mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
a741de7cf6
* Adding Support for Yoruba * test text * Updated test string. * Fixing encoding declaration. * Adding encoding to stop_words.py * Added contributor agreement and removed iranlowo. * Added removed test files and removed iranlowo to keep project bare. * Returned CONTRIBUTING.md to default state. * Added delted conftest entries * Tidy up and auto-format * Revert CONTRIBUTING.md Co-authored-by: Ines Montani <ines@ines.io>
25 lines
593 B
Python
25 lines
593 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
|
|
|
|
class YorubaDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "yo"
|
|
stop_words = STOP_WORDS
|
|
tokenizer_exceptions = BASE_EXCEPTIONS
|
|
|
|
|
|
class Yoruba(Language):
|
|
lang = "yo"
|
|
Defaults = YorubaDefaults
|
|
|
|
|
|
__all__ = ["Yoruba"]
|