spaCy/spacy/lang/sv/__init__.py
Ines Montani f0b30aedad
Make lemmatizers use initialize logic (#6182)
* Make lemmatizer use initialize logic and tidy up

* Fix typo

* Raise for uninitialized tables
2020-10-02 15:42:36 +02:00

40 lines
1.0 KiB
Python

from typing import Optional
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 ...language import Language
from ...pipeline import Lemmatizer
# Punctuation stolen from Danish
from ..da.punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
class SwedishDefaults(Language.Defaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
lex_attr_getters = LEX_ATTRS
syntax_iterators = SYNTAX_ITERATORS
stop_words = STOP_WORDS
class Swedish(Language):
lang = "sv"
Defaults = SwedishDefaults
@Swedish.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={"model": None, "mode": "rule"},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
return Lemmatizer(nlp.vocab, model, name, mode=mode)
__all__ = ["Swedish"]