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
|
// SPDX-License-Identifier: GPL-3.0-or-later
#include "../libnetdata.h"
// ----------------------------------------------------------------------------
// URL encode / decode
// code from: http://www.geekhideout.com/urlcode.shtml
/* Converts a hex character to its integer value */
char from_hex(char ch) {
return (char)(isdigit(ch) ? ch - '0' : tolower(ch) - 'a' + 10);
}
/* Converts an integer value to its hex character*/
char to_hex(char code) {
static char hex[] = "0123456789abcdef";
return hex[code & 15];
}
/* Returns a url-encoded version of str */
/* IMPORTANT: be sure to free() the returned string after use */
char *url_encode(char *str) {
char *buf, *pbuf;
pbuf = buf = mallocz(strlen(str) * 3 + 1);
while (*str) {
if (isalnum(*str) || *str == '-' || *str == '_' || *str == '.' || *str == '~')
*pbuf++ = *str;
else if (*str == ' ')
*pbuf++ = '+';
else
*pbuf++ = '%', *pbuf++ = to_hex(*str >> 4), *pbuf++ = to_hex(*str & 15);
str++;
}
*pbuf = '\0';
pbuf = strdupz(buf);
freez(buf);
return pbuf;
}
/* Returns a url-decoded version of str */
/* IMPORTANT: be sure to free() the returned string after use */
char *url_decode(char *str) {
size_t size = strlen(str) + 1;
char *buf = mallocz(size);
return url_decode_r(buf, str, size);
}
//decode %XX character or return 0 if cannot
char url_percent_escape_decode(char *s) {
if(likely(s[1] && s[2]))
return from_hex(s[1]) << 4 | from_hex(s[2]);
return 0;
}
//this (utf8 string related) should be moved in separate file in future
char url_utf8_get_byte_length(char c) {
if(!IS_UTF8_BYTE(c))
return 1;
char length = 0;
while(likely(c & 0x80)) {
length++;
c <<= 1;
}
//4 byte is max size for UTF-8 char
//10XX XXXX is not valid character -> check length == 1
if(length > 4 || length == 1)
return -1;
return length;
}
//decode % encoded UTF-8 characters and copy them to *d
//return count of bytes written to *d
char url_decode_multibyte_utf8(char *s, char *d, char *d_end) {
char first_byte = url_percent_escape_decode(s);
if(unlikely(!first_byte || !IS_UTF8_STARTBYTE(first_byte)))
return 0;
char byte_length = url_utf8_get_byte_length(first_byte);
if(unlikely(byte_length <= 0 || d+byte_length >= d_end))
return 0;
char to_read = byte_length;
while(to_read > 0) {
char c = url_percent_escape_decode(s);
if(unlikely( !IS_UTF8_BYTE(c) ))
return 0;
if((to_read != byte_length) && IS_UTF8_STARTBYTE(c))
return 0;
*d++ = c;
s+=3;
to_read--;
}
return byte_length;
}
/*
* The utf8_check() function scans the '\0'-terminated string starting
* at s. It returns a pointer to the first byte of the first malformed
* or overlong UTF-8 sequence found, or NULL if the string contains
* only correct UTF-8. It also spots UTF-8 sequences that could cause
* trouble if converted to UTF-16, namely surrogate characters
* (U+D800..U+DFFF) and non-Unicode positions (U+FFFE..U+FFFF). This
* routine is very likely to find a malformed sequence if the input
* uses any other encoding than UTF-8. It therefore can be used as a
* very effective heuristic for distinguishing between UTF-8 and other
* encodings.
*
* Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> -- 2005-03-30
* License: http://www.cl.cam.ac.uk/~mgk25/short-license.html
*/
unsigned char *utf8_check(unsigned char *s)
{
while (*s)
{
if (*s < 0x80)
/* 0xxxxxxx */
s++;
else if ((s[0] & 0xe0) == 0xc0)
{
/* 110XXXXx 10xxxxxx */
if ((s[1] & 0xc0) != 0x80 ||
(s[0] & 0xfe) == 0xc0) /* overlong? */
return s;
else
s += 2;
}
else if ((s[0] & 0xf0) == 0xe0)
{
/* 1110XXXX 10Xxxxxx 10xxxxxx */
if ((s[1] & 0xc0) != 0x80 ||
(s[2] & 0xc0) != 0x80 ||
(s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) || /* overlong? */
(s[0] == 0xed && (s[1] & 0xe0) == 0xa0) || /* surrogate? */
(s[0] == 0xef && s[1] == 0xbf &&
(s[2] & 0xfe) == 0xbe)) /* U+FFFE or U+FFFF? */
return s;
else
s += 3;
}
else if ((s[0] & 0xf8) == 0xf0)
{
/* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */
if ((s[1] & 0xc0) != 0x80 ||
(s[2] & 0xc0) != 0x80 ||
(s[3] & 0xc0) != 0x80 ||
(s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) || /* overlong? */
(s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4) /* > U+10FFFF? */
return s;
else
s += 4;
}
else
return s;
}
return NULL;
}
char *url_decode_r(char *to, char *url, size_t size) {
char *s = url, // source
*d = to, // destination
*e = &to[size - 1]; // destination end
while(*s && d < e) {
if(unlikely(*s == '%')) {
char t = url_percent_escape_decode(s);
if(IS_UTF8_BYTE(t)) {
char bytes_written = url_decode_multibyte_utf8(s, d, e);
if(likely(bytes_written)){
d += bytes_written;
s += (bytes_written * 3)-1;
}
else {
goto fail_cleanup;
}
}
else if(likely(t) && isprint(t)) {
// avoid HTTP header injection
*d++ = t;
s += 2;
}
else
goto fail_cleanup;
}
else if(unlikely(*s == '+'))
*d++ = ' ';
else
*d++ = *s;
s++;
}
*d = '\0';
if(unlikely( utf8_check(to) )) //NULL means sucess here
return NULL;
return to;
fail_cleanup:
*d = '\0';
return NULL;
}
|