Add 'xx' language ID for multi-language support

Allows models to specify their language ID as 'xx'.
This commit is contained in:
ines 2017-05-28 00:58:59 +02:00
parent 33e332e67c
commit 84189c1cab

26
spacy/lang/xx/__init__.py Normal file
View File

@ -0,0 +1,26 @@
# coding: utf8
from __future__ import unicode_literals
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
from ...attrs import LANG
from ...util import update_exc
class MultiLanguageDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'xx'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
class MultiLanguage(Language):
"""Language class to be used for models that support multiple languages.
This module allows models to specify their language ID as 'xx'.
"""
lang = 'xx'
Defaults = MultiLanguageDefaults
__all__ = ['MultiLanguage']