mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
27 lines
824 B
Python
27 lines
824 B
Python
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
||
from ...symbols import ORTH, NORM
|
||
from ...util import update_exc
|
||
|
||
|
||
_exc = {}
|
||
|
||
for exc_data in [
|
||
{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"},
|
||
]:
|
||
_exc[exc_data[ORTH]] = [exc_data]
|
||
|
||
|
||
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
|