mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
24 lines
579 B
Python
24 lines
579 B
Python
|
# 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)
|