spaCy/spacy/lang/nb/__init__.py
2020-03-25 08:54:02 +01:00

41 lines
1.2 KiB
Python

# coding: utf8
from __future__ import unicode_literals
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 .morph_rules import MORPH_RULES
from .syntax_iterators import SYNTAX_ITERATORS
from .tag_map import TAG_MAP
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
morph_rules = MORPH_RULES
tag_map = TAG_MAP
syntax_iterators = SYNTAX_ITERATORS
class Norwegian(Language):
lang = "nb"
Defaults = NorwegianDefaults
__all__ = ["Norwegian"]