1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
175
176
177
178
179
180
181
182
183
184
|
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import os
from datetime import datetime
from unittest import TestCase
from django.test import ignore_warnings
from django.utils import html, safestring
from django.utils._os import upath
from django.utils.deprecation import RemovedInDjango20Warning
from django.utils.encoding import force_text
class TestUtilsHtml(TestCase):
def check_output(self, function, value, output=None):
"""
Check that function(value) equals output. If output is None,
check that function(value) equals value.
"""
if output is None:
output = value
self.assertEqual(function(value), output)
def test_escape(self):
f = html.escape
items = (
('&', '&'),
('<', '<'),
('>', '>'),
('"', '"'),
("'", '''),
)
# Substitution patterns for testing the above items.
patterns = ("%s", "asdf%sfdsa", "%s1", "1%sb")
for value, output in items:
for pattern in patterns:
self.check_output(f, pattern % value, pattern % output)
# Check repeated values.
self.check_output(f, value * 2, output * 2)
# Verify it doesn't double replace &.
self.check_output(f, '<&', '<&')
def test_format_html(self):
self.assertEqual(
html.format_html("{} {} {third} {fourth}",
"< Dangerous >",
html.mark_safe("<b>safe</b>"),
third="< dangerous again",
fourth=html.mark_safe("<i>safe again</i>")
),
"< Dangerous > <b>safe</b> < dangerous again <i>safe again</i>"
)
def test_linebreaks(self):
f = html.linebreaks
items = (
("para1\n\npara2\r\rpara3", "<p>para1</p>\n\n<p>para2</p>\n\n<p>para3</p>"),
("para1\nsub1\rsub2\n\npara2", "<p>para1<br />sub1<br />sub2</p>\n\n<p>para2</p>"),
("para1\r\n\r\npara2\rsub1\r\rpara4", "<p>para1</p>\n\n<p>para2<br />sub1</p>\n\n<p>para4</p>"),
("para1\tmore\n\npara2", "<p>para1\tmore</p>\n\n<p>para2</p>"),
)
for value, output in items:
self.check_output(f, value, output)
def test_strip_tags(self):
f = html.strip_tags
items = (
('<p>See: 'é is an apostrophe followed by e acute</p>',
'See: 'é is an apostrophe followed by e acute'),
('<adf>a', 'a'),
('</adf>a', 'a'),
('<asdf><asdf>e', 'e'),
('hi, <f x', 'hi, <f x'),
('234<235, right?', '234<235, right?'),
('a4<a5 right?', 'a4<a5 right?'),
('b7>b2!', 'b7>b2!'),
('</fe', '</fe'),
('<x>b<y>', 'b'),
('a<p onclick="alert(\'<test>\')">b</p>c', 'abc'),
('a<p a >b</p>c', 'abc'),
('d<a:b c:d>e</p>f', 'def'),
('<strong>foo</strong><a href="http://example.com">bar</a>', 'foobar'),
)
for value, output in items:
self.check_output(f, value, output)
# Some convoluted syntax for which parsing may differ between python versions
output = html.strip_tags('<sc<!-- -->ript>test<<!-- -->/script>')
self.assertNotIn('<script>', output)
self.assertIn('test', output)
output = html.strip_tags('<script>alert()</script>&h')
self.assertNotIn('<script>', output)
self.assertIn('alert()', output)
# Test with more lengthy content (also catching performance regressions)
for filename in ('strip_tags1.html', 'strip_tags2.txt'):
path = os.path.join(os.path.dirname(upath(__file__)), 'files', filename)
with open(path, 'r') as fp:
content = force_text(fp.read())
start = datetime.now()
stripped = html.strip_tags(content)
elapsed = datetime.now() - start
self.assertEqual(elapsed.seconds, 0)
self.assertIn("Please try again.", stripped)
self.assertNotIn('<', stripped)
def test_strip_spaces_between_tags(self):
f = html.strip_spaces_between_tags
# Strings that should come out untouched.
items = (' <adf>', '<adf> ', ' </adf> ', ' <f> x</f>')
for value in items:
self.check_output(f, value)
# Strings that have spaces to strip.
items = (
('<d> </d>', '<d></d>'),
('<p>hello </p>\n<p> world</p>', '<p>hello </p><p> world</p>'),
('\n<p>\t</p>\n<p> </p>\n', '\n<p></p><p></p>\n'),
)
for value, output in items:
self.check_output(f, value, output)
@ignore_warnings(category=RemovedInDjango20Warning)
def test_strip_entities(self):
f = html.strip_entities
# Strings that should come out untouched.
values = ("&", "&a", "&a", "a&#a")
for value in values:
self.check_output(f, value)
# Valid entities that should be stripped from the patterns.
entities = ("", "", "&a;", "&fdasdfasdfasdf;")
patterns = (
("asdf %(entity)s ", "asdf "),
("%(entity)s%(entity)s", ""),
("&%(entity)s%(entity)s", "&"),
("%(entity)s3", "3"),
)
for entity in entities:
for in_pattern, output in patterns:
self.check_output(f, in_pattern % {'entity': entity}, output)
def test_escapejs(self):
f = html.escapejs
items = (
('"double quotes" and \'single quotes\'', '\\u0022double quotes\\u0022 and \\u0027single quotes\\u0027'),
(r'\ : backslashes, too', '\\u005C : backslashes, too'),
('and lots of whitespace: \r\n\t\v\f\b', 'and lots of whitespace: \\u000D\\u000A\\u0009\\u000B\\u000C\\u0008'),
(r'<script>and this</script>', '\\u003Cscript\\u003Eand this\\u003C/script\\u003E'),
('paragraph separator:\u2029and line separator:\u2028', 'paragraph separator:\\u2029and line separator:\\u2028'),
)
for value, output in items:
self.check_output(f, value, output)
@ignore_warnings(category=RemovedInDjango20Warning)
def test_remove_tags(self):
f = html.remove_tags
items = (
("<b><i>Yes</i></b>", "b i", "Yes"),
("<a>x</a> <p><b>y</b></p>", "a b", "x <p>y</p>"),
)
for value, tags, output in items:
self.assertEqual(f(value, tags), output)
def test_smart_urlquote(self):
quote = html.smart_urlquote
# Ensure that IDNs are properly quoted
self.assertEqual(quote('http://öäü.com/'), 'http://xn--4ca9at.com/')
self.assertEqual(quote('http://öäü.com/öäü/'), 'http://xn--4ca9at.com/%C3%B6%C3%A4%C3%BC/')
# Ensure that everything unsafe is quoted, !*'();:@&=+$,/?#[]~ is considered safe as per RFC
self.assertEqual(quote('http://example.com/path/öäü/'), 'http://example.com/path/%C3%B6%C3%A4%C3%BC/')
self.assertEqual(quote('http://example.com/%C3%B6/ä/'), 'http://example.com/%C3%B6/%C3%A4/')
self.assertEqual(quote('http://example.com/?x=1&y=2+3&z='), 'http://example.com/?x=1&y=2+3&z=')
self.assertEqual(quote('http://example.com/?x=<>"\''), 'http://example.com/?x=%3C%3E%22%27')
self.assertEqual(quote('http://example.com/?q=http://example.com/?x=1%26q=django'),
'http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango')
self.assertEqual(quote('http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango'),
'http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango')
def test_conditional_escape(self):
s = '<h1>interop</h1>'
self.assertEqual(html.conditional_escape(s),
'<h1>interop</h1>')
self.assertEqual(html.conditional_escape(safestring.mark_safe(s)), s)
|
