spaCy/spacy/lang/ca/__init__.py

from typing import Optional

from thinc.api import Model

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


class CatalanDefaults(Language.Defaults):
    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
    infixes = TOKENIZER_INFIXES
    suffixes = TOKENIZER_SUFFIXES
    stop_words = STOP_WORDS
    lex_attr_getters = LEX_ATTRS
    syntax_iterators = SYNTAX_ITERATORS


class Catalan(Language):
    lang = "ca"
    Defaults = CatalanDefaults


@Catalan.factory(
    "lemmatizer",
    assigns=["token.lemma"],
    default_config={"model": None, "mode": "rule", "overwrite": False},
    default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
):
    return CatalanLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)


__all__ = ["Catalan"]