2017-03-12 15:07:28 +03:00
|
|
|
# coding: utf8
|
2016-11-24 17:56:38 +03:00
|
|
|
from __future__ import unicode_literals
|
2016-12-17 15:26:01 +03:00
|
|
|
|
2016-12-18 18:54:19 +03:00
|
|
|
from .. import language_data as base
|
|
|
|
|
from ..language_data import update_exc, strings_to_exc
|
2016-12-17 15:26:01 +03:00
|
|
|
|
2017-07-05 15:08:04 +03:00
|
|
|
from .word_sets import STOP_WORDS, NUM_WORDS
|
2016-12-17 15:26:01 +03:00
|
|
|
|
|
|
|
|
|
2016-12-18 18:54:19 +03:00
|
|
|
STOP_WORDS = set(STOP_WORDS)
|
2016-12-17 15:26:01 +03:00
|
|
|
|
2016-11-24 17:56:38 +03:00
|
|
|
|
2017-01-08 22:36:00 +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"]
|
