spaCy/spacy/lang/es/tokenizer_exceptions.py

81 lines
1.6 KiB
Python
Raw Normal View History

2017-03-12 12:07:28 +00:00
# coding: utf8
2016-12-18 15:54:19 +00:00
from __future__ import unicode_literals
from ...symbols import ORTH, LEMMA, NORM, PRON_LEMMA
2016-12-18 15:54:19 +00:00
_exc = {}
2017-05-08 13:48:04 +00:00
for exc_data in [
{ORTH: "", LEMMA: "número"},
{ORTH: "°C", LEMMA: "grados Celcius"},
2017-05-08 13:48:04 +00:00
{ORTH: "aprox.", LEMMA: "aproximadamente"},
{ORTH: "dna.", LEMMA: "docena"},
{ORTH: "dpto.", LEMMA: "departamento"},
{ORTH: "ej.", LEMMA: "ejemplo"},
2017-05-08 13:48:04 +00:00
{ORTH: "esq.", LEMMA: "esquina"},
{ORTH: "pág.", LEMMA: "página"},
{ORTH: "p.ej.", LEMMA: "por ejemplo"},
{ORTH: "Ud.", LEMMA: PRON_LEMMA, NORM: "usted"},
{ORTH: "Vd.", LEMMA: PRON_LEMMA, NORM: "usted"},
{ORTH: "Uds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
{ORTH: "Vds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
{ORTH: "vol.", NORM: "volúmen"},
]:
2017-11-01 22:02:45 +00:00
_exc[exc_data[ORTH]] = [exc_data]
2017-05-08 13:48:04 +00:00
# Times
_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", LEMMA: "p.m."}]
2017-05-08 13:48:04 +00:00
for h in range(1, 12 + 1):
for period in ["a.m.", "am"]:
_exc["%d%s" % (h, period)] = [{ORTH: "%d" % h}, {ORTH: period, LEMMA: "a.m."}]
2017-05-08 13:48:04 +00:00
for period in ["p.m.", "pm"]:
_exc["%d%s" % (h, period)] = [{ORTH: "%d" % h}, {ORTH: period, LEMMA: "p.m."}]
2017-05-08 13:48:04 +00:00
for orth in [
"a.C.",
"a.J.C.",
"d.C.",
"d.J.C.",
"apdo.",
"Av.",
"Avda.",
"Cía.",
"Dr.",
"Dra.",
"EE.UU.",
"etc.",
"fig.",
"Gob.",
"Gral.",
"Ing.",
"J.C.",
"km/h",
"Lic.",
"m.n.",
"núm.",
"P.D.",
"Prof.",
"Profa.",
"q.e.p.d.",
"Q.E.P.D."
"S.A.",
"S.L.",
"S.R.L."
"s.s.s.",
"Sr.",
"Sra.",
"Srta.",
]:
2017-05-08 13:48:04 +00:00
_exc[orth] = [{ORTH: orth}]
2016-12-18 15:54:19 +00:00
TOKENIZER_EXCEPTIONS = _exc