spaCy/spacy/lang/da/__init__.py

36 lines
1.1 KiB
Python
Raw Normal View History

2017-05-10 19:15:12 +00:00
# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
2017-05-10 19:15:12 +00:00
from .stop_words import STOP_WORDS
2017-07-03 13:45:31 +00:00
from .lex_attrs import LEX_ATTRS
2017-07-03 13:49:09 +00:00
from .morph_rules import MORPH_RULES
2017-07-03 13:51:58 +00:00
from ..tag_map import TAG_MAP
2017-05-10 19:15:12 +00:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
2017-05-10 19:15:12 +00:00
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2017-05-10 19:15:12 +00:00
class DanishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
2017-07-03 13:45:31 +00:00
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: 'da'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
BASE_NORMS, NORM_EXCEPTIONS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
# morph_rules = MORPH_RULES
tag_map = TAG_MAP
stop_words = STOP_WORDS
2017-05-10 19:15:12 +00:00
class Danish(Language):
lang = 'da'
Defaults = DanishDefaults
2017-05-10 19:15:12 +00:00
__all__ = ['Danish']