2017-11-02 15:32:24 +00:00
|
|
|
# coding: utf8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
2017-12-01 14:04:32 +00:00
|
|
|
from .lemmatizer import LOOKUP
|
2017-11-02 15:32:24 +00:00
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
|
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
|
|
|
from ..norm_exceptions import BASE_NORMS
|
|
|
|
|
from ...language import Language
|
|
|
|
|
from ...attrs import LANG, NORM
|
|
|
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TurkishDefaults(Language.Defaults):
|
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'tr'
|
|
|
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
|
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
|
|
|
stop_words = STOP_WORDS
|
2017-12-01 14:04:32 +00:00
|
|
|
lemma_lookup = LOOKUP
|
2017-11-02 15:32:24 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
class Turkish(Language):
|
|
|
|
|
lang = 'tr'
|
|
|
|
|
Defaults = TurkishDefaults
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
__all__ = ['Turkish']
|
|
|
|
|
|
