spaCy/spacy/es/language_data.py
2016-12-18 16:54:19 +01:00

20 lines
511 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, ORTH_ONLY
TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
STOP_WORDS = set(STOP_WORDS)
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]