2017-05-12 10:25:37 +03:00
|
|
|
# coding: utf8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
|
|
from ...language import Language
|
|
|
|
from ...attrs import LANG
|
|
|
|
from ...util import update_exc
|
|
|
|
|
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class PolishDefaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'pl'
|
|
|
|
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
|
|
|
|
stop_words = set(STOP_WORDS)
|
2017-05-12 10:25:37 +03:00
|
|
|
|
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class Polish(Language):
|
|
|
|
lang = 'pl'
|
|
|
|
Defaults = PolishDefaults
|
2017-05-12 10:25:37 +03:00
|
|
|
|
|
|
|
|
|
|
|
__all__ = ['Polish']
|