html5lib-python/html5lib/tests/test_sanitizer.py at master · lixkel/html5lib-python · GitHub

History

174 lines (135 loc) · 6.64 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

from __future__ import absolute_import, division, unicode_literals

import warnings

import pytest

from html5lib import constants, parseFragment, serialize

with warnings.catch_warnings():

warnings.simplefilter("ignore", DeprecationWarning)

from html5lib.filters import sanitizer

def sanitize_html(stream):

parsed = parseFragment(stream)

with pytest.deprecated_call():

serialized = serialize(parsed,

sanitize=True,

omit_optional_tags=False,

use_trailing_solidus=True,

space_before_trailing_solidus=False,

quote_attr_values="always",

quote_char='"',

alphabetical_attributes=True)

return serialized

def test_should_handle_astral_plane_characters():

sanitized = sanitize_html("𝒵 𝔸")

expected = '\U0001d4b5 \U0001d538'

assert expected == sanitized

def test_should_allow_relative_uris():

sanitized = sanitize_html('<a href="/example.com"></a>')

expected = '<a href="/example.com"></a>'

assert expected == sanitized

def test_invalid_data_uri():

sanitized = sanitize_html('<audio controls="" src="data:foobar"></audio>')

expected = '<audio controls></audio>'

assert expected == sanitized

def test_invalid_ipv6_url():

sanitized = sanitize_html('<a href="h://]">')

expected = "<a></a>"

assert expected == sanitized

def test_data_uri_disallowed_type():

sanitized = sanitize_html('<audio controls="" src="data:text/html,<html>"></audio>')

expected = "<audio controls></audio>"

assert expected == sanitized

def test_wbr_allowed():

sanitized = sanitize_html('')

expected = ''

assert expected == sanitized

def param_sanitizer():

for ns, tag_name in sanitizer.allowed_elements:

if ns != constants.namespaces["html"]:

continue

if tag_name in ['caption', 'col', 'colgroup', 'optgroup', 'option', 'table', 'tbody', 'td',

'tfoot', 'th', 'thead', 'tr', 'select']:

continue # TODO

if tag_name == 'image':

yield ("test_should_allow_%s_tag" % tag_name,

"<img title=\"1\"/>foo <bad>bar</bad> baz",

"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))

elif tag_name == 'br':

yield ("test_should_allow_%s_tag" % tag_name,

" foo <bad>bar</bad> baz ",

"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))

elif tag_name in constants.voidElements:

yield ("test_should_allow_%s_tag" % tag_name,

"<%s title=\"1\"/>foo <bad>bar</bad> baz" % tag_name,

"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))

else:

yield ("test_should_allow_%s_tag" % tag_name,

"<%s title=\"1\">foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name),

"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))

for ns, attribute_name in sanitizer.allowed_attributes:

if ns is not None:

continue

if attribute_name != attribute_name.lower():

continue # TODO

if attribute_name == 'style':

continue

attribute_value = 'foo'

if attribute_name in sanitizer.attr_val_is_uri:

attribute_value = '%s://sub.domain.tld/path/object.ext' % sanitizer.allowed_protocols[0]

yield ("test_should_allow_%s_attribute" % attribute_name,

"foo <bad>bar</bad> baz" % (attribute_name, attribute_value),

"foo <bad>bar</bad> baz" % (attribute_name, attribute_value))

for protocol in sanitizer.allowed_protocols:

rest_of_uri = '//sub.domain.tld/path/object.ext'

if protocol == 'data':

rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='

yield ("test_should_allow_uppercase_%s_uris" % protocol,

"<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),

"""<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))

for protocol in sanitizer.allowed_protocols:

rest_of_uri = '//sub.domain.tld/path/object.ext'

if protocol == 'data':

rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='

protocol = protocol.upper()

yield ("test_should_allow_uppercase_%s_uris" % protocol,

"<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),

"""<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))

def test_details_open_allowed():

sanitized = sanitize_html("<details open>.</details>")

expected = '<details open>.</details>'

assert expected == sanitized

def test_details_summary_allowed():

sanitized = sanitize_html("<details><summary>.</summary>...</details>")

expected = '<details><summary>.</summary>...</details>'

assert expected == sanitized

@pytest.mark.parametrize("expected, input",

(pytest.param(expected, input, id=id)

for id, expected, input in param_sanitizer()))

def test_sanitizer(expected, input):

parsed = parseFragment(expected)

expected = serialize(parsed,

omit_optional_tags=False,

use_trailing_solidus=True,

space_before_trailing_solidus=False,

quote_attr_values="always",

quote_char='"',

alphabetical_attributes=True)

assert expected == sanitize_html(input)

def test_lowercase_color_codes_in_style():

sanitized = sanitize_html("")

expected = ''

assert expected == sanitized

def test_uppercase_color_codes_in_style():

sanitized = sanitize_html("")

expected = ''

assert expected == sanitized

def test_ol_start_allowed():

sanitized = sanitize_html("<ol start=2><li>.</ol>")

expected = '<ol start="2"><li>.</li></ol>'

assert expected == sanitized

def test_ol_type_allowed():

sanitized = sanitize_html("<ol type=I><li>.</ol>")

expected = '<ol type="I"><li>.</li></ol>'

assert expected == sanitized

def test_ol_reversed_allowed():

sanitized = sanitize_html("<ol reversed><li>.</ol>")

expected = '<ol reversed><li>.</li></ol>'

assert expected == sanitized

html5lib-python/html5lib/tests/test_sanitizer.py at master · lixkel/html5lib-python · GitHub

Expand file tree

Breadcrumbs

test_sanitizer.py

Latest commit

History

Breadcrumbs

test_sanitizer.py

File metadata and controls