from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .punctuation import TOKENIZER_INFIXES from .tag_map import TAG_MAP from .stop_words import STOP_WORDS from .lex_attrs import LEX_ATTRS from ..tokenizer_exceptions import BASE_EXCEPTIONS from ..norm_exceptions import BASE_NORMS from ...language import Language from ...attrs import LANG, NORM from ...util import update_exc, add_lookups 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 ) tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) stop_words = STOP_WORDS tag_map = TAG_MAP infixes = TOKENIZER_INFIXES class Polish(Language): lang = "pl" Defaults = PolishDefaults __all__ = ["Polish"]