mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
32 lines
987 B
Python
32 lines
987 B
Python
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_SUFFIXES
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
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
|
|
|
|
|
|
class ArabicDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "ar"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
|
|
|
|
|
|
class Arabic(Language):
|
|
lang = "ar"
|
|
Defaults = ArabicDefaults
|
|
|
|
|
|
__all__ = ["Arabic"]
|