Files
wehub-resource-sync f877c37fc6
tests / Test (macos-latest, 3.14) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.10) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.13) (push) Has been cancelled
tests / Test (windows-latest, 3.14) (push) Has been cancelled
tests / Validate (push) Has been cancelled
tests / Test (macos-latest, 3.10) (push) Has been cancelled
tests / Test (macos-latest, 3.11) (push) Has been cancelled
tests / Test (macos-latest, 3.12) (push) Has been cancelled
tests / Test (macos-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.12) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.14) (push) Has been cancelled
tests / Test (windows-latest, 3.10) (push) Has been cancelled
tests / Test (windows-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.12) (push) Has been cancelled
universe validation / Validate (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:37:51 +08:00

22 lines
572 B
Python

from ...language import BaseDefaults, Language
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class ArabicDefaults(BaseDefaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
suffixes = TOKENIZER_SUFFIXES
stop_words = STOP_WORDS
lex_attr_getters = LEX_ATTRS
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
class Arabic(Language):
Defaults = ArabicDefaults
lang = "ar"
__all__ = ["Arabic"]