def test_special_characters_are_not_ignored(self):
found, *_ = TextSearcher.find(phrase_to_find="Armii Krajowej",
text="na ulicy Armii, Krajowej")
self.assertFalse(found)
found, *_ = TextSearcher.find(phrase_to_find="Armii Krajowej",
text="na ulicy Armii Krajowej")
self.assertTrue(found)
def test_custom_comparators(self):
eq_comparator = MorphologicComparator().equals
to_find = "Nowy Kleparz"
found, *_ = TextSearcher.find(phrase_to_find=to_find,
text="na Nowym Kleparzu",
equality_comparator=eq_comparator)
self.assertTrue(found)
found, *_ = TextSearcher.find(phrase_to_find=to_find,
text="lokalizacja Nowy Kleparz",
equality_comparator=eq_comparator)
self.assertTrue(found)
found, *_ = TextSearcher.find(phrase_to_find=to_find,
text="niedaleko od Nowego Kleparza",
equality_comparator=eq_comparator)
self.assertTrue(found)
def _contains_phrase(self, phrase, flat):
comparator = MorphologicComparator().equals
found_in_title, _ = TextSearcher.find(
phrase_to_find=phrase,
text=flat.title,
equality_comparator=comparator)
if found_in_title:
return True
found_in_description, _ = TextSearcher.find(
phrase_to_find=phrase,
text=flat.description,
equality_comparator=comparator)
if found_in_description:
return True
return False
def __call__(self, description: str):
phrases_to_look_for = ['przechodni pokój', 'pokój przechodni']
comparator = MorphologicComparator().equals
for phrase in phrases_to_look_for:
found, _ = TextSearcher.find(phrase_to_find=phrase,
text=description,
equality_comparator=comparator)
if found:
return {True}
return {False}
def __call__(self, description: str):
phrases_to_look_for = ['aneks kuchenny', 'aneks', 'salon z kuchnią']
comparator = MorphologicComparator().equals
for phrase in phrases_to_look_for:
found, _ = TextSearcher.find(
phrase_to_find=phrase,
text=description,
equality_comparator=comparator)
if found:
return {True}
return {False}
def __call__(self, description: str):
phrases_to_look_for = [
'kawalerka', 'studio', 'garsoniera', 'jednopokojowe', '1-pokojowe',
'1 pokojowe', 'jedno pokojowe'
]
comparator = MorphologicComparator().equals
for phrase in phrases_to_look_for:
found, _ = TextSearcher.find(phrase_to_find=phrase,
text=description,
equality_comparator=comparator)
if found:
return {True}
return {False}
def does_contain_person_first_name(self, text):
# check contain_exceptions
for contain_exception, ret_val in self._contain_person_first_name_exceptions.items(
):
comparator = MorphologicComparator().equals
does_contain, *_ = TextSearcher.find(
phrase_to_find=contain_exception,
text=text,
equality_comparator=comparator)
if does_contain:
return ret_val
# do normal text analysis
for word in text.split():
for inflection in self._analyser.get_base_form(word):
if inflection in self._first_names:
return True
return False
def _match_locations(self, all_locations, description):
all_matched_locations = []
for location in all_locations:
for location_name in [
location["official"], *location["colloquial"]
]:
found, all_words = TextSearcher.find(
phrase_to_find=location_name,
text=description,
equality_comparator=self._get_comparator(location_name))
if found:
for match_slice_pos in found:
match = AddressMatch(
location=location['official'],
match_slice_position=match_slice_pos,
source=all_words)
all_matched_locations.append(match)
return all_matched_locations
def test_text_searcher_correctly_handles_incorrect_spacing(self):
# hyphen should be surrounded by spaces
found, *_ = TextSearcher.find(phrase_to_find="Armii Krajowej",
text="Armii Krajowej-na skrzyżowaniu")
self.assertTrue(found)