2017-07-23 13:51:31 +00:00
|
|
|
# coding: utf8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
2017-07-23 15:54:49 +00:00
|
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
2017-07-23 13:51:31 +00:00
|
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2017-07-23 14:30:34 +00:00
|
|
|
from ...language import Language
|
|
|
|
from ...attrs import LANG
|
|
|
|
from ...util import update_exc
|
2017-07-23 13:51:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
class IndonesianDefaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'id'
|
|
|
|
|
|
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
|
2017-07-23 14:30:34 +00:00
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
2017-07-23 13:51:31 +00:00
|
|
|
stop_words = set(STOP_WORDS)
|
|
|
|
|
|
|
|
|
|
|
|
class Indonesian(Language):
|
|
|
|
lang = 'id'
|
|
|
|
Defaults = IndonesianDefaults
|
|
|
|
|
|
|
|
|
|
|
|
__all__ = ['Indonesian']
|