spaCy/spacy/fr/language_data.py

18 lines
393 B
Python
Raw Normal View History

# encoding: utf8
from __future__ import unicode_literals
2016-12-18 18:54:19 +03:00
from .. import language_data as base
from ..language_data import strings_to_exc, update_exc
2016-12-18 18:54:19 +03:00
from .stop_words import STOP_WORDS
2016-12-18 18:54:19 +03:00
STOP_WORDS = set(STOP_WORDS)
2016-12-17 14:33:09 +03:00
TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS)
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
2016-12-18 18:54:19 +03:00
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]