spaCy/spacy/sv/language_data.py
2016-12-20 11:05:06 +01:00

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"]