2016-12-17 14:25:44 +03:00
|
|
|
# encoding: utf8
|
2016-11-02 22:02:41 +03:00
|
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
|
|
2017-02-09 19:07:21 +03:00
|
|
|
from ..language import Language
|
2016-12-08 22:07:14 +03:00
|
|
|
from ..attrs import LANG
|
|
|
|
|
|
2016-12-18 18:54:19 +03:00
|
|
|
from .language_data import *
|
2017-02-09 19:07:21 +03:00
|
|
|
from .punctuation import TOKENIZER_INFIXES
|
2016-11-02 22:02:41 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
class French(Language):
|
|
|
|
|
lang = 'fr'
|
2016-12-08 22:07:14 +03:00
|
|
|
|
2017-02-09 19:07:21 +03:00
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'fr'
|
|
|
|
|
|
|
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
|
|
|
stop_words = STOP_WORDS
|
|
|
|
|
infixes = tuple(TOKENIZER_INFIXES)
|
