2017-03-12 12:07:28 +00:00
|
|
|
# coding: utf8
|
2015-09-06 20:10:37 +00:00
|
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
|
|
|
|
from ..language import Language
|
2016-12-08 18:52:18 +00:00
|
|
|
from ..attrs import LANG
|
|
|
|
|
2016-12-18 15:54:19 +00:00
|
|
|
from .language_data import *
|
2017-05-03 10:14:42 +00:00
|
|
|
from ..lemmatizerlookup import Lemmatizer
|
|
|
|
from .lemmatization import LOOK_UP
|
2015-09-06 20:10:37 +00:00
|
|
|
|
2016-11-02 19:03:24 +00:00
|
|
|
class Italian(Language):
|
2016-11-02 18:56:32 +00:00
|
|
|
lang = 'it'
|
2016-12-08 18:52:18 +00:00
|
|
|
|
2016-11-02 18:56:32 +00:00
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'it'
|
|
|
|
|
2016-12-08 18:52:18 +00:00
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
|
|
stop_words = STOP_WORDS
|
2017-05-03 09:01:42 +00:00
|
|
|
|
2017-05-03 10:14:42 +00:00
|
|
|
@classmethod
|
|
|
|
def create_lemmatizer(cls, nlp=None):
|
|
|
|
return Lemmatizer(LOOK_UP)
|
|
|
|
|
|
|
|
|
2017-05-03 09:01:42 +00:00
|
|
|
|
|
|
|
EXPORT = Italian
|