spaCy/spacy/lang/es/tokenizer_exceptions.py

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...util import update_exc


_exc = {
    "pal": [{ORTH: "pa"}, {ORTH: "l", NORM: "el"}],
}


for exc_data in [
    {ORTH: "n°"},
    {ORTH: "°C"},
    {ORTH: "aprox."},
    {ORTH: "dna."},
    {ORTH: "dpto."},
    {ORTH: "ej."},
    {ORTH: "esq."},
    {ORTH: "pág."},
    {ORTH: "p.ej."},
    {ORTH: "Ud.", NORM: "usted"},
    {ORTH: "Vd.", NORM: "usted"},
    {ORTH: "Uds.", NORM: "ustedes"},
    {ORTH: "Vds.", NORM: "ustedes"},
    {ORTH: "vol.", NORM: "volúmen"},
]:
    _exc[exc_data[ORTH]] = [exc_data]


# Times

_exc["12m."] = [{ORTH: "12"}, {ORTH: "m."}]


for h in range(1, 12 + 1):
    for period in ["a.m.", "am"]:
        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period}]
    for period in ["p.m.", "pm"]:
        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period}]


for orth in [
    "a.C.",
    "a.J.C.",
    "d.C.",
    "d.J.C.",
    "apdo.",
    "Av.",
    "Avda.",
    "Cía.",
    "Dr.",
    "Dra.",
    "EE.UU.",
    "Ee.Uu.",
    "UU.", # For "EE. UU."
    "Uu.", # For "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.",
]:
    _exc[orth] = [{ORTH: orth}]


TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)