mirror of https://github.com/explosion/spaCy.git
Reorganise Hebrew language data
This commit is contained in:
parent
7f05e977fa
commit
a77c9fc60d
|
@ -1,10 +1,12 @@
|
|||
# encoding: utf8
|
||||
from __future__ import unicode_literals, print_function
|
||||
# coding: utf8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .stop_words import STOP_WORDS
|
||||
|
||||
from ..language_data import BASE_EXCEPTIONS
|
||||
from ..language import Language
|
||||
from ..attrs import LANG
|
||||
|
||||
from .language_data import *
|
||||
from ..util import update_exc
|
||||
|
||||
|
||||
class Hebrew(Language):
|
||||
|
@ -14,8 +16,8 @@ class Hebrew(Language):
|
|||
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
||||
lex_attr_getters[LANG] = lambda text: 'he'
|
||||
|
||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||
stop_words = STOP_WORDS
|
||||
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
|
||||
stop_words = set(STOP_WORDS)
|
||||
|
||||
|
||||
EXPORT = Hebrew
|
||||
__all__ = ['Hebrew']
|
||||
|
|
|
@ -1,6 +1,7 @@
|
|||
# encoding: utf8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
|
||||
STOP_WORDS = set("""
|
||||
אני
|
||||
את
|
||||
|
|
Loading…
Reference in New Issue