2017-05-08 13:51:22 +00:00
|
|
|
# coding: utf8
|
|
|
|
from __future__ import unicode_literals
|
2017-03-23 10:10:22 +00:00
|
|
|
|
2017-05-08 13:51:22 +00:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from .morph_rules import MORPH_RULES
|
2017-03-23 10:10:22 +00:00
|
|
|
|
2017-05-08 20:29:04 +00:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
|
|
from ...language import Language
|
|
|
|
from ...attrs import LANG
|
|
|
|
from ...util import update_exc
|
2017-03-23 10:10:22 +00:00
|
|
|
|
|
|
|
|
2017-04-11 16:30:15 +00:00
|
|
|
class Norwegian(Language):
|
2017-05-08 13:51:22 +00:00
|
|
|
lang = 'nb'
|
2017-03-23 10:10:22 +00:00
|
|
|
|
2017-04-12 15:59:55 +00:00
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'nb'
|
2017-05-08 13:51:22 +00:00
|
|
|
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
|
|
stop_words = set(STOP_WORDS)
|
2017-05-03 09:01:42 +00:00
|
|
|
|
|
|
|
|
2017-05-08 13:51:22 +00:00
|
|
|
__all__ = ['Norwegian']
|