spaCy/spacy/lang/ca/tokenizer_exceptions.py

41 lines
1.2 KiB
Python

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...util import update_exc
_exc = {}
for exc_data in [
{ORTH: "aprox.", NORM: "aproximadament"},
{ORTH: "pàg.", NORM: "pàgina"},
{ORTH: "p.ex.", NORM: "per exemple"},
{ORTH: "gen.", NORM: "gener"},
{ORTH: "feb.", NORM: "febrer"},
{ORTH: "abr.", NORM: "abril"},
{ORTH: "jul.", NORM: "juliol"},
{ORTH: "set.", NORM: "setembre"},
{ORTH: "oct.", NORM: "octubre"},
{ORTH: "nov.", NORM: "novembre"},
{ORTH: "dec.", NORM: "desembre"},
{ORTH: "Dr.", NORM: "doctor"},
{ORTH: "Sr.", NORM: "senyor"},
{ORTH: "Sra.", NORM: "senyora"},
{ORTH: "Srta.", NORM: "senyoreta"},
{ORTH: "núm", NORM: "número"},
{ORTH: "St.", NORM: "sant"},
{ORTH: "Sta.", NORM: "santa"},
]:
_exc[exc_data[ORTH]] = [exc_data]
# Times
_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", NORM: "p.m."}]
for h in range(1, 12 + 1):
for period in ["a.m.", "am"]:
_exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, NORM: "a.m."}]
for period in ["p.m.", "pm"]:
_exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, NORM: "p.m."}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)