spaCy/spacy/lang/es/__init__.py

39 lines
1.1 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2017-05-08 16:48:04 +03:00
from __future__ import unicode_literals
2017-05-08 16:48:04 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .lemmatizer import LOOKUP
from .syntax_iterators import SYNTAX_ITERATORS
2017-05-08 23:29:04 +03:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
2017-05-08 23:29:04 +03:00
from ...language import Language
from ...lemmatizerlookup import Lemmatizer
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2016-12-08 21:47:03 +03:00
class SpanishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'es'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = dict(TAG_MAP)
stop_words = set(STOP_WORDS)
sytax_iterators = dict(SYNTAX_ITERATORS)
2016-12-08 21:47:03 +03:00
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
2017-05-03 12:01:42 +03:00
class Spanish(Language):
lang = 'es'
Defaults = SpanishDefaults
2017-05-08 16:48:04 +03:00
__all__ = ['Spanish']