Python Organization.as_dict方法代码示例

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_parent_id_resolution():
    parent = ScrapeOrganization('UN', classification='international')
    child = ScrapeOrganization('UNESCO', classification='unknown', parent_id=parent._id)
    OrganizationImporter('jurisdiction-id').import_data([parent.as_dict(), child.as_dict()])
    assert Organization.objects.count() == 2
    assert Organization.objects.get(name='UN').children.count() == 1
    assert Organization.objects.get(name='UNESCO').parent.name == 'UN'

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_deduplication_prevents_identical():
    org1 = ScrapeOrganization('United Nations', classification='international')
    org2 = ScrapeOrganization('United Nations', classification='international',
                              founding_date='1945')
    OrganizationImporter('jurisdiction-id').import_data([org1.as_dict()])
    assert Organization.objects.count() == 1

    OrganizationImporter('jurisdiction-id').import_data([org2.as_dict()])
    assert Organization.objects.count() == 1

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_pseudo_parent_id_resolution():
    create_jurisdictions()
    parent = ScrapeOrganization('UN', classification='international')
    child = ScrapeOrganization('UNESCO', classification='unknown',
                               parent_id='~{"classification": "international"}')
    OrganizationImporter('jid1').import_data([parent.as_dict(), child.as_dict()])
    assert Organization.objects.count() == 2
    assert Organization.objects.get(name='UN').children.count() == 1
    assert Organization.objects.get(name='UNESCO').parent.name == 'UN'

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_deduplication_parties():
    party = ScrapeOrganization('Wild', classification='party')
    OrganizationImporter('jurisdiction-id').import_data([party.as_dict()])
    assert Organization.objects.count() == 1

    # parties shouldn't get jurisdiction id attached, so don't differ on import
    party = ScrapeOrganization('Wild', classification='party')
    OrganizationImporter('new-jurisdiction-id').import_data([party.as_dict()])
    assert Organization.objects.count() == 1

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
    def categorize_data(self, csv_data):
        return_objs = []
        Contribution = namedtuple('Contribution', self.csv_header_row.replace(' ', '_'))
        for line in csv_data.split('\n'): # explicity defining delimiter because otherwise fails in case of single line
            if not line:
                continue

            # cur_obj will be the person or organization that made the contribution
            cur_obj = None
            contribution = Contribution(*line.split(','))
            
            if contribution.Contributor_Type in self.business_contribution_types:
                cur_obj = Organization(contribution.Contributor_Name)
            elif contribution.Contributor_Type in self.individual_contribution_types:
                cur_obj = Person(contribution.Contributor_Name)
            elif contribution.Contributor_Type == 'Unknown/Anonymous':
                if contribution.Contributor_Name: #ignoring un-named contributors
                    #these look like catch-all business contributions
                    cur_obj = Organization(contribution.Contributor_Name)
            if cur_obj: 
                #we don't set cur_obj in the event that there was an 
                #anonymous/unknown contribution without a Contribution_Name
                #so we need to check that it exists before adding to it
                cur_obj.add_source(url=self.search_url)
                cur_obj.source_identified = True
                if contribution.Contributor_Address:
                    cur_obj.add_contact_detail(type='address', value=contribution.Contributor_Address)
                if contribution.Employer_Name:
                    cur_obj.extras['Employer'] = contribution.Employer_Name
                if contribution.Employer_Occupation:
                    cur_obj.extras['Occupation'] = contribution.Employer_Occupation
                
                #recipiant_obj is the organization that received the contribution
                recipiant_obj = Organization(contribution.Receiving_Committee)  
                recipiant_obj.extras['Office'] = contribution.Office
                recipiant_obj.extras['Filing Period'] = contribution.Filing_Period
                recipiant_obj.extras['Fundtype'] = contribution.Fundtype

                #transaction is the event linking the donor and recipiant
                transaction = Event('Contribution', contribution.Contribution_Date, 'EST', 'Maryland') #EST and Maryland b/c MD
                transaction.extras['Contribution Amount'] = contribution.Contribution_Amount
                transaction.extras['Contribution Type'] = contribution.Contribution_Type
                transaction.add_source(url=self.search_url)
                #transaction.source_identified = True
                transaction.participants.append(cur_obj.as_dict())
                transaction.participants.append(recipiant_obj.as_dict())
                yield (cur_obj, recipiant_obj, transaction)        
            else:
                yield []

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_full_organization():
    org = ScrapeOrganization('United Nations', classification='international')
    org.add_identifier('un')
    org.add_name('UN', start_date='1945')
    org.add_contact_detail(type='phone', value='555-555-1234', note='this is fake')
    org.add_link('http://example.com/link')
    org.add_source('http://example.com/source')

    # import org
    od = org.as_dict()
    OrganizationImporter('jurisdiction-id').import_data([od])

    # get person from db and assert it imported correctly
    o = Organization.objects.get()
    assert 'ocd-organization' in o.id
    assert o.name == org.name

    assert o.identifiers.all()[0].identifier == 'un'
    assert o.identifiers.all()[0].scheme == ''

    assert o.other_names.all()[0].name == 'UN'
    assert o.other_names.all()[0].start_date == '1945'

    assert o.contact_details.all()[0].type == 'phone'
    assert o.contact_details.all()[0].value == '555-555-1234'
    assert o.contact_details.all()[0].note == 'this is fake'

    assert o.links.all()[0].url == 'http://example.com/link'
    assert o.sources.all()[0].url == 'http://example.com/source'

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_deduplication_other_name_exists():
    create_jurisdictions()
    create_org()
    org = ScrapeOrganization('UN', classification='international')
    od = org.as_dict()
    OrganizationImporter('jid1').import_data([od])
    assert Organization.objects.all().count() == 1

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_fix_bill_id():
    j = create_jurisdiction()
    j.legislative_sessions.create(name='1900', identifier='1900')

    org1 = ScrapeOrganization(name='House', classification='lower')
    bill = ScrapeBill('HB 1', '1900', 'Test Bill ID',
                      classification='bill', chamber='lower')

    oi = OrganizationImporter('jid')

    oi.import_data([org1.as_dict()])

    from pupa.settings import IMPORT_TRANSFORMERS
    IMPORT_TRANSFORMERS['bill'] = {
        'identifier': lambda x: re.sub(r'([A-Z]*)\s*0*([-\d]+)', r'\1 \2', x, 1)
    }

    bi = BillImporter('jid', oi, DumbMockImporter())
    bi.import_data([bill.as_dict()])

    ve = ScrapeVoteEvent(legislative_session='1900', motion_text='passage',
                         start_date='1900-04-02', classification='passage:bill',
                         result='fail', bill_chamber='lower', bill='HB1',
                         identifier='4',
                         bill_action='passage',
                         organization=org1._id)

    VoteEventImporter('jid', DumbMockImporter(), oi, bi).import_data([
        ve.as_dict(),
    ])

    IMPORT_TRANSFORMERS['bill'] = {}

    ve = VoteEvent.objects.get()
    ve.bill.identifier == 'HB 1'

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_extras_organization():
    org = ScrapeOrganization('United Nations', classification='international')
    org.extras = {"hello": "world",
                  "foo": {"bar": "baz"}}
    od = org.as_dict()
    OrganizationImporter('jurisdiction-id').import_data([od])
    o = Organization.objects.get()
    assert o.extras['foo']['bar'] == 'baz'

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
    def categorize_data(self, csv_data):
        #Is there a better place to define this?
        return_objs = []
        Contribution = namedtuple('Contribution', self.csv_header_row.replace(' ', '_'))
        for line in csv_data.split('\n'): # explicity defining delimiter because otherwise fails in case of single line
            if not line:
                continue
            cur_obj = None
            try:
                contribution = Contribution(*line.split(','))
            except Exception as e:
                import pdb; pdb.set_trace()
            if contribution.Contributor_Type in self.business_contribution_types:
                cur_obj = Organization(contribution.Contributor_Name)
            elif contribution.Contributor_Type in self.individual_contribution_types:
                cur_obj = Person(contribution.Contributor_Name)
            elif contribution.Contributor_Type == 'Unknown/Anonymous':
                if contribution.Contributor_Name: #ignoring un-named contributors
                    #these look like catch-all business contributions
                    cur_obj = Organization(contribution.Contributor_Name)
            if cur_obj: 
                cur_obj.add_source(url=self.search_url)
                cur_obj.source_identified = True
                if contribution.Contributor_Address:
                    cur_obj.add_contact_detail(type='address', value=contribution.Contributor_Address)
                if contribution.Employer_Name:
                    cur_obj.extras['Employer'] = contribution.Employer_Name
                if contribution.Employer_Occupation:
                    cur_obj.extras['Occupation'] = contribution.Employer_Occupation
                
                recipiant_obj = Organization(contribution.Receiving_Committee)  
                recipiant_obj.extras['Office'] = contribution.Office
                recipiant_obj.extras['Filing Period'] = contribution.Filing_Period
                recipiant_obj.extras['Fundtype'] = contribution.Fundtype

                transaction = Event('Contribution', contribution.Contribution_Date, 'EST', 'Maryland') #EST and Maryland b/c MD
                transaction.extras['Contribution Amount'] = contribution.Contribution_Amount
                transaction.extras['Contribution Type'] = contribution.Contribution_Type
                transaction.add_source(url=self.search_url)
                #transaction.source_identified = True
                transaction.participants.append(cur_obj.as_dict())
                transaction.participants.append(recipiant_obj.as_dict())
                yield (cur_obj, recipiant_obj, transaction)        
            else:
                yield [] 

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_deduplication_similar_but_different():
    o1 = ScrapeOrganization('United Nations', classification='international')
    # different classification
    o2 = ScrapeOrganization('United Nations', classification='global')
    # different name
    o3 = ScrapeOrganization('United Nations of Earth', classification='international')
    # has a parent
    o4 = ScrapeOrganization('United Nations', classification='international', parent_id=o1._id)

    # similar, but no duplicates
    orgs = [o1.as_dict(), o2.as_dict(), o3.as_dict(), o4.as_dict()]
    OrganizationImporter('jurisdiction-id').import_data(orgs)
    assert Organization.objects.count() == 4

    # should get a new one  when jurisdiction_id changes
    o5 = ScrapeOrganization('United Nations', classification='international')
    OrganizationImporter('new-jurisdiction-id').import_data([o5.as_dict()])
    assert Organization.objects.count() == 5

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_deduplication_overlap_name_distinct_juris():
    create_jurisdictions()

    org_jid_1 = Organization.objects.create(name='World Wrestling Federation',
                                            classification='international',
                                            jurisdiction_id='jid1')
    org_jid_1.other_names.create(name='WWF')

    org = ScrapeOrganization(name="WWF", classification="international")
    org.add_name('WWF')

    oi1 = OrganizationImporter('jid1')
    oi1.import_item(org.as_dict())
    assert Organization.objects.count() == 1

    oi2 = OrganizationImporter('jid2')
    oi2.import_item(org.as_dict())
    assert Organization.objects.count() == 2

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_save_related():
    s = Scraper('jurisdiction', '/tmp/')
    p = Person('Michael Jordan')
    p.add_source('http://example.com')
    o = Organization('Chicago Bulls')
    o.add_source('http://example.com')
    p._related.append(o)

    with mock.patch('json.dump') as json_dump:
        s.save_object(p)

    assert json_dump.mock_calls == [mock.call(p.as_dict(), mock.ANY, cls=mock.ANY),
                                    mock.call(o.as_dict(), mock.ANY, cls=mock.ANY)]

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_vote_event_bill_actions_two_stage():
    # this test is very similar to what we're testing in test_vote_event_bill_actions w/
    # ve3 and ve4, that two bills that reference the same action won't conflict w/ the
    # OneToOneField, but in this case we do it in two stages so that the conflict is found
    # even if the votes weren't in the same scrape
    j = create_jurisdiction()
    j.legislative_sessions.create(name='1900', identifier='1900')
    org1 = ScrapeOrganization(name='House', classification='lower')
    bill = ScrapeBill('HB 1', '1900', 'Axe & Tack Tax Act', from_organization=org1._id)

    bill.add_action(description='passage', date='1900-04-02', chamber='lower')

    ve1 = ScrapeVoteEvent(legislative_session='1900', motion_text='passage',
                          start_date='1900-04-02', classification='passage:bill',
                          result='pass', bill_chamber='lower', bill='HB 1',
                          bill_action='passage',
                          organization=org1._id)
    ve2 = ScrapeVoteEvent(legislative_session='1900', motion_text='passage',
                          start_date='1900-04-02', classification='passage:bill',
                          result='pass', bill_chamber='lower', bill='HB 1',
                          bill_action='passage',
                          organization=org1._id)
    # disambiguate them
    ve1.pupa_id = 'one'
    ve2.pupa_id = 'two'

    oi = OrganizationImporter('jid')
    oi.import_data([org1.as_dict()])

    bi = BillImporter('jid', oi, DumbMockImporter())
    bi.import_data([bill.as_dict()])

    # first imports just fine
    VoteEventImporter('jid', DumbMockImporter(), oi, bi).import_data([
        ve1.as_dict(),
    ])
    votes = list(VoteEvent.objects.all())
    assert len(votes) == 1
    assert votes[0].bill_action is not None

    # when second is imported, ensure that action stays pinned to first just as it would
    # have if they were both in same import
    VoteEventImporter('jid', DumbMockImporter(), oi, bi).import_data([
        ve1.as_dict(),
        ve2.as_dict(),
    ])
    votes = list(VoteEvent.objects.all())
    assert len(votes) == 2
    assert votes[0].bill_action is not None
    assert votes[1].bill_action is None

# 需要导入模块: from pupa.scrape import Organization [as 别名]
# 或者: from pupa.scrape.Organization import as_dict [as 别名]
def test_deduplication_error_overlaps():
    create_jurisdictions()

    Organization.objects.create(name='World Wrestling Federation',
                                classification='international',
                                jurisdiction_id='jid1')
    wildlife = Organization.objects.create(name='World Wildlife Fund',
                                           classification='international',
                                           jurisdiction_id='jid1')
    wildlife.other_names.create(name='WWF')

    org = ScrapeOrganization('World Wrestling Federation', classification='international')
    org.add_name('WWF')
    od = org.as_dict()
    with pytest.raises(SameOrgNameError):
        OrganizationImporter('jid1').import_data([od])