spaCy/spacy/lang/nl/__init__.py

55 lines
1.3 KiB
Python

from typing import Optional, Callable
from thinc.api import Model
from .lemmatizer import DutchLemmatizer
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .punctuation import TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from ...language import Language, BaseDefaults
class DutchDefaults(BaseDefaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
prefixes = TOKENIZER_PREFIXES
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
lex_attr_getters = LEX_ATTRS
syntax_iterators = SYNTAX_ITERATORS
stop_words = STOP_WORDS
class Dutch(Language):
lang = "nl"
Defaults = DutchDefaults
@Dutch.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 DutchLemmatizer(
nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
)
__all__ = ["Dutch"]