mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
41 lines
930 B
Python
41 lines
930 B
Python
from typing import Callable
|
|
from thinc.api import Config
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .lemmatizer import RussianLemmatizer
|
|
from ...util import registry
|
|
from ...language import Language
|
|
|
|
|
|
DEFAULT_CONFIG = """
|
|
[nlp]
|
|
|
|
[nlp.lemmatizer]
|
|
@lemmatizers = "spacy.ru.RussianLemmatizer"
|
|
"""
|
|
|
|
|
|
@registry.lemmatizers("spacy.ru.RussianLemmatizer")
|
|
def create_lemmatizer() -> Callable[[Language], RussianLemmatizer]:
|
|
def lemmatizer_factory(nlp: Language) -> RussianLemmatizer:
|
|
return RussianLemmatizer()
|
|
|
|
return lemmatizer_factory
|
|
|
|
|
|
class RussianDefaults(Language.Defaults):
|
|
config = Config().from_str(DEFAULT_CONFIG)
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
lex_attr_getters = LEX_ATTRS
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Russian(Language):
|
|
lang = "ru"
|
|
Defaults = RussianDefaults
|
|
|
|
|
|
__all__ = ["Russian"]
|