mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
27 lines
796 B
Python
27 lines
796 B
Python
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
class MultiLanguageDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "xx"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
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"]
|