spaCy/spacy/lang/ru/__init__.py
Richard Hudson a9559e7435
Handle Cyrillic combining diacritics (#10837)
* Handle Russian, Ukrainian and Bulgarian

* Corrections

* Correction

* Correction to comment

* Changes based on review

* Correction

* Reverted irrelevant change in punctuation.py

* Remove unnecessary group

* Reverted accidental change
2022-06-28 15:35:32 +02:00

51 lines
1.3 KiB
Python

from typing import Optional, Callable
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 ..punctuation import COMBINING_DIACRITICS_TOKENIZER_INFIXES
from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
from ...language import Language, BaseDefaults
class RussianDefaults(BaseDefaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
lex_attr_getters = LEX_ATTRS
stop_words = STOP_WORDS
suffixes = COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
infixes = COMBINING_DIACRITICS_TOKENIZER_INFIXES
class Russian(Language):
lang = "ru"
Defaults = RussianDefaults
@Russian.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={
"model": None,
"mode": "pymorphy2",
"overwrite": False,
"scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"},
},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
nlp: Language,
model: Optional[Model],
name: str,
mode: str,
overwrite: bool,
scorer: Optional[Callable],
):
return RussianLemmatizer(
nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
)
__all__ = ["Russian"]