Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Reorganise Hebrew language data

This commit is contained in:
ines 2017-05-08 15:49:28 +02:00
parent 7f05e977fa
commit a77c9fc60d
2 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/he/__init__.py
View File

@ -1,10 +1,12 @@
# encoding: utf8 # coding: utf8
from __future__ import unicode_literals, print_function from __future__ import unicode_literals
from .stop_words import STOP_WORDS
from ..language_data import BASE_EXCEPTIONS
from ..language import Language from ..language import Language
from ..attrs import LANG from ..attrs import LANG
from ..util import update_exc
from .language_data import *
class Hebrew(Language): class Hebrew(Language):
@ -14,8 +16,8 @@ class Hebrew(Language):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters) lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'he' lex_attr_getters[LANG] = lambda text: 'he'
tokenizer_exceptions = TOKENIZER_EXCEPTIONS tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = STOP_WORDS stop_words = set(STOP_WORDS)
EXPORT = Hebrew __all__ = ['Hebrew']

1
spacy/he/stop_words.py
View File

@ -1,6 +1,7 @@
# encoding: utf8 # encoding: utf8
from __future__ import unicode_literals from __future__ import unicode_literals
STOP_WORDS = set(""" STOP_WORDS = set("""
אני אני
את את