spaCy/spacy/lang/ar/__init__.py

# coding: utf8
from __future__ import unicode_literals

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"]