spaCy/spacy/ru/language_data.py
yuukos 241d19a3e6 fixed Russian Tokenizer
- added trailing space flags for tokens
2017-10-16 13:37:05 +07:00

19 lines
440 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
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
STOP_WORDS = set(STOP_WORDS)
TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
__all__ = ["STOP_WORDS", "TOKENIZER_EXCEPTIONS"]