from typing import Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from ...language import Language, BaseDefaults
from .lemmatizer import IrishLemmatizer
class IrishDefaults(BaseDefaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
stop_words = STOP_WORDS
class Irish(Language):
lang = "ga"
Defaults = IrishDefaults
@Irish.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={"model": None, "mode": "pos_lookup", "overwrite": False},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
):
return IrishLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
__all__ = ["Irish"]
