mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
18 lines
393 B
Python
18 lines
393 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
|
|
|
|
|
|
STOP_WORDS = set(STOP_WORDS)
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS)
|
|
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
|
|
|
|
|
|
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]
|