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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
#!/usr/bin/env python
from __future__ import absolute_import, division, with_statement
import tornado.escape
import unittest
from tornado.escape import utf8, xhtml_escape, xhtml_unescape, url_escape, url_unescape, to_unicode, json_decode, json_encode
from tornado.util import b
linkify_tests = [
# (input, linkify_kwargs, expected_output)
("hello http://world.com/!", {},
u'hello <a href="http://world.com/">http://world.com/</a>!'),
("hello http://world.com/with?param=true&stuff=yes", {},
u'hello <a href="http://world.com/with?param=true&stuff=yes">http://world.com/with?param=true&stuff=yes</a>'),
# an opened paren followed by many chars killed Gruber's regex
("http://url.com/w(aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa", {},
u'<a href="http://url.com/w">http://url.com/w</a>(aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'),
# as did too many dots at the end
("http://url.com/withmany.......................................", {},
u'<a href="http://url.com/withmany">http://url.com/withmany</a>.......................................'),
("http://url.com/withmany((((((((((((((((((((((((((((((((((a)", {},
u'<a href="http://url.com/withmany">http://url.com/withmany</a>((((((((((((((((((((((((((((((((((a)'),
# some examples from http://daringfireball.net/2009/11/liberal_regex_for_matching_urls
# plus a fex extras (such as multiple parentheses).
("http://foo.com/blah_blah", {},
u'<a href="http://foo.com/blah_blah">http://foo.com/blah_blah</a>'),
("http://foo.com/blah_blah/", {},
u'<a href="http://foo.com/blah_blah/">http://foo.com/blah_blah/</a>'),
("(Something like http://foo.com/blah_blah)", {},
u'(Something like <a href="http://foo.com/blah_blah">http://foo.com/blah_blah</a>)'),
("http://foo.com/blah_blah_(wikipedia)", {},
u'<a href="http://foo.com/blah_blah_(wikipedia)">http://foo.com/blah_blah_(wikipedia)</a>'),
("http://foo.com/blah_(blah)_(wikipedia)_blah", {},
u'<a href="http://foo.com/blah_(blah)_(wikipedia)_blah">http://foo.com/blah_(blah)_(wikipedia)_blah</a>'),
("(Something like http://foo.com/blah_blah_(wikipedia))", {},
u'(Something like <a href="http://foo.com/blah_blah_(wikipedia)">http://foo.com/blah_blah_(wikipedia)</a>)'),
("http://foo.com/blah_blah.", {},
u'<a href="http://foo.com/blah_blah">http://foo.com/blah_blah</a>.'),
("http://foo.com/blah_blah/.", {},
u'<a href="http://foo.com/blah_blah/">http://foo.com/blah_blah/</a>.'),
("<http://foo.com/blah_blah>", {},
u'<<a href="http://foo.com/blah_blah">http://foo.com/blah_blah</a>>'),
("<http://foo.com/blah_blah/>", {},
u'<<a href="http://foo.com/blah_blah/">http://foo.com/blah_blah/</a>>'),
("http://foo.com/blah_blah,", {},
u'<a href="http://foo.com/blah_blah">http://foo.com/blah_blah</a>,'),
("http://www.example.com/wpstyle/?p=364.", {},
u'<a href="http://www.example.com/wpstyle/?p=364">http://www.example.com/wpstyle/?p=364</a>.'),
("rdar://1234",
{"permitted_protocols": ["http", "rdar"]},
u'<a href="rdar://1234">rdar://1234</a>'),
("rdar:/1234",
{"permitted_protocols": ["rdar"]},
u'<a href="rdar:/1234">rdar:/1234</a>'),
("http://userid:password@example.com:8080", {},
u'<a href="http://userid:password@example.com:8080">http://userid:password@example.com:8080</a>'),
("http://userid@example.com", {},
u'<a href="http://userid@example.com">http://userid@example.com</a>'),
("http://userid@example.com:8080", {},
u'<a href="http://userid@example.com:8080">http://userid@example.com:8080</a>'),
("http://userid:password@example.com", {},
u'<a href="http://userid:password@example.com">http://userid:password@example.com</a>'),
("message://%3c330e7f8409726r6a4ba78dkf1fd71420c1bf6ff@mail.gmail.com%3e",
{"permitted_protocols": ["http", "message"]},
u'<a href="message://%3c330e7f8409726r6a4ba78dkf1fd71420c1bf6ff@mail.gmail.com%3e">message://%3c330e7f8409726r6a4ba78dkf1fd71420c1bf6ff@mail.gmail.com%3e</a>'),
(u"http://\u27a1.ws/\u4a39", {},
u'<a href="http://\u27a1.ws/\u4a39">http://\u27a1.ws/\u4a39</a>'),
("<tag>http://example.com</tag>", {},
u'<tag><a href="http://example.com">http://example.com</a></tag>'),
("Just a www.example.com link.", {},
u'Just a <a href="http://www.example.com">www.example.com</a> link.'),
("Just a www.example.com link.",
{"require_protocol": True},
u'Just a www.example.com link.'),
("A http://reallylong.com/link/that/exceedsthelenglimit.html",
{"require_protocol": True, "shorten": True},
u'A <a href="http://reallylong.com/link/that/exceedsthelenglimit.html" title="http://reallylong.com/link/that/exceedsthelenglimit.html">http://reallylong.com/link...</a>'),
("A http://reallylongdomainnamethatwillbetoolong.com/hi!",
{"shorten": True},
u'A <a href="http://reallylongdomainnamethatwillbetoolong.com/hi" title="http://reallylongdomainnamethatwillbetoolong.com/hi">http://reallylongdomainnametha...</a>!'),
("A file:///passwords.txt and http://web.com link", {},
u'A file:///passwords.txt and <a href="http://web.com">http://web.com</a> link'),
("A file:///passwords.txt and http://web.com link",
{"permitted_protocols": ["file"]},
u'A <a href="file:///passwords.txt">file:///passwords.txt</a> and http://web.com link'),
("www.external-link.com",
{"extra_params": 'rel="nofollow" class="external"'},
u'<a href="http://www.external-link.com" rel="nofollow" class="external">www.external-link.com</a>'),
("www.external-link.com and www.internal-link.com/blogs extra",
{"extra_params": lambda(href):'class="internal"' if href.startswith("http://www.internal-link.com") else 'rel="nofollow" class="external"'},
u'<a href="http://www.external-link.com" rel="nofollow" class="external">www.external-link.com</a> and <a href="http://www.internal-link.com/blogs" class="internal">www.internal-link.com/blogs</a> extra'),
("www.external-link.com",
{"extra_params": lambda(href):' rel="nofollow" class="external" '},
u'<a href="http://www.external-link.com" rel="nofollow" class="external">www.external-link.com</a>'),
]
class EscapeTestCase(unittest.TestCase):
def test_linkify(self):
for text, kwargs, html in linkify_tests:
linked = tornado.escape.linkify(text, **kwargs)
self.assertEqual(linked, html)
def test_xhtml_escape(self):
tests = [
("<foo>", "<foo>"),
(u"<foo>", u"<foo>"),
(b("<foo>"), b("<foo>")),
("<>&\"", "<>&""),
("&", "&amp;"),
]
for unescaped, escaped in tests:
self.assertEqual(utf8(xhtml_escape(unescaped)), utf8(escaped))
self.assertEqual(utf8(unescaped), utf8(xhtml_unescape(escaped)))
def test_url_escape(self):
tests = [
# byte strings are passed through as-is
(u'\u00e9'.encode('utf8'), '%C3%A9'),
(u'\u00e9'.encode('latin1'), '%E9'),
# unicode strings become utf8
(u'\u00e9', '%C3%A9'),
]
for unescaped, escaped in tests:
self.assertEqual(url_escape(unescaped), escaped)
def test_url_unescape(self):
tests = [
('%C3%A9', u'\u00e9', 'utf8'),
('%C3%A9', u'\u00c3\u00a9', 'latin1'),
('%C3%A9', utf8(u'\u00e9'), None),
]
for escaped, unescaped, encoding in tests:
# input strings to url_unescape should only contain ascii
# characters, but make sure the function accepts both byte
# and unicode strings.
self.assertEqual(url_unescape(to_unicode(escaped), encoding), unescaped)
self.assertEqual(url_unescape(utf8(escaped), encoding), unescaped)
def test_escape_return_types(self):
# On python2 the escape methods should generally return the same
# type as their argument
self.assertEqual(type(xhtml_escape("foo")), str)
self.assertEqual(type(xhtml_escape(u"foo")), unicode)
def test_json_decode(self):
# json_decode accepts both bytes and unicode, but strings it returns
# are always unicode.
self.assertEqual(json_decode(b('"foo"')), u"foo")
self.assertEqual(json_decode(u'"foo"'), u"foo")
# Non-ascii bytes are interpreted as utf8
self.assertEqual(json_decode(utf8(u'"\u00e9"')), u"\u00e9")
def test_json_encode(self):
# json deals with strings, not bytes, but our encoding function should
# accept bytes as well as long as they are utf8.
self.assertEqual(json_decode(json_encode(u"\u00e9")), u"\u00e9")
self.assertEqual(json_decode(json_encode(utf8(u"\u00e9"))), u"\u00e9")
self.assertRaises(UnicodeDecodeError, json_encode, b("\xe9"))
|
