mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
b10c7bc56e
* Update stop_words.py Hebrew STOP WORDS * Update stop_words.py * contributor * contributor * add some common domain extentions support human number 1K/1M.... * support human number 1K/1M.... * hebrew number tokenize 1K/1M implement in EN * test human tokenize fix * test * heb like num revert human number change * heb like num
28 lines
719 B
Python
28 lines
719 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
from ...util import update_exc
|
|
|
|
|
|
class HebrewDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "he"
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
|
|
|
|
|
|
class Hebrew(Language):
|
|
lang = "he"
|
|
Defaults = HebrewDefaults
|
|
|
|
|
|
__all__ = ["Hebrew"]
|