spaCy/spacy/lang/pl/tokenizer_exceptions.py

24 lines
579 B
Python
Raw Normal View History

2017-06-27 00:40:04 +03:00
# encoding: utf8
from __future__ import unicode_literals
from ..symbols import ORTH, LEMMA, POS
_exc = {}
for exc_data in [
{ORTH: "m.in.", LEMMA: "między innymi", POS: ADV},
{ORTH: "inż.", LEMMA: "inżynier", POS: NOUN},
{ORTH: "mgr.", LEMMA: "magister", POS: NOUN},
{ORTH: "tzn.", LEMMA: "to znaczy", POS: ADV},
{ORTH: "tj.", LEMMA: "to jest", POS: ADV},
{ORTH: "tzw.", LEMMA: "tak zwany", POS: ADJ}]:
_exc[exc_data[ORTH]] = [dict(exc_data)],
for orth in [
"w.", "r."]:
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = dict(_exc)