mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +03:00
d83e3c44c5
* Remove corpus-specific morph rules * Add options similar to tag maps to provide them in the `train` and `debug-data` CLIs
41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
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
|
|
|
|
|
|
def _return_lt(_):
|
|
return "lt"
|
|
|
|
|
|
class LithuanianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = _return_lt
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
mod_base_exceptions = {
|
|
exc: val for exc, val in BASE_EXCEPTIONS.items() if not exc.endswith(".")
|
|
}
|
|
del mod_base_exceptions["8)"]
|
|
tokenizer_exceptions = update_exc(mod_base_exceptions, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Lithuanian(Language):
|
|
lang = "lt"
|
|
Defaults = LithuanianDefaults
|
|
|
|
|
|
__all__ = ["Lithuanian"]
|