spaCy/spacy/lang/ti/tokenizer_exceptions.py
2021-01-15 11:57:36 +11:00

23 lines
339 B
Python

from ...symbols import ORTH, NORM
_exc = {}
for exc_data in [
{ORTH: "ት/ቤት"},
{ORTH: "ወ/ሮ", NORM: "ወይዘሮ"},
{ORTH: "ወ/ሪ", NORM: "ወይዘሪት"},
]:
_exc[exc_data[ORTH]] = [exc_data]
for orth in [
"ዓ.ም.",
"ኪ.ሜ.",
]:
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = _exc