wehub-resource-sync
f877c37fc6
tests / Test (macos-latest, 3.14) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.10) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.13) (push) Has been cancelled
tests / Test (windows-latest, 3.14) (push) Has been cancelled
tests / Validate (push) Has been cancelled
tests / Test (macos-latest, 3.10) (push) Has been cancelled
tests / Test (macos-latest, 3.11) (push) Has been cancelled
tests / Test (macos-latest, 3.12) (push) Has been cancelled
tests / Test (macos-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.12) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.14) (push) Has been cancelled
tests / Test (windows-latest, 3.10) (push) Has been cancelled
tests / Test (windows-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.12) (push) Has been cancelled
universe validation / Validate (push) Has been cancelled
34 lines
819 B
Python
34 lines
819 B
Python
from typing import Optional
|
|
|
|
from thinc.api import Model
|
|
|
|
from ...language import BaseDefaults, Language
|
|
from .lemmatizer import IrishLemmatizer
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
|
|
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"]
|