spaCy/spacy/lang/hsb/tokenizer_exceptions.py

19 lines
386 B
Python

from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = dict()
for exc_data in [
{ORTH: "mil.", NORM: "milion"},
{ORTH: "wob.", NORM: "wobydler"},
]:
_exc[exc_data[ORTH]] = [exc_data]
for orth in [
"resp.",
]:
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)