def run_sanitizer_on(**kwargs):
place = PlaceInfo({'name': kwargs})
name, _ = PlaceSanitizer([{
'step': 'split-name-list'
}]).process_names(place)
return sorted([(p.name, p.kind, p.suffix) for p in name])
def index_places(self, worker, places):
values = []
for place in places:
values.extend((place[x] for x in ('place_id', 'address')))
values.append(PlaceInfo(place).analyze(self.analyzer))
worker.perform(self._index_sql(len(places)), values)
def test_no_name_list():
place = PlaceInfo({'address': {'housenumber': '3'}})
name, address = PlaceSanitizer([{
'step': 'split-name-list'
}]).process_names(place)
assert not name
assert len(address) == 1
def index_places(self, worker, places):
values = []
for place in places:
for field in ('place_id', 'name', 'address', 'linked_place_id'):
values.append(place[field])
values.append(PlaceInfo(place).analyze(self.analyzer))
worker.perform(self._index_sql(len(places)), values)
def test_no_names():
place = PlaceInfo({'address': {'housenumber': '3'}})
name, address = PlaceSanitizer([{
'step': 'strip-brace-terms'
}]).process_names(place)
assert not name
assert len(address) == 1
def test_process_place_housenumbers_simple(analyzer, hnr):
info = analyzer.process_place(
PlaceInfo({'address': {
'housenumber': hnr
}}))
assert info['hnr'] == hnr
assert info['hnr_tokens'].startswith("{")
def test_process_place_names(analyzer, make_keywords):
info = analyzer.process_place(
PlaceInfo({'name': {
'name': 'Soft bAr',
'ref': '34'
}}))
assert info['names'] == '{1,2,3}'
def sanitize_with_delimiter(delimiter, name):
place = PlaceInfo({'name': {'name': name}})
san = PlaceSanitizer([{
'step': 'split-name-list',
'delimiters': delimiter
}])
name, _ = san.process_names(place)
return sorted([p.name for p in name])
def test_sanitizer_empty_list(rules):
san = sanitizer.PlaceSanitizer(rules)
name, address = san.process_names(
PlaceInfo({'name': {
'name:de:de': '1;2;3'
}}))
assert len(name) == 1
assert all(isinstance(n, sanitizer.PlaceName) for n in name)
def test_process_place_street_from_cache(self):
self.analyzer.process_place(PlaceInfo({'name': {
'name': 'Grand Road'
}}))
self.process_address(street='Grand Road')
# request address again
info = self.process_address(street='Grand Road')
assert eval(info['street']) == self.name_token_set('#Grand Road')
def test_process_place_housenumbers_duplicates(analyzer):
info = analyzer.process_place(
PlaceInfo({
'address': {
'housenumber': '134',
'conscriptionnumber': '134',
'streetnumber': '99a'
}
}))
assert set(info['hnr'].split(';')) == set(('134', '99a'))
def run_sanitizer_on(country, **kwargs):
place = PlaceInfo({
'name': {k.replace('_', ':'): v
for k, v in kwargs.items()},
'country_code': country
})
name, _ = PlaceSanitizer([{
'step': 'tag-analyzer-by-language'
}]).process_names(place)
return sorted([(p.name, p.kind, p.suffix, p.attr) for p in name])
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')}
def test_missing_country(self):
place = PlaceInfo({'name': {'name': 'something'}})
name, _ = PlaceSanitizer([{
'step': 'tag-analyzer-by-language',
'use-defaults': 'all',
'mode': 'replace'
}]).process_names(place)
assert len(name) == 1
assert name[0].name == 'something'
assert name[0].suffix is None
assert 'analyzer' not in name[0].attr
def test_process_place_multiple_street_tags(self):
self.analyzer.process_place(
PlaceInfo({'name': {
'name': 'Grand Road',
'ref': '05989'
}}))
info = self.process_address(**{
'street': 'Grand Road',
'street:sym_ul': '05989'
})
assert eval(info['street']) == self.name_token_set(
'#Grand Road', '#05989')
def add_country_names(self, country_code, names):
""" Add names for the given country to the search index.
"""
# Make sure any name preprocessing for country names applies.
info = PlaceInfo({
'name': names,
'country_code': country_code,
'rank_address': 4,
'class': 'boundary',
'type': 'administrative'
})
self._add_country_full_names(country_code,
self.sanitizer.process_names(info)[0])
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 run_sanitizer_on(whitelist, **kwargs):
place = PlaceInfo(
{'name': {k.replace('_', ':'): v
for k, v in kwargs.items()}})
name, _ = PlaceSanitizer([{
'step': 'tag-analyzer-by-language',
'mode': 'replace',
'whitelist': whitelist
}]).process_names(place)
assert all(isinstance(p.attr, dict) for p in name)
assert all(len(p.attr) <= 1 for p in name)
assert all(not p.attr or ('analyzer' in p.attr and p.attr['analyzer'])
for p in name)
return sorted([(p.name, p.attr.get('analyzer', '')) for p in name])
def run_sanitizer_replace(mode, country, **kwargs):
place = PlaceInfo({
'name': {k.replace('_', ':'): v
for k, v in kwargs.items()},
'country_code': country
})
name, _ = PlaceSanitizer([{
'step': 'tag-analyzer-by-language',
'use-defaults': mode,
'mode': 'replace'
}]).process_names(place)
assert all(isinstance(p.attr, dict) for p in name)
assert all(len(p.attr) <= 1 for p in name)
assert all(not p.attr or ('analyzer' in p.attr and p.attr['analyzer'])
for p in name)
return sorted([(p.name, p.attr.get('analyzer', '')) for p in name])
def test_sanitizer_default():
san = sanitizer.PlaceSanitizer([{'step': 'split-name-list'}])
name, address = san.process_names(
PlaceInfo({
'name': {
'name:de:de': '1;2;3'
},
'address': {
'street': 'Bald'
}
}))
assert len(name) == 3
assert all(isinstance(n, sanitizer.PlaceName) for n in name)
assert all(n.kind == 'name' for n in name)
assert all(n.suffix == 'de:de' for n in name)
assert len(address) == 1
assert all(isinstance(n, sanitizer.PlaceName) for n in address)
def process_address(self, **kwargs):
return self.analyzer.process_place(PlaceInfo({'address': kwargs}))
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 process_named_place(self, names):
return self.analyzer.process_place(PlaceInfo({'name': names}))
def test_process_place_housenumbers_lists(analyzer):
info = analyzer.process_place(PlaceInfo({'address': {'conscriptionnumber' : '1; 2;3'}}))
assert set(info['hnr'].split(';')) == set(('1', '2', '3'))
def test_process_place_bad_postcode(analyzer, create_postcode_id, word_table,
pcode):
analyzer.process_place(PlaceInfo({'address': {'postcode': pcode}}))
assert not word_table.get_postcodes()