spaCy/spacy/lang/es/tokenizer_exceptions.py

67 lines
1.4 KiB
Python
Raw Normal View History

from ...symbols import ORTH, LEMMA, NORM, PRON_LEMMA
2016-12-18 18:54:19 +03:00
2017-05-08 16:48:04 +03:00
_exc = {
"pal": [{ORTH: "pa", LEMMA: "para"}, {ORTH: "l", LEMMA: "el", NORM: "el"}],
"pala": [{ORTH: "pa", LEMMA: "para"}, {ORTH: "la", LEMMA: "la", NORM: "la"}],
2017-05-08 16:48:04 +03:00
}
2017-05-08 16:48:04 +03:00
for exc_data in [
{ORTH: "aprox.", LEMMA: "aproximadamente"},
{ORTH: "dna.", LEMMA: "docena"},
{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"},
]:
2017-11-02 01:02:45 +03:00
_exc[exc_data[ORTH]] = [exc_data]
2017-05-08 16:48:04 +03:00
# Times
_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", LEMMA: "p.m."}]
2017-05-08 16:48:04 +03:00
for h in range(1, 12 + 1):
for period in ["a.m.", "am"]:
2019-12-25 19:59:52 +03:00
_exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, LEMMA: "a.m."}]
2017-05-08 16:48:04 +03:00
for period in ["p.m.", "pm"]:
2019-12-25 19:59:52 +03:00
_exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, LEMMA: "p.m."}]
2017-05-08 16:48:04 +03:00
for orth in [
"a.C.",
"a.J.C.",
"apdo.",
"Av.",
"Avda.",
"Cía.",
"etc.",
"Gob.",
"Gral.",
"Ing.",
"J.C.",
"Lic.",
"m.n.",
"no.",
"núm.",
"P.D.",
"Prof.",
"Profa.",
"q.e.p.d.",
"S.A.",
"S.L.",
"s.s.s.",
"Sr.",
"Sra.",
"Srta.",
]:
2017-05-08 16:48:04 +03:00
_exc[orth] = [{ORTH: orth}]
2016-12-18 18:54:19 +03:00
TOKENIZER_EXCEPTIONS = _exc