2017-03-12 12:07:28 +00:00
|
|
|
# coding: utf8
|
2016-11-02 19:02:41 +00:00
|
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
|
|
|
|
from os import path
|
|
|
|
|
|
|
|
from ..language import Language
|
2016-12-08 18:47:03 +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
|
2016-11-02 19:02:41 +00:00
|
|
|
|
|
|
|
class Spanish(Language):
|
|
|
|
lang = 'es'
|
2016-12-08 18:47:03 +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: 'es'
|
|
|
|
|
2016-12-08 18:47:03 +00:00
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
2017-04-06 16:48:45 +00:00
|
|
|
tag_map = TAG_MAP
|
2016-12-08 18:47:03 +00:00
|
|
|
stop_words = STOP_WORDS
|
2017-05-03 09:01:42 +00:00
|
|
|
|
|
|
|
|
2017-05-03 10:14:42 +00:00
|
|
|
|
2017-05-03 09:01:42 +00:00
|
|
|
EXPORT = Spanish
|