spaCy/spacy/lang/it/tokenizer_exceptions.py

59 lines
1.1 KiB
Python
Raw Normal View History

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH
from ...util import update_exc
_exc = {
"all'art.": [{ORTH: "all'"}, {ORTH: "art."}],
"dall'art.": [{ORTH: "dall'"}, {ORTH: "art."}],
"dell'art.": [{ORTH: "dell'"}, {ORTH: "art."}],
"L'art.": [{ORTH: "L'"}, {ORTH: "art."}],
"l'art.": [{ORTH: "l'"}, {ORTH: "art."}],
"nell'art.": [{ORTH: "nell'"}, {ORTH: "art."}],
"po'": [{ORTH: "po'"}],
2020-03-25 14:28:12 +03:00
"sett..": [{ORTH: "sett."}, {ORTH: "."}],
}
for orth in [
"..",
"....",
"al.",
"all-path",
"art.",
"Art.",
"artt.",
"att.",
"by-pass",
"c.d.",
"centro-sinistra",
"check-up",
"Civ.",
"cm.",
"Cod.",
"col.",
"Cost.",
"d.C.",
2020-03-25 14:28:12 +03:00
'de"',
"distr.",
"E'",
"ecc.",
"e-mail",
"e/o",
"etc.",
"Jr.",
"",
"nord-est",
"pag.",
"Proc.",
"prof.",
"sett.",
"s.p.a.",
"ss.",
"St.",
"tel.",
"week-end",
]:
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)