2017-03-12 12:07:28 +00:00
|
|
|
# coding: utf8
|
2017-05-08 13:51:39 +00:00
|
|
|
from __future__ import unicode_literals
|
2016-11-24 14:56:38 +00:00
|
|
|
|
2017-05-08 13:51:39 +00:00
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
|
|
|
from ..language_data import BASE_EXCEPTIONS
|
2016-11-24 14:56:38 +00:00
|
|
|
from ..language import Language
|
2016-12-17 12:26:01 +00:00
|
|
|
from ..attrs import LANG
|
2017-05-08 13:51:39 +00:00
|
|
|
from ..util import update_exc
|
|
|
|
|
2016-11-24 14:56:38 +00:00
|
|
|
|
|
|
|
|
|
|
|
class Dutch(Language):
|
|
|
|
lang = 'nl'
|
|
|
|
|
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'nl'
|
|
|
|
|
2017-05-08 13:51:39 +00:00
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
|
|
|
|
stop_words = set(STOP_WORDS)
|
2017-05-03 09:01:42 +00:00
|
|
|
|
|
|
|
|
2017-05-08 13:51:39 +00:00
|
|
|
__all__ = ['Dutch']
|