spaCy/spacy/lang/es/__init__.py
2020-07-22 15:59:37 +02:00

59 lines
1.5 KiB
Python

from typing import Set, Dict, Callable, Any
from thinc.config import Config
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
from ...util import update_exc, registry
DEFAULT_CONFIG = """
[nlp]
lang = "es"
stop_words = {"@language_data": "spacy.es.stop_words"}
lex_attr_getters = {"@language_data": "spacy.es.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_cluster", "lexeme_prob", "lexeme_settings"]
"""
@registry.language_data("spacy.es.stop_words")
def stop_words() -> Set[str]:
return STOP_WORDS
@registry.language_data("spacy.es.lex_attr_getters")
def lex_attr_getters() -> Dict[int, Callable[[str], Any]]:
return LEX_ATTRS
class SpanishDefaults(Language.Defaults):
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
syntax_iterators = SYNTAX_ITERATORS
class Spanish(Language):
lang = "es"
Defaults = SpanishDefaults
default_config = Config().from_str(DEFAULT_CONFIG)
__all__ = ["Spanish"]