mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
15 lines
322 B
Python
15 lines
322 B
Python
|
# encoding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from .. import language_data as base
|
||
|
|
from ..language_data import update_exc, strings_to_exc
|
||
|
|
|
||
|
|
from .stop_words import STOP_WORDS
|
||
|
|
|
||
|
|
|
||
|
|
TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS)
|
||
|
|
STOP_WORDS = set(STOP_WORDS)
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]
|