-
-
Save dimidd/fe0cb84d406648dc1365 to your computer and use it in GitHub Desktop.
Pasted from IPython
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pymongo | |
cl = pymongo.MongoClient() | |
db = cl.ner-dict | |
db = cl['ner-dict'] | |
c = db.dict | |
c.count | |
c.count() | |
qs = c.find() | |
aliases = [bytes(x, 'latin1').decode('utf8') for x in r['aliases']] | |
aliases | |
Out[26]: | |
['Herzl, Theodor,', | |
'הרצל, בנימין זאב,', | |
'Герцль, Теодор,', | |
'هرصل، بنيامين زئيب', | |
'הרצל, בנימין זאב', | |
'Herzl, Benjamin Zeev', | |
'Herzl, Tivadar,', | |
'Herzl, Teodoro', | |
'הרצל, תאודור', | |
'הערצל, בנימין זאב,', | |
'הערצעל, בנימין זאב,', | |
'Херцл, Теодор,', | |
'Херцел, Теодор,', | |
'هرتزل، بنيامين زئيب', | |
'هرصل، ثيودور', | |
'هرتسل، ثيودور', | |
'هيرتسل، ثيودور', | |
'هرتزل، ثيودور', | |
'הרצל, תיאודור', | |
'הרצל, מתתיהו', | |
'הירצל, תיאודור', | |
'הערצל, תיאודור', | |
'הרצל, בנימין זאב בן יעקב'] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment