mirror of
https://github.com/explosion/spaCy.git
synced 2025-02-03 05:04:09 +03:00
d83e3c44c5
* Remove corpus-specific morph rules * Add options similar to tag maps to provide them in the `train` and `debug-data` CLIs
28 lines
787 B
Python
28 lines
787 B
Python
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
from ...util import update_exc
|
|
|
|
|
|
class DanishDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "da"
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Danish(Language):
|
|
lang = "da"
|
|
Defaults = DanishDefaults
|
|
|
|
|
|
__all__ = ["Danish"]
|