view frontends/src/tools/strings.py @ 832:c4b22aedb7d7

plugin groupblog, XEP-0071, XEP-0277, text_syntaxes: manage raw/rich/xhtml data for content/title: Implementation should follow the following formal specification: "title" and "content" data can be passed in raw, xhtml or rich format. When we receive from a frontend a new/updated microblog item: - keys "title" or "content" have to be escaped (disable HTML tags) - keys "title_rich" or "content_rich" have to be converted from the current syntax to XHTML - keys "title_xhtml" or "content_xhtml" have to be cleaned from unwanted XHTML content Rules to deal with concurrent keys: - existence of both "*_xhtml" and "*_rich" keys must raise an exception - existence of both raw and ("*_xhtml" or "*_rich") is OK As the storage always need raw data, if it is not given by the user it can be extracted from the "*_rich" or "*_xhtml" data (remove the XHTML tags). When a frontend wants to edit a blog post that contains XHTML title or content, the conversion is made from XHTML to the current user-defined syntax. - plugin text_syntaxes: added "text" syntax (using lxml)
author souliane <souliane@mailoo.org>
date Wed, 05 Feb 2014 16:36:51 +0100
parents 1fe00f0c9a91
children 429c6a0ef73d
line wrap: on
line source

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

# SAT helpers methods for plugins
# Copyright (C) 2013, 2014 Adrien Cossa (souliane@mailoo.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/>.

import re


def getURLParams(url):
    """This comes from pyjamas.Location.makeUrlDict with a small change
    to also parse full URLs, and parameters with no value specified
    (in that case the default value "" is used).
    @param url: any URL with or without parameters
    @return: a dictionary of the parameters, if any was given, or {}
    """
    dict_ = {}
    if "/" in url:
        # keep the part after the last "/"
        url = url[url.rindex("/") + 1:]
    if url.startswith("?"):
        # remove the first "?"
        url = url[1:]
    pairs = url.split("&")
    for pair in pairs:
        if len(pair) < 3:
            continue
        kv = pair.split("=", 1)
        dict_[kv[0]] = kv[1] if len(kv) > 1 else ""
    return dict_


def addURLToText(string):
    """Check a text for what looks like an URL and make it clickable. Regexp
    from http://daringfireball.net/2010/07/improved_regex_for_matching_urls"""

    def repl(match):
        url = match.group(0)
        if not re.match(r"""[a-z]{3,}://|mailto:|xmpp:""", url):
            url = "http://" + url
        return '<a href="%s" target="_blank" class="url">%s</a>' % (url, match.group(0))
    pattern = r"""(?i)\b((?:[a-z]{3,}://|(www|ftp)\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/|mailto:|xmpp:)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'".,<>?]))"""
    return re.sub(pattern, repl, string)