#!/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 . """ 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 = """ a link another link

a paragraph

secret EVIL!
of EVIL!
Password:
annoying EVIL! spam spam SPAM! """ # example from lxml: /usr/share/doc/python-lxml-doc/html/lxmlhtml.html#cleaning-up-html EVIL_HTML2 = """

test retest
toto

""" 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 = """
a link another link

a paragraph

secret EVIL!
of EVIL! Password: annoying EVIL! spam spam SPAM!
""" d = self.text_syntaxes.cleanXHTML(self.EVIL_HTML1) d.addCallback(self.assertEqualXML, expected, ignore_blank=True) return d def test_styles_sanitise(self): expected = """

test retest
toto

""" 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 = '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())