mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
abd3f2b65a
Rename Polish lemmatizer method to `pos_lookup` to distinguish it from pure token-based lookup methods.
53 lines
1.3 KiB
Python
53 lines
1.3 KiB
Python
from typing import Optional
|
|
|
|
from thinc.api import Model
|
|
|
|
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 .lemmatizer import PolishLemmatizer
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...lookups import Lookups
|
|
from ...language import Language
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = {
|
|
exc: val for exc, val in BASE_EXCEPTIONS.items() if not exc.endswith(".")
|
|
}
|
|
|
|
|
|
class PolishDefaults(Language.Defaults):
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
lex_attr_getters = LEX_ATTRS
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Polish(Language):
|
|
lang = "pl"
|
|
Defaults = PolishDefaults
|
|
|
|
|
|
@Polish.factory(
|
|
"lemmatizer",
|
|
assigns=["token.lemma"],
|
|
default_config={"model": None, "mode": "pos_lookup", "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 = PolishLemmatizer.load_lookups(nlp.lang, mode, lookups)
|
|
return PolishLemmatizer(nlp.vocab, model, name, mode=mode, lookups=lookups)
|
|
|
|
|
|
__all__ = ["Polish"]
|