spaCy/spacy/lang/da/__init__.py

27 lines
648 B
Python
Raw Normal View History

2017-05-10 19:15:12 +00:00
# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
from ...attrs import LANG
from ...util import update_exc
class DanishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'da'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
2017-05-10 19:15:12 +00:00
class Danish(Language):
lang = 'da'
Defaults = DanishDefaults
2017-05-10 19:15:12 +00:00
__all__ = ['Danish']