def setUp(self):
self.passive = Passive.objects.create(name=u'leonor')
i = Identifier(
identifier=
'http://preproduccion-datos.infolobby.cl:80/resource/URI/Pasivo/0100000035FBA8A3489DC55B38F2412000ECD823B7B037613D60FA221702F4025EF216475E4450578C83800A796A265767CF60B10C5D1C0A3D55C867E588683B758B4B6C684FD3391E2B0601'
)
self.passive.identifiers.add(i)
self.organization = Organization.objects.create(name=u'organization')
i2 = Identifier(
identifier=
'http://preproduccion-datos.infolobby.cl:80/resource/URI/Institucion/AF001'
)
self.organization.identifiers.add(i2)
def setUp(self):
self.organization = Organization.objects.create(name=u"The org")
i = Identifier(
identifier=
"http://preproduccion-datos.infolobby.cl:80/resource/URI/Institucion/AF001"
)
self.organization.identifiers.add(i)
def parse_line(self, line):
active = Active()
active.name = unicode(line[3] + " " + line[4])
active.save()
seed = line[3] + line[4] + line[5] + line[7]
i = Identifier(identifier=line[0])
active.identifiers.add(i)
def test_use_two_identifiers(self):
active = Active.objects.create(name=u"Perico los palotes")
identifier = Identifier(identifier="perico")
identifier2 = Identifier(identifier="condorito")
active.identifiers.add(identifier)
active.identifiers.add(identifier2)
active_search_one = Active.objects.get(
identifiers__identifier="perico")
active_search_two = Active.objects.get(
identifiers__identifier="condorito")
self.assertTrue(active_search_one)
self.assertTrue(active_search_two)
self.assertEquals(active_search_one.name, u"Perico los palotes")
self.assertEquals(active_search_two.name, u"Perico los palotes")
def test_use_identifiers(self):
active = Active.objects.create(name=u"Perico los palotes")
identifier = Identifier(identifier="perico")
active.identifiers.add(identifier)
active2 = Active.objects.get(identifiers__identifier='perico')
self.assertTrue(active2)
self.assertEquals(active2.name, u"Perico los palotes")
def get_things_from_lines_and_klasses(self, klass, lines, pre_):
things = []
problems = []
for line in lines:
original_name = name = line[3].decode(
'utf-8').strip() + u" " + line[4].decode('utf-8').strip()
ps = self.get_count(klass, name)
if ps.count() > 1:
problems.append({'name': name, 'count': ps.count()})
if not ps:
name2 = line[3].decode(
'utf-8').strip() + u" " + line[4].decode('utf-8').strip()
ps = self.get_count(klass, name2)
if not ps:
apellidos = line[4].decode('utf-8').strip().split(" ")
if len(apellidos) == 2:
apellidos_ = apellidos[0] + " " + apellidos[1]
name3 = line[3].decode(
'utf-8').strip() + u" " + apellidos_
ps = self.get_count(klass, name3)
if not ps:
nombres = line[3].decode('utf-8').strip().split(
" ")
name4 = nombres[0] + u" " + apellidos_
ps = self.get_count(klass, name4)
if not ps:
instance = klass.objects.create(
name=original_name)
i = Identifier(identifier=pre_ + line[0])
instance.identifiers.add(i)
continue
if ps.count() == 1:
i = Identifier(identifier=pre_ + line[0])
q = ps[0].identifiers.filter(identifier=i.identifier)
if not q:
ps[0].identifiers.add(i)
else:
if q.count() > 1:
print q.count()
q.exclude(id=q[0].id).delete()
things.append(ps[0])
return things, problems
def parse(self, response_json, id):
previous_persons = self.model.objects.filter(
identifiers__identifier=id)
if previous_persons:
return None
person = self.model()
for result in response_json['results']['bindings']:
person = self.extra_processor(result, person)
if result['property']['value'] == "http://xmlns.com/foaf/0.1/name":
person.name = result["hasValue"]["value"]
person.save()
identifier = Identifier(identifier=id)
person.identifiers.add(identifier)
return person
def parse(self, response_json, id):
all_audiencias = Audiencia.objects.filter(identifiers__identifier=id)
if all_audiencias:
return
audiencia = Audiencia()
active = []
for result in response_json['results']['bindings']:
if result['property']['value'].endswith(
'resource/cplt/descripcion'):
audiencia.description = result['hasValue']['value']
if result['property']['value'].endswith(
'resource/cplt/observaciones'):
audiencia.observations = result['hasValue']['value']
if result['property']['value'].endswith("resource/cplt/duracion"):
minutes_scraper = MinutesScraper(requester=self.requester)
audiencia.length = minutes_scraper.get_one(
result['hasValue']['value'])
if result['property']['value'].endswith(
"resource/cplt/registradoPor"):
organization = Organization.objects.get(
identifiers__identifier=result['hasValue']['value'])
audiencia.registering_organization = organization
if result['property']['value'].endswith("resource/cplt/inicia"):
date_scraper = IniciaScraper(requester=self.requester)
audiencia.date = date_scraper.get_one(
result['hasValue']['value'])
if result['property']['value'].endswith('resource/cplt/participa'):
person = result['isValueOf']['value']
try:
audiencia.passive = Passive.objects.get(
identifiers__identifier=person)
except Passive.DoesNotExist:
active.append(
Active.objects.get(identifiers__identifier=person))
audiencia.save()
for a in active:
audiencia.actives.add(a)
identifier = Identifier(identifier=id)
audiencia.identifiers.add(identifier)
def uri_for_api(self):
"""Return the URL the tastypie API uses to refer to this person"""
old_url = None
new_url = None
for i in self.identifiers.all():
# If the old identifier exists, use this so that the IDs
# used in the API don't change.
if i.scheme == 'popit_url':
assert old_url is None
old_url = i.identifier
# For more recently created Person objects, popolo_uri is
# the best single identifier to use in the API:
elif i.scheme == 'popolo_uri':
assert new_url is None
new_url = i.identifier
if old_url:
return old_url
if new_url:
return new_url
msg = "Could find no global identifier for PopoloPerson with ID {0}"
raise PopoloIdentifier.DoesNotExist(msg.format(self.pk))
def parse_entidades(self, *args):
entidades = {}
entidades_csv_reader = open(args[1], 'rb')
lines_for_entidades_loader = csv.reader(entidades_csv_reader,
delimiter=',')
entidades_lines = []
for line in lines_for_entidades_loader:
entidades_lines.append(line)
for line in entidades_lines:
entidad = Entidad()
entidad.rut = line[1].decode('utf-8').strip()
entidad.name = line[3].decode('utf-8').strip()
try:
if line[14] == "True":
entidad.remunerado = True
if line[14] == "False":
entidad.remunerado = False
except:
pass
entidad.giro = line[5].decode('utf-8').strip()
slug = unicodedata.normalize('NFKD', entidad.name).encode(
'ascii', 'ignore').lower().replace(" ", "")
id = "entidad_" + line[0]
if slug in entidades:
if id not in entidades[slug]['ids']:
entidades[slug]['ids'].append(id)
else:
entidades[slug] = {'entidad': entidad, 'ids': [id]}
for slug in entidades:
e = entidades[slug]
e['entidad'].save()
for iden in e['ids']:
i = Identifier(identifier=iden)
e['entidad'].identifiers.add(i)
def test_instanciate(self):
organization = Organization.objects.create(name=u"The organization")
date = timezone.localtime(timezone.now())
audiencia = Audiencia()
audiencia.description = "Description"
audiencia.length = 60
audiencia.date = date
audiencia.place = 13101
audiencia.registering_organization = organization
audiencia.observations = "Esto puede ser extenso"
audiencia.passive = self.passive
audiencia.save()
identifier = Identifier(identifier='perrito')
audiencia.identifiers.add(identifier)
self.assertTrue(audiencia)
audiencia = Audiencia.objects.get(id=audiencia.id)
self.assertEquals(audiencia.length, 60)
self.assertEquals(audiencia.date, date)
self.assertEquals(audiencia.place, 13101)
self.assertEquals(audiencia.registering_organization, organization)
self.assertEquals(audiencia.observations, "Esto puede ser extenso")
self.assertEquals(audiencia.passive, self.passive)
self.assertTrue(audiencia.identifiers.all())
self.assertEquals(audiencia.identifiers.count(), 1)
def parse_one_person(self, line, klass, pre_):
name = line[3].decode('utf-8').strip() + u" " + line[4].decode(
'utf-8').strip()
p = klass.objects.get(name=name)
i = Identifier(identifier=pre_ + line[0].decode('utf-8').strip())
p.identifiers.add(i)