Add short names of months to tokenizer_exceptions

This commit is contained in:
mollerhoj 2017-07-03 15:44:17 +02:00
parent e840077601
commit e8f40ceed8

View File

@ -1,11 +1,27 @@
# encoding: utf8
from __future__ import unicode_literals
from ...symbols import ORTH, LEMMA
from ...symbols import ORTH, LEMMA, NORM
_exc = {}
for exc_data in [
{ORTH: "Kbh.", LEMMA: "København", NORM: "København"},
{ORTH: "Jan.", LEMMA: "januar", NORM: "januar"},
{ORTH: "Feb.", LEMMA: "februar", NORM: "februar"},
{ORTH: "Mar.", LEMMA: "marts", NORM: "marts"},
{ORTH: "Apr.", LEMMA: "april", NORM: "april"},
{ORTH: "Maj.", LEMMA: "maj", NORM: "maj"},
{ORTH: "Jun.", LEMMA: "juni", NORM: "juni"},
{ORTH: "Jul.", LEMMA: "juli", NORM: "juli"},
{ORTH: "Aug.", LEMMA: "august", NORM: "august"},
{ORTH: "Sep.", LEMMA: "september", NORM: "september"},
{ORTH: "Okt.", LEMMA: "oktober", NORM: "oktober"},
{ORTH: "Nov.", LEMMA: "november", NORM: "november"},
{ORTH: "Dec.", LEMMA: "december", NORM: "december"}]:
_exc[exc_data[ORTH]] = [dict(exc_data)]
for orth in [
"A/S", "beg.", "bl.a.", "ca.", "d.s.s.", "dvs.", "f.eks.", "fr.", "hhv.",