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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
// Copyright (c) 2012 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "base/basictypes.h"
#include "net/base/data_url.h"
#include "testing/gtest/include/gtest/gtest.h"
#include "url/gurl.h"
namespace net {
namespace {
struct ParseTestData {
const char* url;
bool is_valid;
const char* mime_type;
const char* charset;
const char* data;
};
} // namespace
TEST(DataURLTest, Parse) {
const ParseTestData tests[] = {
{ "data:",
false,
"",
"",
"" },
{ "data:,",
true,
"text/plain",
"US-ASCII",
"" },
{ "data:;base64,",
true,
"text/plain",
"US-ASCII",
"" },
{ "data:;charset=,test",
false,
"",
"",
"" },
{ "data:TeXt/HtMl,<b>x</b>",
true,
"text/html",
"US-ASCII",
"<b>x</b>" },
{ "data:,foo",
true,
"text/plain",
"US-ASCII",
"foo" },
{ "data:;base64,aGVsbG8gd29ybGQ=",
true,
"text/plain",
"US-ASCII",
"hello world" },
// Allow invalid mediatype for backward compatibility but set mime_type to
// "text/plain" instead of the invalid mediatype.
{ "data:foo,boo",
true,
"text/plain",
"US-ASCII",
"boo" },
// When accepting an invalid mediatype, override charset with "US-ASCII"
{ "data:foo;charset=UTF-8,boo",
true,
"text/plain",
"US-ASCII",
"boo" },
// Invalid mediatype. Includes a slash but the type part is not a token.
{ "data:f(oo/bar;baz=1;charset=kk,boo",
true,
"text/plain",
"US-ASCII",
"boo" },
{ "data:foo/bar;baz=1;charset=kk,boo",
true,
"foo/bar",
"kk",
"boo" },
{ "data:foo/bar;charset=kk;baz=1,boo",
true,
"foo/bar",
"kk",
"boo" },
{ "data:text/html,%3Chtml%3E%3Cbody%3E%3Cb%3Ehello%20world"
"%3C%2Fb%3E%3C%2Fbody%3E%3C%2Fhtml%3E",
true,
"text/html",
"US-ASCII",
"<html><body><b>hello world</b></body></html>" },
{ "data:text/html,<html><body><b>hello world</b></body></html>",
true,
"text/html",
"US-ASCII",
"<html><body><b>hello world</b></body></html>" },
// the comma cannot be url-escaped!
{ "data:%2Cblah",
false,
"",
"",
"" },
// invalid base64 content
{ "data:;base64,aGVs_-_-",
false,
"",
"",
"" },
// Spaces should be removed from non-text data URLs (we already tested
// spaces above).
{ "data:image/fractal,a b c d e f g",
true,
"image/fractal",
"US-ASCII",
"abcdefg" },
// Spaces should also be removed from anything base-64 encoded
{ "data:;base64,aGVs bG8gd2 9ybGQ=",
true,
"text/plain",
"US-ASCII",
"hello world" },
// Other whitespace should also be removed from anything base-64 encoded.
{ "data:;base64,aGVs bG8gd2 \n9ybGQ=",
true,
"text/plain",
"US-ASCII",
"hello world" },
// In base64 encoding, escaped whitespace should be stripped.
// (This test was taken from acid3)
// http://b/1054495
{ "data:text/javascript;base64,%20ZD%20Qg%0D%0APS%20An%20Zm91cic%0D%0A%207"
"%20",
true,
"text/javascript",
"US-ASCII",
"d4 = 'four';" },
// Only unescaped whitespace should be stripped in non-base64.
// http://b/1157796
{ "data:img/png,A B %20 %0A C",
true,
"img/png",
"US-ASCII",
"AB \nC" },
{ "data:text/plain;charset=utf-8;base64,SGVsbMO2",
true,
"text/plain",
"utf-8",
"Hell\xC3\xB6" },
// Not sufficiently padded.
{ "data:;base64,aGVsbG8gd29ybGQ",
true,
"text/plain",
"US-ASCII",
"hello world" },
// Bad encoding (truncated).
{ "data:;base64,aGVsbG8gd29yb",
false,
"",
"",
"" },
// BiDi control characters should be unescaped and preserved as is, and
// should not be replaced with % versions. In the below case, \xE2\x80\x8F
// is the RTL mark and the parsed text should preserve it as is.
{
"data:text/plain;charset=utf-8,\xE2\x80\x8Ftest",
true,
"text/plain",
"utf-8",
"\xE2\x80\x8Ftest"},
// Same as above but with Arabic text after RTL mark.
{
"data:text/plain;charset=utf-8,"
"\xE2\x80\x8F\xD8\xA7\xD8\xAE\xD8\xAA\xD8\xA8\xD8\xA7\xD8\xB1",
true,
"text/plain",
"utf-8",
"\xE2\x80\x8F\xD8\xA7\xD8\xAE\xD8\xAA\xD8\xA8\xD8\xA7\xD8\xB1"},
// RTL mark encoded as %E2%80%8F should be unescaped too. Note that when
// wrapped in a GURL, this URL and the next effectively become the same as
// the previous two URLs.
{
"data:text/plain;charset=utf-8,%E2%80%8Ftest",
true,
"text/plain",
"utf-8",
"\xE2\x80\x8Ftest"},
// Same as above but with Arabic text after RTL mark.
{
"data:text/plain;charset=utf-8,"
"%E2%80%8F\xD8\xA7\xD8\xAE\xD8\xAA\xD8\xA8\xD8\xA7\xD8\xB1",
true,
"text/plain",
"utf-8",
"\xE2\x80\x8F\xD8\xA7\xD8\xAE\xD8\xAA\xD8\xA8\xD8\xA7\xD8\xB1"}
// TODO(darin): add more interesting tests
};
for (size_t i = 0; i < arraysize(tests); ++i) {
std::string mime_type;
std::string charset;
std::string data;
bool ok = DataURL::Parse(GURL(tests[i].url), &mime_type, &charset, &data);
EXPECT_EQ(ok, tests[i].is_valid);
if (tests[i].is_valid) {
EXPECT_EQ(tests[i].mime_type, mime_type);
EXPECT_EQ(tests[i].charset, charset);
EXPECT_EQ(tests[i].data, data);
}
}
}
} // namespace net
|
