spaCy/spacy/sv/language_data.py

20 lines
577 B
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2016-12-20 13:05:06 +03:00
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
2017-02-04 17:22:21 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, ORTH_ONLY
2016-12-20 13:05:06 +03:00
STOP_WORDS = set(STOP_WORDS)
2017-02-04 17:22:21 +03:00
TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
2016-12-20 13:05:06 +03:00
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]