+
+
+class TestPlaceNames:
+
+ @pytest.fixture(autouse=True)
+ def setup(self, analyzer):
+ self.analyzer = analyzer
+
+
+ def expect_name_terms(self, info, *expected_terms):
+ tokens = self.analyzer.get_word_token_info(list(expected_terms))
+ for token in tokens:
+ assert token[2] is not None, "No token for {0}".format(token)
+
+ assert eval(info['names']) == set((t[2] for t in tokens)),\
+ f"Expected: {tokens}\nGot: {info['names']}"
+
+
+ def process_named_place(self, names):
+ return self.analyzer.process_place(PlaceInfo({'name': names}))
+
+
+ def test_simple_names(self):
+ info = self.process_named_place({'name': 'Soft bAr', 'ref': '34'})
+
+ self.expect_name_terms(info, '#Soft bAr', '#34', 'Soft', 'bAr', '34')
+
+
+ @pytest.mark.parametrize('sep', [',' , ';'])
+ def test_names_with_separator(self, sep):
+ info = self.process_named_place({'name': sep.join(('New York', 'Big Apple'))})
+
+ self.expect_name_terms(info, '#New York', '#Big Apple',
+ 'new', 'york', 'big', 'apple')
+
+
+ def test_full_names_with_bracket(self):
+ info = self.process_named_place({'name': 'Houseboat (left)'})
+
+ self.expect_name_terms(info, '#Houseboat (left)', '#Houseboat',
+ 'houseboat', '(left)')
+
+
+ def test_country_name(self, word_table):
+ place = PlaceInfo({'name' : {'name': 'Norge'},
+ 'country_code': 'no',
+ 'rank_address': 4,
+ 'class': 'boundary',
+ 'type': 'administrative'})
+
+ info = self.analyzer.process_place(place)
+
+ self.expect_name_terms(info, '#norge', 'norge')
+ assert word_table.get_country() == {('no', ' norge')}
+
+
+class TestPlaceAddress:
+
+ @pytest.fixture(autouse=True)
+ def setup(self, analyzer):
+ self.analyzer = analyzer
+
+
+ @pytest.fixture
+ def getorcreate_hnr_id(self, temp_db_cursor):
+ temp_db_cursor.execute("""CREATE SEQUENCE seq_hnr start 1;
+ CREATE OR REPLACE FUNCTION getorcreate_housenumber_id(lookup_word TEXT)
+ RETURNS INTEGER AS $$
+ SELECT -nextval('seq_hnr')::INTEGER; $$ LANGUAGE SQL""")
+
+ def process_address(self, **kwargs):
+ return self.analyzer.process_place(PlaceInfo({'address': kwargs}))
+
+
+ def name_token_set(self, *expected_terms):
+ tokens = self.analyzer.get_word_token_info(list(expected_terms))
+ for token in tokens:
+ assert token[2] is not None, "No token for {0}".format(token)
+
+ return set((t[2] for t in tokens))
+
+
+ @pytest.mark.parametrize('pcode', ['12345', 'AB 123', '34-345'])
+ def test_process_place_postcode(self, word_table, pcode):
+ self.process_address(postcode=pcode)
+
+ assert word_table.get_postcodes() == {pcode, }
+
+
+ @pytest.mark.parametrize('pcode', ['12:23', 'ab;cd;f', '123;836'])
+ def test_process_place_bad_postcode(self, word_table, pcode):
+ self.process_address(postcode=pcode)
+
+ assert not word_table.get_postcodes()
+
+
+ @pytest.mark.parametrize('hnr', ['123a', '0', '101'])
+ def test_process_place_housenumbers_simple(self, hnr, getorcreate_hnr_id):
+ info = self.process_address(housenumber=hnr)
+
+ assert info['hnr'] == hnr.lower()
+ assert info['hnr_tokens'] == "{-1}"
+
+
+ def test_process_place_housenumbers_lists(self, getorcreate_hnr_id):
+ info = self.process_address(conscriptionnumber='1; 2;3')
+
+ assert set(info['hnr'].split(';')) == set(('1', '2', '3'))
+ assert info['hnr_tokens'] == "{-1,-2,-3}"
+
+
+ def test_process_place_housenumbers_duplicates(self, getorcreate_hnr_id):
+ info = self.process_address(housenumber='134',
+ conscriptionnumber='134',
+ streetnumber='99A')
+
+ assert set(info['hnr'].split(';')) == set(('134', '99a'))
+ assert info['hnr_tokens'] == "{-1,-2}"
+
+
+ def test_process_place_street(self):
+ # legacy tokenizer only indexes known names
+ self.analyzer.process_place(PlaceInfo({'name': {'name' : 'Grand Road'}}))
+ info = self.process_address(street='Grand Road')
+
+ assert eval(info['street']) == self.name_token_set('#Grand Road')
+
+
+ def test_process_place_street_empty(self):
+ info = self.process_address(street='🜵')
+
+ assert 'street' not in info
+
+
+ def test_process_place_place(self):
+ self.analyzer.process_place(PlaceInfo({'name': {'name' : 'Honu Lulu'}}))
+ info = self.process_address(place='Honu Lulu')
+
+ assert eval(info['place_search']) == self.name_token_set('#Honu Lulu',
+ 'Honu', 'Lulu')
+ assert eval(info['place_match']) == self.name_token_set('#Honu Lulu')
+
+
+ def test_process_place_place_empty(self):
+ info = self.process_address(place='🜵')
+
+ assert 'place' not in info
+
+
+ def test_process_place_address_terms(self):
+ for name in ('Zwickau', 'Haupstraße', 'Sachsen'):
+ self.analyzer.process_place(PlaceInfo({'name': {'name' : name}}))
+ info = self.process_address(country='de', city='Zwickau', state='Sachsen',
+ suburb='Zwickau', street='Hauptstr',
+ full='right behind the church')
+
+ city = self.name_token_set('ZWICKAU')
+ state = self.name_token_set('SACHSEN')
+
+ print(info)
+ result = {k: eval(v[0]) for k,v in info['addr'].items()}
+
+ assert result == {'city': city, 'suburb': city, 'state': state}
+
+
+ def test_process_place_address_terms_empty(self):
+ info = self.process_address(country='de', city=' ', street='Hauptstr',
+ full='right behind the church')
+
+ assert 'addr' not in info
+
projects / nominatim.git / blobdiff