spaCy/spacy/lang/nb/__init__.py

45 lines
1.2 KiB
Python

from typing import Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
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 ...language import Language
from ...lookups import Lookups
from ...pipeline import Lemmatizer
class NorwegianDefaults(Language.Defaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
prefixes = TOKENIZER_PREFIXES
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
syntax_iterators = SYNTAX_ITERATORS
stop_words = STOP_WORDS
class Norwegian(Language):
lang = "nb"
Defaults = NorwegianDefaults
@Norwegian.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={"model": None, "mode": "rule", "lookups": None},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
nlp: Language,
model: Optional[Model],
name: str,
mode: str,
lookups: Optional[Lookups],
):
lookups = Lemmatizer.load_lookups(nlp.lang, mode, lookups)
return Lemmatizer(nlp.vocab, model, name, mode=mode, lookups=lookups)
__all__ = ["Norwegian"]