spaCy/spacy/lang/lij/tokenizer_exceptions.py
2023-06-26 11:41:03 +02:00

50 lines
870 B
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 ...symbols import ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}
for raw in [
"a-e",
"a-o",
"a-i",
"a-a",
"co-a",
"co-e",
"co-i",
"co-o",
"da-a",
"da-e",
"da-i",
"da-o",
"pe-a",
"pe-e",
"pe-i",
"pe-o",
]:
for orth in [raw, raw.capitalize()]:
_exc[orth] = [{ORTH: orth}]
# Prefix + prepositions with à (e.g. "sott'a-o")
for prep in [
"a-a",
"a-e",
"a-o",
"a-i",
]:
for prefix in [
"sott'",
"sott",
"contr'",
"contr",
"ch'",
"ch",
"s'",
"s",
]:
for prefix_orth in [prefix, prefix.capitalize()]:
_exc[prefix_orth + prep] = [{ORTH: prefix_orth}, {ORTH: prep}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)