2020-07-22 23:18:46 +03:00
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2020-07-23 00:09:01 +03:00
|
|
|
|
from ...symbols import ORTH, NORM
|
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 [
|
2020-07-23 00:09:01 +03:00
|
|
|
|
{ORTH: "вул.", NORM: "вулиця"},
|
|
|
|
|
|
{ORTH: "ім.", NORM: "імені"},
|
|
|
|
|
|
{ORTH: "просп.", NORM: "проспект"},
|
|
|
|
|
|
{ORTH: "бул.", NORM: "бульвар"},
|
|
|
|
|
|
{ORTH: "пров.", NORM: "провулок"},
|
|
|
|
|
|
{ORTH: "пл.", NORM: "площа"},
|
|
|
|
|
|
{ORTH: "г.", NORM: "гора"},
|
|
|
|
|
|
{ORTH: "п.", NORM: "пан"},
|
|
|
|
|
|
{ORTH: "м.", NORM: "місто"},
|
|
|
|
|
|
{ORTH: "проф.", NORM: "професор"},
|
|
|
|
|
|
{ORTH: "акад.", NORM: "академік"},
|
|
|
|
|
|
{ORTH: "доц.", NORM: "доцент"},
|
|
|
|
|
|
{ORTH: "оз.", NORM: "озеро"},
|
2019-02-08 16:14:49 +03:00
|
|
|
|
]:
|
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)
|
