explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

a start

Browse Source
This commit is contained in:
Jim O'Regan 2017-06-26 22:40:04 +01:00
parent 28d7f0a672
commit 2f84c73585
1 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
spacy/lang/pl/tokenizer_exceptions.py Normal file
View File

@ -0,0 +1,23 @@
# 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)