spaCy/spacy/lang/pl/__init__.py

44 lines
1.3 KiB
Python
Raw Normal View History

from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .punctuation import TOKENIZER_SUFFIXES
2017-05-12 07:25:37 +00:00
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .lemmatizer import PolishLemmatizer
2017-05-12 07:25:37 +00:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
2017-05-12 07:25:37 +00:00
from ...language import Language
from ...attrs import LANG, NORM
2020-05-21 12:14:01 +00:00
from ...util import add_lookups
from ...lookups import Lookups
2017-05-12 07:25:37 +00:00
class PolishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: "pl"
lex_attr_getters[NORM] = add_lookups(
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
)
mod_base_exceptions = {
exc: val for exc, val in BASE_EXCEPTIONS.items() if not exc.endswith(".")
}
tokenizer_exceptions = mod_base_exceptions
stop_words = STOP_WORDS
prefixes = TOKENIZER_PREFIXES
2019-02-08 13:14:49 +00:00
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
2017-05-12 07:25:37 +00:00
@classmethod
def create_lemmatizer(cls, nlp=None, lookups=None):
if lookups is None:
lookups = Lookups()
return PolishLemmatizer(lookups)
2017-05-12 07:25:37 +00:00
class Polish(Language):
lang = "pl"
Defaults = PolishDefaults
2017-05-12 07:25:37 +00:00
__all__ = ["Polish"]