spaCy/spacy/lang/lb/__init__.py

56 lines
1.3 KiB
Python

from typing import Set, Dict, Callable, Any
from thinc.api import Config
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES
from .lex_attrs import LEX_ATTRS
from .stop_words import STOP_WORDS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
from ...util import update_exc, registry
DEFAULT_CONFIG = """
[nlp]
lang = "lb"
stop_words = {"@language_data": "spacy.lb.stop_words"}
lex_attr_getters = {"@language_data": "spacy.lb.lex_attr_getters"}
[nlp.lemmatizer]
@lemmatizers = "spacy.Lemmatizer.v1"
[nlp.lemmatizer.data]
@language_data = "spacy-lookups-data"
lang = ${nlp:lang}
tables = ["lemma_lookup"]
[nlp.vocab_data]
@language_data = "spacy-lookups-data"
lang = ${nlp:lang}
tables = ["lexeme_norm"]
"""
@registry.language_data("spacy.lb.stop_words")
def stop_words() -> Set[str]:
return STOP_WORDS
@registry.language_data("spacy.lb.lex_attr_getters")
def lex_attr_getters() -> Dict[int, Callable[[str], Any]]:
return LEX_ATTRS
class LuxembourgishDefaults(Language.Defaults):
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
infixes = TOKENIZER_INFIXES
class Luxembourgish(Language):
lang = "lb"
Defaults = LuxembourgishDefaults
default_config = Config().from_str(DEFAULT_CONFIG)
__all__ = ["Luxembourgish"]