view sat/test/test_plugin_misc_text_syntaxes.py @ 3888:aa7197b67c26

component AP gateway: AP <=> XMPP reactions conversions: - Pubsub Attachments plugin has been renamed to XEP-0470 following publication - XEP-0470 has been updated to follow 0.2 changes - AP reactions (as implemented in Pleroma) are converted to XEP-0470 - XEP-0470 events are converted to AP reactions (again, using "EmojiReact" from Pleroma) - AP activities related to attachments (like/reactions) are cached in Libervia because it's not possible to retrieve them from Pleroma instances once they have been emitted (doing an HTTP get on their ID returns a 404). For now those cache are not flushed, this should be improved in the future. - `sharedInbox` is used when available. Pleroma returns a 500 HTTP error when ``to`` or ``cc`` are used in a direct inbox. - reactions and like are not currently used for direct messages, because they can't be emitted from Pleroma in this case, thus there is no point in implementing them for the moment. rel 371
author Goffi <goffi@goffi.org>
date Wed, 31 Aug 2022 17:07:03 +0200
parents be6d91572633
children 524856bd7b19
line wrap: on
line source

#!/usr/bin/env python3


# SAT: a jabber client
# Copyright (C) 2009-2021 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/>.

""" Plugin text syntaxes tests """

from sat.test import helpers
from sat.plugins import plugin_misc_text_syntaxes
from twisted.trial.unittest import SkipTest
import re
import importlib


class SanitisationTest(helpers.SatTestCase):

    EVIL_HTML1 = """
   <html>
    <head>
      <script type="text/javascript" src="evil-site"></script>
      <link rel="alternate" type="text/rss" src="evil-rss">
      <style>
        body {background-image: url(javascript:do_evil)};
        div {color: expression(evil)};
      </style>
    </head>
    <body onload="evil_function()">
      <!-- I am interpreted for EVIL! -->
      <a href="javascript:evil_function()">a link</a>
      <a href="#" onclick="evil_function()">another link</a>
      <p onclick="evil_function()">a paragraph</p>
      <div style="display: none">secret EVIL!</div>
      <object> of EVIL! </object>
      <iframe src="evil-site"></iframe>
      <form action="evil-site">
        Password: <input type="password" name="password">
      </form>
      <blink>annoying EVIL!</blink>
      <a href="evil-site">spam spam SPAM!</a>
      <image src="evil!">
    </body>
   </html>"""  # example from lxml: /usr/share/doc/python-lxml-doc/html/lxmlhtml.html#cleaning-up-html

    EVIL_HTML2 = """<p style='display: None; test: blah; background: url(: alert()); color: blue;'>test <strong>retest</strong><br><span style="background-color: (alert('bouh')); titi; color: #cf2828; font-size: 3px; direction: !important; color: red; color: red !important; font-size: 100px       !important; font-size: 100px  ! important; font-size: 100%; font-size: 100ox; font-size: 100px; font-size: 100;;;; font-size: 100 %; color: 100 px 1.7em; color: rgba(0, 0, 0, 0.1); color: rgb(35,79,255); background-color: no-repeat; background-color: :alert(1); color: (alert('XSS')); color: (window.location='http://example.org/'); color: url(:window.location='http://example.org/'); "> toto </span></p>"""

    def setUp(self):
        self.host = helpers.FakeSAT()
        importlib.reload(plugin_misc_text_syntaxes)  # reload the plugin to avoid conflict error
        self.text_syntaxes = plugin_misc_text_syntaxes.TextSyntaxes(self.host)

    def test_xhtml_sanitise(self):
        expected = """<div>
      <style>/* deleted */</style>
    <body>
      <a href="">a link</a>
      <a href="#">another link</a>
      <p>a paragraph</p>
      <div style="">secret EVIL!</div>
       of EVIL!
        Password:
      annoying EVIL!
      <a href="evil-site">spam spam SPAM!</a>
      <img src="evil!">
    </img></body>
   </div>"""

        d = self.text_syntaxes.cleanXHTML(self.EVIL_HTML1)
        d.addCallback(self.assertEqualXML, expected, ignore_blank=True)
        return d

    def test_styles_sanitise(self):
        expected = """<p style="color: blue">test <strong>retest</strong><br/><span style="color: #cf2828; font-size: 3px; color: red; color: red !important; font-size: 100px       !important; font-size: 100%; font-size: 100px; font-size: 100; font-size: 100 %; color: rgba(0, 0, 0, 0.1); color: rgb(35,79,255); background-color: no-repeat"> toto </span></p>"""

        d = self.text_syntaxes.cleanXHTML(self.EVIL_HTML2)
        d.addCallback(self.assertEqualXML, expected)
        return d

    def test_html2text(self):
        """Check that html2text is not inserting \n in the middle of that link.
        By default lines are truncated after the 79th characters."""
        source = '<img src="http://sat.goffi.org/static/images/screenshots/libervia/libervia_discussions.png" alt="sat"/>'
        expected = "![sat](http://sat.goffi.org/static/images/screenshots/libervia/libervia_discussions.png)"
        try:
            d = self.text_syntaxes.convert(
                source,
                self.text_syntaxes.SYNTAX_XHTML,
                self.text_syntaxes.SYNTAX_MARKDOWN,
            )
        except plugin_misc_text_syntaxes.UnknownSyntax:
            raise SkipTest("Markdown syntax is not available.")
        d.addCallback(self.assertEqual, expected)
        return d

    def test_removeXHTMLMarkups(self):
        expected = """ a link another link a paragraph secret EVIL! of EVIL! Password: annoying EVIL! spam spam SPAM! """
        result = self.text_syntaxes._removeMarkups(self.EVIL_HTML1)
        self.assertEqual(re.sub(r"\s+", " ", result).rstrip(), expected.rstrip())

        expected = """test retest toto"""
        result = self.text_syntaxes._removeMarkups(self.EVIL_HTML2)
        self.assertEqual(re.sub(r"\s+", " ", result).rstrip(), expected.rstrip())