def update_instance(self):
# override default update to handle extra fields (collection & dates)
# NOTE: collection membership can only be set when a CollectionObject
# was passed in as form instance
super(CollectionForm, self).update_instance()
# cleaned data only available when the form is valid,
# but xmlobjectform is_valid calls update_instance
if hasattr(self, 'cleaned_data'):
# set date created - could be a single date or a date range
# remove existing dates and re-add
self.instance.create_origin_info()
for i in range(len(self.instance.origin_info.created)):
self.instance.origin_info.created.pop()
self.instance.origin_info.created.append(mods.DateCreated(
date=self.cleaned_data['date_created'],
key_date=True,
))
# if there is a date end, store it and set end & start attributes
if 'date_end' in self.cleaned_data and self.cleaned_data['date_end']:
self.instance.create_origin_info()
self.instance.origin_info.created.append(mods.DateCreated(
date=self.cleaned_data['date_end'],
point='end',
))
self.instance.origin_info.created[0].point = 'start'
# set relation to archive object when an instance was passed in
if hasattr(self, 'object_instance'):
self.object_instance.collection = self.object_instance.get_object(self.cleaned_data['collection'])
# must return mods portion because XmlObjectForm depends on it for validation
return self.instance
def englishdocs_collection():
repo = Repository()
obj = repo.get_object(type=CollectionObject)
obj.label = 'English documents collection'
obj.mods.content.title = 'English documents collection'
obj.mods.content.source_id = '309'
obj.collection = repo.get_object(FedoraFixtures.archives()[1].uri)
obj.mods.content.create_origin_info()
obj.mods.content.origin_info.created.append(
mods.DateCreated(date=1509, point='start'))
obj.mods.content.origin_info.created.append(
mods.DateCreated(date=1805, point='end'))
return obj
def esterbrook_collection():
repo = Repository()
obj = repo.get_object(type=CollectionObject)
obj.label = 'Thomas Esterbrook letter books'
obj.mods.content.title = 'Thomas Esterbrook letter books'
obj.mods.content.source_id = '123'
obj.collection = repo.get_object(FedoraFixtures.archives()[2].uri)
obj.mods.content.create_origin_info()
obj.mods.content.origin_info.created.append(
mods.DateCreated(date=1855, point='start'))
obj.mods.content.origin_info.created.append(
mods.DateCreated(date=1861, point='end'))
obj.mods.content.create_name()
obj.mods.content.name.name_parts.append(
mods.NamePart(text='Thomas Esterbrook'))
return obj
def rushdie_collection():
repo = Repository()
obj = repo.get_object(type=CollectionObject)
obj.label = 'Salman Rushdie Collection'
obj.mods.content.title = 'Salman Rushdie Collection'
obj.mods.content.source_id = '1000'
obj.collection = repo.get_object(FedoraFixtures.archives()[1].uri)
obj.mods.content.create_origin_info()
obj.mods.content.origin_info.created.append(
mods.DateCreated(date=1947, point='start'))
obj.mods.content.origin_info.created.append(
mods.DateCreated(date=2008, point='end'))
obj.mods.content.create_name()
obj.mods.content.name.name_parts.append(
mods.NamePart(text='Salman Rushdie'))
return obj
def test_create_mods(self):
# test creating MODS from scratch - ensure sub-xmlobject definitions are correct
# and produce schema-valid MODS
mymods = mods.MODS()
mymods.create_title_info()
# titleInfo subfields
mymods.title_info.non_sort = 'A '
mymods.title_info.title = 'Record'
mymods.title_info.subtitle = ': for testing'
mymods.title_info.part_number = '1'
mymods.title_info.part_name = 'first installment'
mymods.title_info_list.append(mods.TitleInfo(non_sort='An ', title='Alternative Title', subtitle=': for testing',
part_number = '1', part_name='first installment', label='First line'))
mymods.resource_type = 'text'
mymods.create_name()
mymods.name.type = 'personal'
mymods.name.authority = 'local'
mymods.name.name_parts.extend([mods.NamePart(type='family', text='Schmoe'),
mods.NamePart(type='given', text='Joe')])
mymods.name.roles.append(mods.Role(type='text', authority='local',
text='Test Subject'))
mymods.create_abstract()
mymods.abstract.text = 'A testing record with made up content.'
mymods.create_note()
mymods.note.type = 'general'
mymods.note.text = 'general note'
mymods.create_origin_info()
mymods.origin_info.created.append(mods.DateCreated(date='2001-10-02'))
mymods.origin_info.issued.append(mods.DateIssued(date='2001-12-01'))
mymods.create_record_info()
mymods.record_info.record_id = 'id:1'
mymods.identifiers.extend([mods.Identifier(type='uri', text='http://ur.l'),
mods.Identifier(type='local', text='332')])
mymods.access_conditions.extend([mods.AccessCondition(type='restriction', text='unavailable'),
mods.AccessCondition(type='use', text='Tuesdays only')])
mymods.related_items.extend([mods.RelatedItem(type='host', title='EU Archives'),
mods.RelatedItem(type='isReferencedBy', title='Finding Aid')])
mymods.subjects.extend([mods.Subject(authority='keyword', topic='automated testing'),
mods.Subject(authority='keyword', topic='test records')])
mymods.parts.append(mods.Part())
mymods.parts[0].details.extend([mods.PartDetail(type='volume', number='90'),
mods.PartDetail(type='issue', number='2')])
mymods.parts[0].create_extent()
mymods.parts[0].extent.unit = 'pages'
mymods.parts[0].extent.start = '339'
mymods.parts[0].extent.end = '361'
xml = mymods.serialize(pretty=True)
self.assert_(b'<mods:mods ' in xml)
self.assert_(b'xmlns:mods="http://www.loc.gov/mods/v3"' in xml)
self.assertTrue(mymods.is_valid(), "MODS created from scratch should be schema-valid")
def test_is_empty_date_values(self):
self.origin_info.created.append(mods.DateCreated(date='300'))
self.assertFalse(self.origin_info.is_empty())
self.origin_info.issued.append(mods.DateIssued(date='450'))
self.assertFalse(self.origin_info.is_empty())
def test_is_empty_with_empty_dates(self):
self.origin_info.created.append(mods.DateCreated())
self.assertTrue(self.origin_info.is_empty())
self.origin_info.issued.append(mods.DateIssued())
self.assertTrue(self.origin_info.is_empty())
def setUp(self):
super(TestModsDate, self).setUp()
self.date = mods.DateCreated()
def generate_collection(self):
'''Generate a :class:`CollectionObject` with fields pre-populated
based on the contents of the current Finding Aid object.
'''
repo = Repository()
coll = repo.get_object(type=CollectionObject)
# TODO: archive membership?
# title - using 'short' form without unitdate, stripping any trailing whitespace & . or ,
# TODO/FIXME: does NOT work for unittitles with nested tags, e.g. title - see pomerantz
coll.mods.content.title = unicode(self.unittitle.short).rstrip().rstrip('.,')
# main entry/name - origination, if any
if self.archdesc.did.origination:
name_text = unicode(self.archdesc.did.origination)
# determine type of name
colltype = self.archdesc.did.node.xpath('''local-name(e:origination/e:persname |
e:origination/e:corpname | e:origination/e:famname)''',
namespaces=self.ROOT_NAMESPACES)
if colltype == 'persname':
name_type = 'personal'
elif colltype == 'famname':
name_type = 'family'
# family names consistently end with a period, which can be removed
name_text = name_text.rstrip('.')
elif colltype == 'corpname':
name_type = 'corporate'
if name_type is not None:
coll.mods.content.create_name()
coll.mods.content.name.type = name_type
authority = self.archdesc.did.node.xpath('string(e:origination/*/@source)',
namespaces=self.ROOT_NAMESPACES)
# lcnaf in the EAD is equivalent to naf in MODS
if authority == 'lcnaf':
coll.mods.content.name.authority = 'naf'
coll.mods.content.name.name_parts.append(mods.NamePart(text=name_text))
# date coverage
if self.coverage:
date_encoding = {'encoding': 'w3cdtf'}
# date range
coll.mods.content.create_origin_info()
if '/' in self.coverage:
start, end = self.coverage.split('/')
coll.mods.content.origin_info.created.append(mods.DateCreated(date=start,
point='start', key_date=True, **date_encoding))
coll.mods.content.origin_info.created.append(mods.DateCreated(date=end,
point='end', **date_encoding))
# single date
else:
coll.mods.content.origin_info.created.append(mods.DateCreated(date=self.coverage,
key_date=True, **date_encoding))
# source id - numeric form of the manuscript/archive collection number
coll.mods.content.source_id = self.archdesc.did.unitid.identifier
# access restriction
if self.archdesc.access_restriction:
coll.mods.content.create_restrictions_on_access()
coll.mods.content.restrictions_on_access.text = "\n".join([
unicode(c) for c in self.archdesc.access_restriction.content])
# use & reproduction
if self.archdesc.use_restriction:
coll.mods.content.create_use_and_reproduction()
coll.mods.content.use_and_reproduction.text = "\n".join([
unicode(c) for c in self.archdesc.use_restriction.content])
# set initial mods:typeOfResource - not specified in EAD, but all
# collections shoud be mixed material
coll.mods.content.resource_type = 'mixed material'
# EAD url - where does this go?
# accessible at self.eadid.url
return coll
