2017-03-12 15:07:28 +03:00
|
|
|
# coding: utf8
|
2017-05-08 16:51:39 +03:00
|
|
|
from __future__ import unicode_literals
|
2016-11-24 17:56:38 +03:00
|
|
|
|
2017-05-08 16:51:39 +03:00
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
2017-05-08 23:29:04 +03:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2017-06-03 23:29:21 +03:00
|
|
|
from ..norm_exceptions import BASE_NORMS
|
2017-05-08 23:29:04 +03:00
|
|
|
from ...language import Language
|
2017-06-03 23:29:21 +03:00
|
|
|
from ...attrs import LANG, NORM
|
|
|
|
from ...util import update_exc, add_lookups
|
2017-05-08 16:51:39 +03:00
|
|
|
|
2016-11-24 17:56:38 +03:00
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class DutchDefaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'nl'
|
2017-06-03 23:29:21 +03:00
|
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
|
2016-11-24 17:56:38 +03:00
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
|
|
|
|
stop_words = set(STOP_WORDS)
|
2016-11-24 17:56:38 +03:00
|
|
|
|
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class Dutch(Language):
|
|
|
|
lang = 'nl'
|
|
|
|
Defaults = DutchDefaults
|
2017-05-03 12:01:42 +03:00
|
|
|
|
|
|
|
|
2017-05-08 16:51:39 +03:00
|
|
|
__all__ = ['Dutch']
|