Reorganise Dutch language data

This commit is contained in:
ines 2017-05-08 15:51:39 +02:00
parent 04ef5025bd
commit 279895ea83

View File

@ -1,9 +1,13 @@
# coding: utf8
from __future__ import unicode_literals, print_function
from __future__ import unicode_literals
from .stop_words import STOP_WORDS
from ..language_data import BASE_EXCEPTIONS
from ..language import Language
from ..attrs import LANG
from .language_data import *
from ..util import update_exc
class Dutch(Language):
@ -13,8 +17,8 @@ class Dutch(Language):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'nl'
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
stop_words = STOP_WORDS
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
EXPORT = Dutch
__all__ = ['Dutch']