spaCy/spacy/lang/lb/tokenizer_exceptions.py

54 lines
1.1 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...util import update_exc
# TODO
# treat other apostrophes within words as part of the word: [op d'mannst], [fir d'éischt] (= exceptions)
_exc = {}
# translate / delete what is not necessary
for exc_data in [
{ORTH: "t", NORM: "et"},
{ORTH: "T", NORM: "et"},
{ORTH: "'t", NORM: "et"},
{ORTH: "'T", NORM: "et"},
{ORTH: "wgl.", NORM: "wannechgelift"},
{ORTH: "M.", NORM: "Monsieur"},
{ORTH: "Mme.", NORM: "Madame"},
{ORTH: "Dr.", NORM: "Dokter"},
{ORTH: "Tel.", NORM: "Telefon"},
{ORTH: "asw.", NORM: "an sou weider"},
{ORTH: "etc.", NORM: "et cetera"},
{ORTH: "bzw.", NORM: "bezéiungsweis"},
{ORTH: "Jan.", NORM: "Januar"},
]:
_exc[exc_data[ORTH]] = [exc_data]
# to be extended
for orth in [
"z.B.",
"Dipl.",
"Dr.",
"etc.",
"i.e.",
"o.k.",
"O.K.",
"p.a.",
"p.s.",
"P.S.",
"phil.",
"q.e.d.",
"R.I.P.",
"rer.",
"sen.",
"ë.a.",
"U.S.",
"U.S.A.",
]:
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)