view src/tools/utils.py @ 615:6f4c31192c7c

plugins XEP-0060, XEP-0277, groupblog: comments implementation (first draft, not finished yet): - PubSub options constants are moved to XEP-0060 - comments url are generated/parsed according to XEP-0277 - microblog data can now have the following keys: - "comments", with the url as given in the <link> tag - "comments_service", with the jid of the PubSub service hosting the comments - "comments_node", with the parsed node - comments nodes use different access_model according to parent microblog item access - publisher is not verified yet, see FIXME warning - so far, comments node are automatically subscribed - some bug fixes
author Goffi <goffi@goffi.org>
date Mon, 20 May 2013 23:21:29 +0200
parents 84a6e83157c2
children 1fe00f0c9a91
line wrap: on
line source

#!/usr/bin/python
# -*- coding: utf-8 -*-

# SAT: a jabber client
# Copyright (C) 2009, 2010, 2011, 2012, 2013  Jérôme Poisson (goffi@goffi.org)

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.

# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

""" various useful methods """

import unicodedata
    
    
def clean_ustr(ustr):
    """Clean unicode string
    remove special characters from unicode string"""
    def valid_chars(unicode_source):
        for char in unicode_source:
            if unicodedata.category(char) == 'Cc' and char!='\n':
                continue
            yield char
    return ''.join(valid_chars(ustr))