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
|
2017-05-12 13:37:45 +00:00
|
|
|
from .lex_attrs import LEX_ATTRS
|
2017-05-08 13:52:01 +00:00
|
|
|
from .lemmatizer import LOOKUP
|
|
|
|
|
|
2017-05-08 20:29:04 +00:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2017-06-03 20:29:21 +00:00
|
|
|
from ..norm_exceptions import BASE_NORMS
|
2017-05-08 20:29:04 +00:00
|
|
|
from ...language import Language
|
2017-06-03 20:29:21 +00:00
|
|
|
from ...attrs import LANG, NORM
|
|
|
|
|
from ...util import update_exc, add_lookups
|
2016-12-08 19:41:41 +00:00
|
|
|
|
2016-11-02 19:02:41 +00:00
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
class PortugueseDefaults(Language.Defaults):
|
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'pt'
|
2017-06-03 20:29:21 +00:00
|
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
|
2017-05-20 17:02:27 +00:00
|
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
2017-10-11 13:34:55 +00:00
|
|
|
stop_words = STOP_WORDS
|
|
|
|
|
lemma_lookup = LOOKUP
|
2016-11-02 19:02:41 +00:00
|
|
|
|
2017-05-03 09:01:42 +00:00
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
class Portuguese(Language):
|
|
|
|
|
lang = 'pt'
|
|
|
|
|
Defaults = PortugueseDefaults
|
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']
|
