You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
58 lines
1.5 KiB
58 lines
1.5 KiB
from typing import Callable, Optional
|
|
|
|
from thinc.api import Model
|
|
|
|
from ...attrs import LANG
|
|
from ...language import BaseDefaults, Language
|
|
from ...lookups import Lookups
|
|
from ...util import update_exc
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from .lemmatizer import MacedonianLemmatizer
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
|
|
class MacedonianDefaults(BaseDefaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "mk"
|
|
|
|
# Optional: replace flags with custom functions, e.g. like_num()
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
# Merge base exceptions and custom tokenizer exceptions
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Macedonian(Language):
|
|
lang = "mk"
|
|
Defaults = MacedonianDefaults
|
|
|
|
|
|
@Macedonian.factory(
|
|
"lemmatizer",
|
|
assigns=["token.lemma"],
|
|
default_config={
|
|
"model": None,
|
|
"mode": "rule",
|
|
"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 MacedonianLemmatizer(
|
|
nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
|
|
)
|
|
|
|
|
|
__all__ = ["Macedonian"]
|