from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES from .punctuation import TOKENIZER_SUFFIXES from .stop_words import STOP_WORDS from .syntax_iterators import SYNTAX_ITERATORS 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 NorwegianDefaults(Language.Defaults): lex_attr_getters = dict(Language.Defaults.lex_attr_getters) lex_attr_getters[LANG] = lambda text: "nb" lex_attr_getters[NORM] = add_lookups( Language.Defaults.lex_attr_getters[NORM], BASE_NORMS ) tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) prefixes = TOKENIZER_PREFIXES infixes = TOKENIZER_INFIXES suffixes = TOKENIZER_SUFFIXES stop_words = STOP_WORDS syntax_iterators = SYNTAX_ITERATORS class Norwegian(Language): lang = "nb" Defaults = NorwegianDefaults __all__ = ["Norwegian"]