2016-12-17 11:25:44 +00:00
|
|
|
# encoding: utf8
|
2016-11-02 19:02:41 +00:00
|
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
|
|
|
|
from os import path
|
|
|
|
|
|
|
|
from ..language import Language
|
|
|
|
from . import language_data
|
2016-12-08 18:47:03 +00:00
|
|
|
from ..attrs import LANG
|
|
|
|
|
2016-12-17 11:29:02 +00:00
|
|
|
from ..language_data import update_exc
|
2016-12-17 11:32:48 +00:00
|
|
|
from ..language_data import strings_to_exc
|
2016-12-08 18:47:03 +00:00
|
|
|
from ..language_data import EMOTICONS
|
2016-12-17 11:33:09 +00:00
|
|
|
|
2016-12-08 18:47:03 +00:00
|
|
|
from .language_data import ORTH_ONLY
|
|
|
|
|
|
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)
|
|
|
|
TOKENIZER_PREFIXES = tuple(language_data.TOKENIZER_PREFIXES)
|
|
|
|
TOKENIZER_SUFFIXES = tuple(language_data.TOKENIZER_SUFFIXES)
|
|
|
|
TOKENIZER_INFIXES = tuple(language_data.TOKENIZER_INFIXES)
|
|
|
|
TAG_MAP = dict(language_data.TAG_MAP)
|
|
|
|
STOP_WORDS = set(language_data.STOP_WORDS)
|
|
|
|
|
|
|
|
|
|
|
|
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(EMOTICONS))
|
|
|
|
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
|
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
|
|
|
|
prefixes = TOKENIZER_PREFIXES
|
|
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
|
|
infixes = TOKENIZER_INFIXES
|
|
|
|
tag_map = TAG_MAP
|
|
|
|
stop_words = STOP_WORDS
|