mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
7ed7908716
* Add support basic support for upper sorbian. * Add tokenizer exceptions and tests. * Update spacy/lang/hsb/examples.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
19 lines
386 B
Python
19 lines
386 B
Python
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...symbols import ORTH, NORM
|
|
from ...util import update_exc
|
|
|
|
_exc = dict()
|
|
for exc_data in [
|
|
{ORTH: "mil.", NORM: "milion"},
|
|
{ORTH: "wob.", NORM: "wobydler"},
|
|
]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
for orth in [
|
|
"resp.",
|
|
]:
|
|
_exc[orth] = [{ORTH: orth}]
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
|