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
245
246
247
248
249
250
251
252
253
254
|
/* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
#include <ctype.h>
#include <stdio.h>
#include <mozilla/RefPtr.h>
#include "nsEscape.h"
#include "nsString.h"
#include "nsUrlClassifierUtils.h"
#include "stdlib.h"
#include "Common.h"
static char int_to_hex_digit(int32_t i) {
NS_ASSERTION((i >= 0) && (i <= 15), "int too big in int_to_hex_digit");
return static_cast<char>(((i < 10) ? (i + '0') : ((i - 10) + 'A')));
}
static void CheckEquals(nsCString& expected, nsCString& actual) {
ASSERT_TRUE((expected).Equals((actual)))
<< "Expected:" << expected.get() << ", Actual:" << actual.get();
}
static void TestUnescapeHelper(const char* in, const char* expected) {
nsCString out, strIn(in), strExp(expected);
NS_UnescapeURL(strIn.get(), strIn.Length(), esc_AlwaysCopy, out);
CheckEquals(strExp, out);
}
static void TestEncodeHelper(const char* in, const char* expected) {
nsCString out, strIn(in), strExp(expected);
nsUrlClassifierUtils::GetInstance()->SpecialEncode(strIn, true, out);
CheckEquals(strExp, out);
}
static void TestCanonicalizeHelper(const char* in, const char* expected) {
nsCString out, strIn(in), strExp(expected);
nsUrlClassifierUtils::GetInstance()->CanonicalizePath(strIn, out);
CheckEquals(strExp, out);
}
static void TestCanonicalNumHelper(const char* in, uint32_t bytes,
bool allowOctal, const char* expected) {
nsCString out, strIn(in), strExp(expected);
nsUrlClassifierUtils::GetInstance()->CanonicalNum(strIn, bytes, allowOctal,
out);
CheckEquals(strExp, out);
}
void TestHostnameHelper(const char* in, const char* expected) {
nsCString out, strIn(in), strExp(expected);
nsUrlClassifierUtils::GetInstance()->CanonicalizeHostname(strIn, out);
CheckEquals(strExp, out);
}
// Make sure Unescape from nsEncode.h's unescape does what the server does.
TEST(UrlClassifierUtils, Unescape)
{
// test empty string
TestUnescapeHelper("\0", "\0");
// Test docoding of all characters.
nsCString allCharsEncoded, allCharsEncodedLowercase, allCharsAsString;
for (int32_t i = 1; i < 256; ++i) {
allCharsEncoded.Append('%');
allCharsEncoded.Append(int_to_hex_digit(i / 16));
allCharsEncoded.Append((int_to_hex_digit(i % 16)));
allCharsEncodedLowercase.Append('%');
allCharsEncodedLowercase.Append(tolower(int_to_hex_digit(i / 16)));
allCharsEncodedLowercase.Append(tolower(int_to_hex_digit(i % 16)));
allCharsAsString.Append(static_cast<char>(i));
}
nsCString out;
NS_UnescapeURL(allCharsEncoded.get(), allCharsEncoded.Length(),
esc_AlwaysCopy, out);
CheckEquals(allCharsAsString, out);
out.Truncate();
NS_UnescapeURL(allCharsEncodedLowercase.get(),
allCharsEncodedLowercase.Length(), esc_AlwaysCopy, out);
CheckEquals(allCharsAsString, out);
// Test %-related edge cases
TestUnescapeHelper("%", "%");
TestUnescapeHelper("%xx", "%xx");
TestUnescapeHelper("%%", "%%");
TestUnescapeHelper("%%%", "%%%");
TestUnescapeHelper("%%%%", "%%%%");
TestUnescapeHelper("%1", "%1");
TestUnescapeHelper("%1z", "%1z");
TestUnescapeHelper("a%1z", "a%1z");
TestUnescapeHelper("abc%d%e%fg%hij%klmno%", "abc%d%e%fg%hij%klmno%");
// A few more tests
TestUnescapeHelper("%25", "%");
TestUnescapeHelper("%25%32%35", "%25");
}
TEST(UrlClassifierUtils, Enc)
{
// Test empty string
TestEncodeHelper("", "");
// Test that all characters we shouldn't encode ([33-34],36,[38,126]) are not.
nsCString noenc;
for (int32_t i = 33; i < 127; i++) {
if (i != 35 && i != 37) { // skip %
noenc.Append(static_cast<char>(i));
}
}
nsCString out;
nsUrlClassifierUtils::GetInstance()->SpecialEncode(noenc, false, out);
CheckEquals(noenc, out);
// Test that all the chars that we should encode [0,32],35, 37,[127,255] are
nsCString yesAsString, yesExpectedString;
for (int32_t i = 1; i < 256; i++) {
if (i < 33 || i == 35 || i == 37 || i > 126) {
yesAsString.Append(static_cast<char>(i));
yesExpectedString.Append('%');
yesExpectedString.Append(int_to_hex_digit(i / 16));
yesExpectedString.Append(int_to_hex_digit(i % 16));
}
}
out.Truncate();
nsUrlClassifierUtils::GetInstance()->SpecialEncode(yesAsString, false, out);
CheckEquals(yesExpectedString, out);
TestEncodeHelper("blah//blah", "blah/blah");
}
TEST(UrlClassifierUtils, Canonicalize)
{
// Test repeated %-decoding. Note: %25 --> %, %32 --> 2, %35 --> 5
TestCanonicalizeHelper("%25", "%25");
TestCanonicalizeHelper("%25%32%35", "%25");
TestCanonicalizeHelper("asdf%25%32%35asd", "asdf%25asd");
TestCanonicalizeHelper("%%%25%32%35asd%%", "%25%25%25asd%25%25");
TestCanonicalizeHelper("%25%32%35%25%32%35%25%32%35", "%25%25%25");
TestCanonicalizeHelper("%25", "%25");
TestCanonicalizeHelper(
"%257Ea%2521b%2540c%2523d%2524e%25f%255E00%252611%252A22%252833%252944_"
"55%252B",
"~a!b@c%23d$e%25f^00&11*22(33)44_55+");
TestCanonicalizeHelper("", "");
TestCanonicalizeHelper(
"%31%36%38%2e%31%38%38%2e%39%39%2e%32%36/%2E%73%65%63%75%72%65/"
"%77%77%77%2E%65%62%61%79%2E%63%6F%6D/",
"168.188.99.26/.secure/www.ebay.com/");
TestCanonicalizeHelper(
"195.127.0.11/uploads/%20%20%20%20/.verify/"
".eBaysecure=updateuserdataxplimnbqmn-xplmvalidateinfoswqpcmlx=hgplmcx/",
"195.127.0.11/uploads/%20%20%20%20/.verify/"
".eBaysecure=updateuserdataxplimnbqmn-xplmvalidateinfoswqpcmlx=hgplmcx/");
// Added in bug 489455. %00 should no longer be changed to %01.
TestCanonicalizeHelper("%00", "%00");
}
void TestParseIPAddressHelper(const char* in, const char* expected) {
nsCString out, strIn(in), strExp(expected);
nsUrlClassifierUtils::GetInstance()->ParseIPAddress(strIn, out);
CheckEquals(strExp, out);
}
TEST(UrlClassifierUtils, ParseIPAddress)
{
TestParseIPAddressHelper("123.123.0.0.1", "");
TestParseIPAddressHelper("255.0.0.1", "255.0.0.1");
TestParseIPAddressHelper("12.0x12.01234", "12.18.2.156");
TestParseIPAddressHelper("276.2.3", "20.2.0.3");
TestParseIPAddressHelper("012.034.01.055", "10.28.1.45");
TestParseIPAddressHelper("0x12.0x43.0x44.0x01", "18.67.68.1");
TestParseIPAddressHelper("167838211", "10.1.2.3");
TestParseIPAddressHelper("3279880203", "195.127.0.11");
TestParseIPAddressHelper("0x12434401", "18.67.68.1");
TestParseIPAddressHelper("413960661", "24.172.137.213");
TestParseIPAddressHelper("03053104725", "24.172.137.213");
TestParseIPAddressHelper("030.0254.0x89d5", "24.172.137.213");
TestParseIPAddressHelper("1.234.4.0377", "1.234.4.255");
TestParseIPAddressHelper("1.2.3.00x0", "");
TestParseIPAddressHelper("10.192.95.89 xy", "10.192.95.89");
TestParseIPAddressHelper("10.192.95.89 xyz", "");
TestParseIPAddressHelper("1.2.3.0x0", "1.2.3.0");
TestParseIPAddressHelper("1.2.3.4", "1.2.3.4");
}
TEST(UrlClassifierUtils, CanonicalNum)
{
TestCanonicalNumHelper("", 1, true, "");
TestCanonicalNumHelper("10", 0, true, "");
TestCanonicalNumHelper("45", 1, true, "45");
TestCanonicalNumHelper("0x10", 1, true, "16");
TestCanonicalNumHelper("367", 2, true, "1.111");
TestCanonicalNumHelper("012345", 3, true, "0.20.229");
TestCanonicalNumHelper("0173", 1, true, "123");
TestCanonicalNumHelper("09", 1, false, "9");
TestCanonicalNumHelper("0x120x34", 2, true, "");
TestCanonicalNumHelper("0x12fc", 2, true, "18.252");
TestCanonicalNumHelper("3279880203", 4, true, "195.127.0.11");
TestCanonicalNumHelper("0x0000059", 1, true, "89");
TestCanonicalNumHelper("0x00000059", 1, true, "89");
TestCanonicalNumHelper("0x0000067", 1, true, "103");
}
TEST(UrlClassifierUtils, Hostname)
{
TestHostnameHelper("abcd123;[]", "abcd123;[]");
TestHostnameHelper("abc.123", "abc.123");
TestHostnameHelper("abc..123", "abc.123");
TestHostnameHelper("trailing.", "trailing");
TestHostnameHelper("i love trailing dots....", "i%20love%20trailing%20dots");
TestHostnameHelper(".leading", "leading");
TestHostnameHelper("..leading", "leading");
TestHostnameHelper(".dots.", "dots");
TestHostnameHelper(".both.", "both");
TestHostnameHelper(".both..", "both");
TestHostnameHelper("..both.", "both");
TestHostnameHelper("..both..", "both");
TestHostnameHelper("..a.b.c.d..", "a.b.c.d");
TestHostnameHelper("..127.0.0.1..", "127.0.0.1");
TestHostnameHelper("AB CD 12354", "ab%20cd%2012354");
TestHostnameHelper("\1\2\3\4\112\177", "%01%02%03%04j%7F");
TestHostnameHelper("<>.AS/-+", "<>.as/-+");
// Added in bug 489455. %00 should no longer be changed to %01.
TestHostnameHelper("%00", "%00");
}
TEST(UrlClassifierUtils, LongHostname)
{
static const int kTestSize = 1024 * 150;
char* str = static_cast<char*>(malloc(kTestSize + 1));
memset(str, 'x', kTestSize);
str[kTestSize] = '\0';
nsAutoCString out;
nsDependentCString in(str);
PRIntervalTime clockStart = PR_IntervalNow();
nsUrlClassifierUtils::GetInstance()->CanonicalizeHostname(in, out);
PRIntervalTime clockEnd = PR_IntervalNow();
CheckEquals(in, out);
printf("CanonicalizeHostname on long string (%dms)\n",
PR_IntervalToMilliseconds(clockEnd - clockStart));
}
|
