mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
52 lines
1.1 KiB
Python
52 lines
1.1 KiB
Python
from typing import Optional
|
|
from thinc.api import Model
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .lemmatizer import RussianLemmatizer
|
|
from ...language import Language
|
|
from ...lookups import Lookups
|
|
from ...util import load_config_from_str
|
|
|
|
|
|
DEFAULT_CONFIG = """
|
|
[initialize]
|
|
|
|
[initialize.lookups]
|
|
@misc = "spacy.LookupsDataLoader.v1"
|
|
lang = ${nlp.lang}
|
|
tables = ["lexeme_norm"]
|
|
"""
|
|
|
|
|
|
class RussianDefaults(Language.Defaults):
|
|
config = load_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
|
|
|
|
|
|
@Russian.factory(
|
|
"lemmatizer",
|
|
assigns=["token.lemma"],
|
|
default_config={"model": None, "mode": "pymorphy2", "lookups": None},
|
|
default_score_weights={"lemma_acc": 1.0},
|
|
)
|
|
def make_lemmatizer(
|
|
nlp: Language,
|
|
model: Optional[Model],
|
|
name: str,
|
|
mode: str,
|
|
lookups: Optional[Lookups],
|
|
):
|
|
return RussianLemmatizer(nlp.vocab, model, name, mode=mode, lookups=lookups)
|
|
|
|
|
|
__all__ = ["Russian"]
|