mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
25bd9f9d48
* added it vocab * copied portuguese * added possessive determiner * added conjed Nps * added nmoded Nps * test misc * more examples * fixed typo * fixed parenth * fixed comma * comma fix * added syntax iters * fix some index problems * fixed index * corrected heads for test case * fixed tets case * fixed determiner gender * cleaned left over * added example with apostophe
50 lines
1.2 KiB
Python
50 lines
1.2 KiB
Python
from typing import Optional, Callable
|
|
from thinc.api import Model
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
|
from ...language import Language, BaseDefaults
|
|
from .lemmatizer import ItalianLemmatizer
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
|
|
|
|
class ItalianDefaults(BaseDefaults):
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
stop_words = STOP_WORDS
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
|
|
class Italian(Language):
|
|
lang = "it"
|
|
Defaults = ItalianDefaults
|
|
|
|
|
|
@Italian.factory(
|
|
"lemmatizer",
|
|
assigns=["token.lemma"],
|
|
default_config={
|
|
"model": None,
|
|
"mode": "pos_lookup",
|
|
"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 ItalianLemmatizer(
|
|
nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
|
|
)
|
|
|
|
|
|
__all__ = ["Italian"]
|