spaCy/spacy/nl/language_data.py

18 lines
401 B
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
from __future__ import unicode_literals
2016-12-18 18:54:19 +03:00
from .. import language_data as base
from ..language_data import update_exc, strings_to_exc
from .word_sets import STOP_WORDS, NUM_WORDS
2016-12-18 18:54:19 +03:00
STOP_WORDS = set(STOP_WORDS)
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"]