1 /*
2 * Copyright (C) 2004-2005 Kay Sievers <kay.sievers@vrfy.org>
3 *
4 * This program is free software; you can redistribute it and/or modify it
5 * under the terms of the GNU General Public License as published by the
6 * Free Software Foundation version 2 of the License.
7 *
8 * This program is distributed in the hope that it will be useful, but
9 * WITHOUT ANY WARRANTY; without even the implied warranty of
10 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
11 * General Public License for more details.
12 *
13 * You should have received a copy of the GNU General Public License along
14 * with this program; if not, write to the Free Software Foundation, Inc.,
15 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
16 *
17 */
18
19
remove_trailing_chars(char * path,char c)20 static void remove_trailing_chars(char *path, char c)
21 {
22 size_t len;
23
24 len = strlen(path);
25 while (len > 0 && path[len-1] == c)
26 path[--len] = '\0';
27 }
28
29 /* count of characters used to encode one unicode char */
utf8_encoded_expected_len(const char * str)30 static int utf8_encoded_expected_len(const char *str)
31 {
32 unsigned char c = (unsigned char)str[0];
33
34 if (c < 0x80)
35 return 1;
36 if ((c & 0xe0) == 0xc0)
37 return 2;
38 if ((c & 0xf0) == 0xe0)
39 return 3;
40 if ((c & 0xf8) == 0xf0)
41 return 4;
42 if ((c & 0xfc) == 0xf8)
43 return 5;
44 if ((c & 0xfe) == 0xfc)
45 return 6;
46 return 0;
47 }
48
49 /* decode one unicode char */
utf8_encoded_to_unichar(const char * str)50 static int utf8_encoded_to_unichar(const char *str)
51 {
52 int unichar;
53 int len;
54 int i;
55
56 len = utf8_encoded_expected_len(str);
57 switch (len) {
58 case 1:
59 return (int)str[0];
60 case 2:
61 unichar = str[0] & 0x1f;
62 break;
63 case 3:
64 unichar = (int)str[0] & 0x0f;
65 break;
66 case 4:
67 unichar = (int)str[0] & 0x07;
68 break;
69 case 5:
70 unichar = (int)str[0] & 0x03;
71 break;
72 case 6:
73 unichar = (int)str[0] & 0x01;
74 break;
75 default:
76 return -1;
77 }
78
79 for (i = 1; i < len; i++) {
80 if (((int)str[i] & 0xc0) != 0x80)
81 return -1;
82 unichar <<= 6;
83 unichar |= (int)str[i] & 0x3f;
84 }
85
86 return unichar;
87 }
88
89 /* expected size used to encode one unicode char */
utf8_unichar_to_encoded_len(int unichar)90 static int utf8_unichar_to_encoded_len(int unichar)
91 {
92 if (unichar < 0x80)
93 return 1;
94 if (unichar < 0x800)
95 return 2;
96 if (unichar < 0x10000)
97 return 3;
98 if (unichar < 0x200000)
99 return 4;
100 if (unichar < 0x4000000)
101 return 5;
102 return 6;
103 }
104
105 /* check if unicode char has a valid numeric range */
utf8_unichar_valid_range(int unichar)106 static int utf8_unichar_valid_range(int unichar)
107 {
108 if (unichar > 0x10ffff)
109 return 0;
110 if ((unichar & 0xfffff800) == 0xd800)
111 return 0;
112 if ((unichar > 0xfdcf) && (unichar < 0xfdf0))
113 return 0;
114 if ((unichar & 0xffff) == 0xffff)
115 return 0;
116 return 1;
117 }
118
119 /* validate one encoded unicode char and return its length */
utf8_encoded_valid_unichar(const char * str)120 static int utf8_encoded_valid_unichar(const char *str)
121 {
122 int len;
123 int unichar;
124 int i;
125
126 len = utf8_encoded_expected_len(str);
127 if (len == 0)
128 return -1;
129
130 /* ascii is valid */
131 if (len == 1)
132 return 1;
133
134 /* check if expected encoded chars are available */
135 for (i = 0; i < len; i++)
136 if ((str[i] & 0x80) != 0x80)
137 return -1;
138
139 unichar = utf8_encoded_to_unichar(str);
140
141 /* check if encoded length matches encoded value */
142 if (utf8_unichar_to_encoded_len(unichar) != len)
143 return -1;
144
145 /* check if value has valid range */
146 if (!utf8_unichar_valid_range(unichar))
147 return -1;
148
149 return len;
150 }
151
152 /* replace everything but whitelisted plain ascii and valid utf8 */
replace_untrusted_chars(char * str)153 static int replace_untrusted_chars(char *str)
154 {
155 size_t i = 0;
156 int replaced = 0;
157
158 while (str[i] != '\0') {
159 int len;
160
161 /* valid printable ascii char */
162 if ((str[i] >= '0' && str[i] <= '9') ||
163 (str[i] >= 'A' && str[i] <= 'Z') ||
164 (str[i] >= 'a' && str[i] <= 'z') ||
165 strchr(" #$%+-./:=?@_,", str[i])) {
166 i++;
167 continue;
168 }
169 /* valid utf8 is accepted */
170 len = utf8_encoded_valid_unichar(&str[i]);
171 if (len > 1) {
172 i += len;
173 continue;
174 }
175
176 /* everything else is garbage */
177 str[i] = '_';
178 i++;
179 replaced++;
180 }
181
182 return replaced;
183 }
184