mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
87c329c711
For languages without provided models and with lemmatizer rules in `spacy-lookups-data`, make the rule-based lemmatizer the default: Bengali, Persian, Norwegian, Swedish
49 lines
1.2 KiB
Python
49 lines
1.2 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 ...lookups import Lookups
|
|
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", "lookups": None},
|
|
scores=["lemma_acc"],
|
|
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__ = ["Swedish"]
|