mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
b64243ed55
* Added examples for Slovene * Update spacy/lang/sl/examples.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * Corrected a typo in one of the sentences * Updated support for Slovenian * Some minor changes to corrections * Added forint currency * Corrected HYPHENS_PERMITTED regex and some formatting * Minor changes * Un-xfail tokenizer test * Format Co-authored-by: Luka Dragar <D20124481@mytudublin.ie> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
23 lines
607 B
Python
23 lines
607 B
Python
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from ...language import Language, BaseDefaults
|
|
|
|
|
|
class SlovenianDefaults(BaseDefaults):
|
|
stop_words = STOP_WORDS
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
lex_attr_getters = LEX_ATTRS
|
|
|
|
|
|
class Slovenian(Language):
|
|
lang = "sl"
|
|
Defaults = SlovenianDefaults
|
|
|
|
|
|
__all__ = ["Slovenian"]
|