spaCy/spacy/lang/fa/__init__.py
2020-09-24 10:27:33 +02:00

45 lines
1.2 KiB
Python

from typing import Optional
from thinc.api import Model
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_SUFFIXES
from .syntax_iterators import SYNTAX_ITERATORS
from ...language import Language
from ...lookups import Lookups
from ...pipeline import Lemmatizer
class PersianDefaults(Language.Defaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
suffixes = TOKENIZER_SUFFIXES
lex_attr_getters = LEX_ATTRS
syntax_iterators = SYNTAX_ITERATORS
stop_words = STOP_WORDS
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
class Persian(Language):
lang = "fa"
Defaults = PersianDefaults
@Persian.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={"model": None, "mode": "rule", "lookups": None},
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__ = ["Persian"]