2020-07-22 23:18:46 +03:00
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2019-02-07 23:05:11 +03:00
|
|
|
|
from ...symbols import ORTH, LEMMA, POS, NORM, NOUN
|
2020-07-22 23:18:46 +03:00
|
|
|
|
from ...util import update_exc
|
2019-02-07 23:05:11 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
_exc = {}
|
|
|
|
|
|
|
|
|
|
|
|
for exc_data in [
|
|
|
|
|
|
{ORTH: "вул.", LEMMA: "вулиця", NORM: "вулиця", POS: NOUN},
|
|
|
|
|
|
{ORTH: "ім.", LEMMA: "ім'я", NORM: "імені", POS: NOUN},
|
|
|
|
|
|
{ORTH: "просп.", LEMMA: "проспект", NORM: "проспект", POS: NOUN},
|
|
|
|
|
|
{ORTH: "бул.", LEMMA: "бульвар", NORM: "бульвар", POS: NOUN},
|
|
|
|
|
|
{ORTH: "пров.", LEMMA: "провулок", NORM: "провулок", POS: NOUN},
|
|
|
|
|
|
{ORTH: "пл.", LEMMA: "площа", NORM: "площа", POS: NOUN},
|
|
|
|
|
|
{ORTH: "г.", LEMMA: "гора", NORM: "гора", POS: NOUN},
|
|
|
|
|
|
{ORTH: "п.", LEMMA: "пан", NORM: "пан", POS: NOUN},
|
|
|
|
|
|
{ORTH: "м.", LEMMA: "місто", NORM: "місто", POS: NOUN},
|
|
|
|
|
|
{ORTH: "проф.", LEMMA: "професор", NORM: "професор", POS: NOUN},
|
|
|
|
|
|
{ORTH: "акад.", LEMMA: "академік", NORM: "академік", POS: NOUN},
|
|
|
|
|
|
{ORTH: "доц.", LEMMA: "доцент", NORM: "доцент", POS: NOUN},
|
2019-02-08 16:14:49 +03:00
|
|
|
|
{ORTH: "оз.", LEMMA: "озеро", NORM: "озеро", POS: NOUN},
|
|
|
|
|
|
]:
|
2019-02-07 23:05:11 +03:00
|
|
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-22 23:18:46 +03:00
|
|
|
|
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
|
