {
'gci': gci,
'gri': gri
},
'Person': {
'lugt': lugt
}
})
return instances
def test_breadth(self): x = model.TransferOfCustody() e = model.Activity() fr = model.Group() to = model.Group() w = model.ManMadeObject() fr.label = "From" to.label = "To" x.transferred_custody_of = w x.transferred_custody_from = fr x.transferred_custody_to = to e.used_specific_object = w e.carried_out_by = to w.current_owner = fr x.specific_purpose = e js = model.factory.toJSON(x) # Okay ... if we're breadth first, then custody_from is a resource # And now it's the first in the list self.assertTrue(isinstance(js['transferred_custody_from'][0], OrderedDict))
def model_publisher_group(self, record, data, seq):
record.setdefault('_publishings', [])
series_label = record['label']
corp_id = data.get('gaia_corp_id')
geog_id = data.get('gaia_geog_id')
a_uri = record['uri'] + f'-pub-{seq}'
cb_label = f' by CB{corp_id}' if corp_id else f' by publisher #{seq}'
a = vocab.Publishing(ident=a_uri,
label=f'Publishing of {series_label}' + cb_label)
if corp_id:
uri = self.helper.corporate_body_uri(corp_id)
a.carried_out_by = model.Group(ident=uri)
if geog_id:
uri = self.helper.place_uri(geog_id)
a.took_place_at = model.Place(ident=uri)
record['_publishings'].append(a)
def __call__(self, data: dict, location_codes, unique_catalogs):
'''Add information about the ownership of a physical copy of an auction catalog'''
# Add the URI of this physical catalog to `unique_catalogs`. This data will be used
# later to figure out which catalogs can be uniquely identified by a catalog number
# and owner code (e.g. for owners who do not have multiple copies of a catalog).
cno = data['catalog_number']
owner_code = data['owner_code']
copy_number = data.get('copy_number', '')
owner_name = None
entry_record = get_crom_object(data.get('_catalog'))
with suppress(KeyError):
owner_name = location_codes[owner_code]
owner_uri = self.helper.make_proj_uri('ORGANIZATION',
'LOCATION-CODE', owner_code)
data['_owner'] = {
'label':
owner_name,
'uri':
owner_uri,
'referred_to_by': [entry_record],
'identifiers': [
model.Name(ident='', content=owner_name),
model.Identifier(ident='', content=str(owner_code))
],
}
owner = model.Group(ident=owner_uri)
owner.referred_to_by = entry_record
add_crom_data(data['_owner'], owner)
if not owner_code:
warnings.warn(f'Setting empty identifier on {owner.id}')
add_crom_data(data=data['_owner'], what=owner)
catalog = get_crom_object(data)
catalog.current_owner = owner
owner_uri = self.helper.physical_catalog_uri(
cno, owner_code, None
) # None here because we want a key that will stand in for all the copies belonging to a single owner
copy_uri = self.helper.physical_catalog_uri(cno, owner_code,
copy_number)
unique_catalogs[owner_uri].add(copy_uri)
return data
def setup_static_instances(self):
'''
These are instances that are used statically in the code. For example, when we
provide attribution of an identifier to Getty, or use a Lugt number, we need to
serialize the related Group or Person record for that attribution, even if it does
not appear in the source data.
'''
lugt_ulan = 500321736
gri_ulan = 500115990
gci_ulan = 500115991
knoedler_ulan = 500304270
GETTY_GRI_URI = self.helper.make_proj_uri('ORGANIZATION',
'LOCATION-CODE', 'JPGM')
GETTY_GCI_URI = self.helper.make_shared_uri(
'STATIC', 'ORGANIZATION', 'Getty Conservation Institute')
LUGT_URI = self.helper.make_proj_uri('PERSON', 'ULAN', lugt_ulan)
KNOEDLER_URI = self.helper.make_shared_uri('ORGANIZATION', 'ULAN',
str(knoedler_ulan))
gci = model.Group(ident=GETTY_GCI_URI,
label='Getty Conservation Institute')
gci.identified_by = vocab.PrimaryName(
ident='', content='Getty Conservation Institute')
gci.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{gci_ulan}')
gri = model.Group(ident=GETTY_GRI_URI,
label='Getty Research Institute')
gri.identified_by = vocab.PrimaryName(
ident='', content='Getty Research Institute')
gri.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{gri_ulan}')
lugt = model.Person(ident=LUGT_URI, label='Frits Lugt')
lugt.identified_by = vocab.PrimaryName(ident='', content='Frits Lugt')
lugt.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{lugt_ulan}')
knoedler_name = 'M. Knoedler & Co.'
knoedler = model.Group(ident=KNOEDLER_URI, label=knoedler_name)
knoedler.identified_by = vocab.PrimaryName(ident='',
content=knoedler_name)
knoedler.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{knoedler_ulan}')
materials = {
aat: model.Material(ident=f'http://vocab.getty.edu/aat/{aat}',
label=label)
for aat, label in self.services['materials'].items()
}
instances = defaultdict(dict)
instances.update({
'Group': {
'gci': gci,
'gri': gri,
'knoedler': knoedler
},
'Person': {
'lugt': lugt
},
'Material': materials,
'Place': self._static_place_instances()
})
return instances
def model_imprint_group(self, record, data):
if not data:
return
record.setdefault('referred_to_by', [])
record.setdefault('used_for', [])
record.setdefault('part_of', [])
record.setdefault('_activities', [])
record.setdefault('_groups', [])
record.setdefault('_places', [])
record.setdefault('identifiers', [])
edition = data.get('edition')
series_number = data.get('series_number')
doi = data.get('doi')
coden = data.get('coden')
website = data.get('website_address')
publishers = _as_list(data.get('publisher'))
distributors = _as_list(data.get('distributor'))
journal = data.get('journal_info')
# imprint_group/journal_info/aata_journal_id
# imprint_group/journal_info/aata_issue_id
degree = data.get('thesis_degree')
tr = data.get('technical_report_number')
if edition:
record['referred_to_by'].append(
vocab.EditionStatement(ident='', content=edition))
if series_number:
record['referred_to_by'].append(
vocab.Note(ident='',
content=series_number)) # TODO: classify this Note
if doi:
record['identifiers'].append(
vocab.DoiIdentifier(ident='', content=doi))
if coden:
record['identifiers'].append(
vocab.CodenIdentifier(ident='', content=coden))
if website:
record['referred_to_by'].append(
vocab.Note(ident='', content=website))
article_label = record['label']
for i, publisher in enumerate(publishers):
corp_id = publisher.get('gaia_corp_id')
geog_id = publisher.get('publisher_location',
{}).get('gaia_geog_id')
a_uri = record['uri'] + f'-pub-{i}'
a = vocab.Publishing(ident=a_uri,
label=f'Publishing of {article_label}')
if corp_id:
uri = self.helper.corporate_body_uri(corp_id)
g = model.Group(ident=uri)
a.carried_out_by = g
record['_groups'].append(add_crom_data({}, g))
if geog_id:
uri = self.helper.place_uri(geog_id)
p = model.Place(ident=uri)
a.took_place_at = p
record['_places'].append(add_crom_data({}, p))
record['used_for'].append(a)
# record['_activities'].append(add_crom_data({}, a))
for i, distributor in enumerate(distributors):
corp_id = distributor.get('gaia_corp_id')
geog_id = distributor.get('distributor_location',
{}).get('gaia_geog_id')
a_uri = record['uri'] + f'-dist-{i}'
a = vocab.Distributing(ident=a_uri,
label=f'Distribution of {article_label}')
if corp_id:
uri = self.helper.corporate_body_uri(corp_id)
g = model.Group(ident=uri)
a.carried_out_by = g
record['_groups'].append(add_crom_data({}, g))
if geog_id:
uri = self.helper.place_uri(geog_id)
p = model.Place(ident=uri)
a.took_place_at = p
record['_places'].append(add_crom_data({}, p))
record['used_for'].append(a)
# record['_activities'].append(add_crom_data({}, a))
if journal:
journal_id = journal.get('aata_journal_id')
issue_id = journal.get('aata_issue_id')
issue_uri = self.helper.issue_uri(journal_id, issue_id)
issue = vocab.IssueText(ident=issue_uri)
record['part_of'].append(add_crom_data({'uri': issue_uri}, issue))
if degree:
record['referred_to_by'].append(
vocab.Note(ident='', content=degree))
if tr:
record['identifiers'].append(model.Identifier(
ident='', content=tr)) # TODO: classify this Identifier
def setup_static_instances(self):
'''
These are instances that are used statically in the code. For example, when we
provide attribution of an identifier to Getty, or use a Lugt number, we need to
serialize the related Group or Person record for that attribution, even if it does
not appear in the source data.
'''
lugt_ulan = 500321736
gri_ulan = 500115990
gci_ulan = 500115991
knoedler_ulan = 500304270
GETTY_PSCP_URI = self.helper.make_shared_uri(
'STATIC', 'ORGANIZATION',
'Project for the Study of Collecting and Provenance')
GETTY_GPI_URI = self.helper.make_shared_uri('STATIC', 'ORGANIZATION',
'Getty Provenance Index')
GETTY_GRI_URI = self.helper.make_proj_uri('ORGANIZATION',
'LOCATION-CODE', 'JPGM')
GETTY_GCI_URI = self.helper.make_shared_uri(
'STATIC', 'ORGANIZATION', 'Getty Conservation Institute')
LUGT_URI = self.helper.make_proj_uri('PERSON', 'ULAN', lugt_ulan)
KNOEDLER_URI = self.helper.make_shared_uri('ORGANIZATION', 'ULAN',
str(knoedler_ulan))
NEWYORK_URI = self.helper.make_shared_uri('PLACE', 'USA', 'NY',
'New York')
gci = model.Group(ident=GETTY_GCI_URI,
label='Getty Conservation Institute')
gci.identified_by = vocab.PrimaryName(
ident='', content='Getty Conservation Institute')
gci.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{gci_ulan}')
gri = model.Group(ident=GETTY_GRI_URI,
label='Getty Research Institute')
gri.identified_by = vocab.PrimaryName(
ident='', content='Getty Research Institute')
gri.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{gri_ulan}')
gpi = model.Group(ident=GETTY_GPI_URI, label='Getty Provenance Index')
gpi.identified_by = vocab.PrimaryName(ident='',
content='Getty Provenance Index')
pscp = model.Group(
ident=GETTY_PSCP_URI,
label='Project for the Study of Collecting and Provenance')
pscp.identified_by = vocab.PrimaryName(
ident='',
content='Project for the Study of Collecting and Provenance')
lugt = model.Person(ident=LUGT_URI, label='Frits Lugt')
lugt.identified_by = vocab.PrimaryName(ident='', content='Frits Lugt')
lugt.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{lugt_ulan}')
knoedler_name = 'M. Knoedler & Co.'
knoedler = model.Group(ident=KNOEDLER_URI, label=knoedler_name)
knoedler.identified_by = vocab.PrimaryName(ident='',
content=knoedler_name)
knoedler.exact_match = model.BaseResource(
ident=f'http://vocab.getty.edu/ulan/{knoedler_ulan}')
newyork_name = 'New York, NY'
newyork = model.Place(ident=NEWYORK_URI, label=newyork_name)
newyork.identified_by = vocab.PrimaryName(ident='',
content=newyork_name)
materials = {}
if 'materials' in self.services:
materials.update({
aat: model.Material(ident=f'http://vocab.getty.edu/aat/{aat}',
label=label)
for aat, label in self.services['materials'].items()
})
places = self._static_place_instances()
places.update({'newyork': newyork})
db_people = self.static_db_instance(
'PEOPLE', name='STAR Person Authority Database', creator=gpi)
db_knoedler = self.static_db_instance('Knoedler',
name='STAR Knoedler Database',
creator=gpi)
db_sales_events = self.static_db_instance(
'Sales',
'Descriptions',
name='STAR Sales Catalogue Database',
creator=gpi)
db_sales_catalogs = self.static_db_instance(
'Sales',
'Catalogue',
name='STAR Physical Sales Catalogue Database',
creator=gpi)
db_sales_contents = self.static_db_instance(
'Sales',
'Contents',
name='STAR Sales Contents Database',
creator=gpi)
instances = defaultdict(dict)
instances.update({
'LinguisticObject': {
'db-people': db_people,
'db-knoedler': db_knoedler,
'db-sales_events': db_sales_events,
'db-sales_catalogs': db_sales_catalogs,
'db-sales_contents': db_sales_contents,
},
'Group': {
'gci': gci,
'pscp': pscp,
'gri': gri,
'gpi': gpi,
'knoedler': knoedler
},
'Person': {
'lugt': lugt
},
'Material': materials,
'Place': places
})
return instances