from typing import Optional, Callable
from thinc.api import Model

from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from .lemmatizer import GreekLemmatizer
from ...language import Language, BaseDefaults


class GreekDefaults(BaseDefaults):
    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
    prefixes = TOKENIZER_PREFIXES
    suffixes = TOKENIZER_SUFFIXES
    infixes = TOKENIZER_INFIXES
    lex_attr_getters = LEX_ATTRS
    stop_words = STOP_WORDS
    syntax_iterators = SYNTAX_ITERATORS


class Greek(Language):
    lang = "el"
    Defaults = GreekDefaults


@Greek.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 GreekLemmatizer(
        nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
    )


__all__ = ["Greek"]