def get_parser(parser, fmt='html'): if fmt == 'raw': return RawParser() elif fmt == 'text': return TextParser() else: if parser == 'signature': parser_instance = HtmlParser(supported_tags=ONELINE_TAGS_LIST) parser_instance.auto_paragraphs = False return parser_instance elif parser == 'profile': parser_instance = HtmlParser(supported_tags=FULL_TAGS_LIST) parser_instance.add_nofollow = False return parser_instance elif parser == 'blog' or parser == 'full': parser_instance = HtmlParser(supported_tags=FULL_TAGS_LIST) parser_instance.auto_paragraphs = False return parser_instance elif parser == 'news_short': parser_instance = HtmlParser(supported_tags=DEFAULT_TAG_LIST) parser_instance.add_nofollow = False return parser_instance elif parser == 'news_long': parser_instance = HtmlParser(supported_tags=FULL_TAGS_LIST) parser_instance.add_nofollow = False return parser_instance else: return HtmlParser()
def get_parser(editor_type):
if editor_type == 'signature':
supported_tags = copy(ONELINE_TAGS)
supported_tags['a'] = deepcopy(supported_tags['a'])
supported_tags['a'].req_attributes['rel'] = 'nofollow'
supported_tags['a'].attribute_validators = {'rel': [NofollowValidator()]}
parser = HtmlParser(supported_tags = supported_tags)
parser.auto_paragraphs = False
return parser
elif editor_type == 'profile':
supported_tags = copy(DEFAULT_TAGS)
supported_tags['img'] = HtmlTag('img', opt_attributes=['title'], req_attributes={'src': '', 'alt': ''}, empty=True, attribute_validators = {'src': [HrefValidator()]})
supported_tags[''] = deepcopy(supported_tags[''])
supported_tags[''].opt.add('img')
return HtmlParser(supported_tags = supported_tags)
elif editor_type == 'blog':
supported_tags = copy(FULL_TAGS)
supported_tags['a'] = deepcopy(supported_tags['a'])
supported_tags['a'].req_attributes['rel'] = 'nofollow'
supported_tags['a'].attribute_validators = {'rel': [NofollowValidator()]}
parser = HtmlParser(supported_tags=supported_tags)
parser.auto_paragraphs = False
return parser
else:
return HtmlParser()
def get_parser(parser, fmt='html'): #pylint: disable=too-many-return-statements
if fmt == 'raw':
return RawParser()
elif fmt == 'text':
return TextParser()
else:
if parser == 'signature':
supported_tags = copy(ONELINE_TAGS)
supported_tags['a'] = deepcopy(supported_tags['a'])
supported_tags['a'].req_attributes['rel'] = 'nofollow'
supported_tags['a'].attribute_validators = {'rel': [NofollowValidator()]}
parser_instance = HtmlParser(supported_tags=supported_tags)
parser_instance.auto_paragraphs = False
return parser_instance
elif parser == 'profile':
supported_tags = copy(DEFAULT_TAGS)
supported_tags['img'] = HtmlTag('img', opt_attributes=['title'], req_attributes={'src': '', 'alt': ''}, empty=True, attribute_validators={'src': [HrefValidator()]})
supported_tags[''] = deepcopy(supported_tags[''])
supported_tags[''].opt.add('img')
return HtmlParser(supported_tags=supported_tags)
elif parser == 'blog' or parser == 'full':
supported_tags = copy(FULL_TAGS)
supported_tags['a'] = deepcopy(supported_tags['a'])
supported_tags['a'].req_attributes['rel'] = 'nofollow'
supported_tags['a'].attribute_validators = {'rel': [NofollowValidator()]}
parser_instance = HtmlParser(supported_tags=supported_tags)
parser_instance.auto_paragraphs = False
return parser_instance
elif parser == 'news_short':
return HtmlParser()
elif parser == 'news_long':
supported_tags = copy(FULL_TAGS)
parser_instance = HtmlParser(supported_tags=supported_tags)
return parser_instance
else:
return HtmlParser()
def setUp(self): self.parser = HtmlParser() self.parser.auto_paragraphs = True self.parser.add_nofollow = False
class ParserTest(TestCase):
def setUp(self):
self.parser = HtmlParser()
self.parser.auto_paragraphs = True
self.parser.add_nofollow = False
def test_auto_paragraph(self):
code = """Test"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), "<p>" + code + "</p>")
def test_valid_html(self):
code = "<p><strong>Test</strong></p>\n<pre>Tadaaa\n\n</pre><p>Text</p>"
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), "<p><strong>Test</strong></p>\n<pre>Tadaaa\n\n</pre><p>Text</p>")
def test_opened_tag(self):
code = """<p>Test"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), code + "</p>")
def test_opened_nested_tag(self):
code = """<p><strong>Test</p>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), code[:-4] + "</strong></p>")
def test_unknown_tag(self):
code = """<xxx>Test</xxx>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), '<p>' + code.replace('<', '<').replace('>', '>') + '</p>')
def test_attribute(self):
code = """<p><a href="#test">Test</a></p>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), code)
def test_missing_attribute(self):
code = """<p><a>Test</a></p>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), """<p><a href="#">Test</a></p>""")
def test_malicious_href(self):
code = """<p><a href="javascript:alert('XSS')">Test</a></p>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), """<p><a href="#">Test</a></p>""")
def test_signature_nofollow(self):
code = """<a href="http://www.linuxos.sk">Test</a>"""
parser = get_parser('signature')
parser.parse(code)
self.assertEqual(parser.get_output(), """<a href="http://www.linuxos.sk" rel="nofollow">Test</a>""")
def test_signature_bad_nofollow(self):
code = """<a href="http://www.linuxos.sk" rel="follow">Test</a>"""
parser = get_parser('signature')
parser.parse(code)
self.assertEqual(parser.get_output(), """<a href="http://www.linuxos.sk" rel="nofollow">Test</a>""")
def test_profile_parser(self):
code = """<p><img alt="" src="http://www.linuxos.sk/img.png"></p>"""
parser = get_parser('profile')
parser.parse(code)
self.assertEqual(parser.get_output(), code)
def test_auto_paragraphs(self):
code = "Paragraph1\n\nParagraph2"
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), "<p>Paragraph1</p>\n\n<p>Paragraph2</p>")
def test_auto_paragraphs_between(self):
code = "<blockquote>BQ</blockquote>Paragraph"
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), "<blockquote>BQ</blockquote><p>Paragraph</p>")
def test_attr_entity(self):
code = """<p><a href="http://linuxos.sk/a&b">Test</a></p>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), """<p><a href="http://linuxos.sk/a&b">Test</a></p>""")
def test_code_class(self):
code = """<pre class="code-cpp">cpp</pre>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), """<pre class="code-cpp">cpp</pre>""")
code = """<pre class="wrong">wrong</pre>"""
self.parser.parse(code)
self.assertEqual(self.parser.get_output(), """<pre>wrong</pre>""")
def setUp(self): self.parser = HtmlParser() self.parser.auto_paragraphs = True
