2017-03-12 12:07:28 +00:00
|
|
|
# coding: utf8
|
2017-05-08 13:52:01 +00:00
|
|
|
from __future__ import unicode_literals
|
2016-11-02 19:02:41 +00:00
|
|
|
|
2017-05-08 13:52:01 +00:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from .lemmatizer import LOOKUP
|
|
|
|
|
|
|
|
from ..language_data import BASE_EXCEPTIONS
|
2016-11-02 19:02:41 +00:00
|
|
|
from ..language import Language
|
2017-05-08 13:52:01 +00:00
|
|
|
from ..lemmatizerlookup import Lemmatizer
|
2016-12-08 19:41:41 +00:00
|
|
|
from ..attrs import LANG
|
2017-05-08 13:52:01 +00:00
|
|
|
from ..util import update_exc
|
2016-12-08 19:41:41 +00:00
|
|
|
|
2016-11-02 19:02:41 +00:00
|
|
|
|
|
|
|
class Portuguese(Language):
|
|
|
|
lang = 'pt'
|
2016-12-08 19:41:41 +00:00
|
|
|
|
2016-11-02 19:02:41 +00:00
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'pt'
|
|
|
|
|
2017-05-08 13:52:01 +00:00
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
|
|
stop_words = set(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):
|
2017-05-08 13:52:01 +00:00
|
|
|
return Lemmatizer(LOOKUP)
|
2017-05-03 10:14:42 +00:00
|
|
|
|
2017-05-03 09:01:42 +00:00
|
|
|
|
2017-05-08 13:52:01 +00:00
|
|
|
__all__ = ['Portuguese']
|