2017-05-08 16:49:28 +03:00
|
|
|
# coding: utf8
|
|
|
|
from __future__ import unicode_literals
|
2017-03-24 18:27:44 +03:00
|
|
|
|
2017-05-08 16:49:28 +03:00
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
2017-05-08 23:29:04 +03:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
|
|
from ...language import Language
|
|
|
|
from ...attrs import LANG
|
|
|
|
from ...util import update_exc
|
2017-03-24 18:27:44 +03:00
|
|
|
|
|
|
|
|
|
|
|
class Hebrew(Language):
|
|
|
|
lang = 'he'
|
|
|
|
|
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'he'
|
|
|
|
|
2017-05-08 16:49:28 +03:00
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
|
|
|
|
stop_words = set(STOP_WORDS)
|
2017-05-03 12:01:42 +03:00
|
|
|
|
|
|
|
|
2017-05-08 16:49:28 +03:00
|
|
|
__all__ = ['Hebrew']
|