spaCy/spacy/lang/fr/__init__.py

51 lines
1.3 KiB
Python

from typing import Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .punctuation import TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from .lemmatizer import FrenchLemmatizer
from ...lookups import Lookups
from ...language import Language
class FrenchDefaults(Language.Defaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
prefixes = TOKENIZER_PREFIXES
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
token_match = TOKEN_MATCH
lex_attr_getters = LEX_ATTRS
syntax_iterators = SYNTAX_ITERATORS
stop_words = STOP_WORDS
class French(Language):
lang = "fr"
Defaults = FrenchDefaults
@French.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 = FrenchLemmatizer.load_lookups(nlp.lang, mode, lookups)
return FrenchLemmatizer(nlp.vocab, model, name, mode=mode, lookups=lookups)
__all__ = ["French"]