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
|
/*
* Copyright (C) 1996-2026 The Squid Software Foundation and contributors
*
* Squid software is distributed under GPLv2+ license and includes
* contributions from numerous individuals and organizations.
* Please see the COPYING and CONTRIBUTORS files for details.
*/
#include "squid.h"
#include "rfc1738.h"
#if HAVE_STRING_H
#include <string.h>
#endif
/*
* RFC 1738 defines that these characters should be escaped, as well
* any non-US-ASCII character or anything between 0x00 - 0x1F.
*/
static char rfc1738_unsafe_chars[] = {
(char) 0x3C, /* < */
(char) 0x3E, /* > */
(char) 0x22, /* " */
(char) 0x23, /* # */
#if 0 /* done in code */
(char) 0x20, /* space */
(char) 0x25, /* % */
#endif
(char) 0x7B, /* { */
(char) 0x7D, /* } */
(char) 0x7C, /* | */
(char) 0x5C, /* \ */
(char) 0x5E, /* ^ */
(char) 0x7E, /* ~ */
(char) 0x5B, /* [ */
(char) 0x5D, /* ] */
(char) 0x60, /* ` */
(char) 0x27 /* ' */
};
static char rfc1738_reserved_chars[] = {
(char) 0x3b, /* ; */
(char) 0x2f, /* / */
(char) 0x3f, /* ? */
(char) 0x3a, /* : */
(char) 0x40, /* @ */
(char) 0x3d, /* = */
(char) 0x26 /* & */
};
/*
* rfc1738_escape - Returns a static buffer contains the RFC 1738
* compliant, escaped version of the given url.
*/
char *
rfc1738_do_escape(const char *url, int flags)
{
static char *buf;
static size_t bufsize = 0;
const char *src;
char *dst;
unsigned int i, do_escape;
if (buf == NULL || strlen(url) * 3 > bufsize) {
xfree(buf);
bufsize = strlen(url) * 3 + 1;
buf = (char*)xcalloc(bufsize, 1);
}
for (src = url, dst = buf; *src != '\0' && dst < (buf + bufsize - 1); src++, dst++) {
/* a-z, A-Z and 0-9 are SAFE. */
if ((*src >= 'a' && *src <= 'z') || (*src >= 'A' && *src <= 'Z') || (*src >= '0' && *src <= '9')) {
*dst = *src;
continue;
}
do_escape = 0;
/* RFC 1738 defines these chars as unsafe */
if ((flags & RFC1738_ESCAPE_UNSAFE)) {
for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
if (*src == rfc1738_unsafe_chars[i]) {
do_escape = 1;
break;
}
}
/* Handle % separately */
if (!(flags & RFC1738_ESCAPE_NOPERCENT) && *src == '%')
do_escape = 1;
/* Handle space separately */
else if (!(flags & RFC1738_ESCAPE_NOSPACE) && *src <= ' ')
do_escape = 1;
}
/* RFC 1738 defines these chars as reserved */
if ((flags & RFC1738_ESCAPE_RESERVED) && do_escape == 0) {
for (i = 0; i < sizeof(rfc1738_reserved_chars); i++) {
if (*src == rfc1738_reserved_chars[i]) {
do_escape = 1;
break;
}
}
}
if ((flags & RFC1738_ESCAPE_CTRLS) && do_escape == 0) {
/* RFC 1738 says any control chars (0x00-0x1F) are encoded */
if ((unsigned char) *src <= (unsigned char) 0x1F)
do_escape = 1;
/* RFC 1738 says 0x7f is encoded */
else if (*src == (char) 0x7F)
do_escape = 1;
/* RFC 1738 says any non-US-ASCII are encoded */
else if (((unsigned char) *src >= (unsigned char) 0x80))
do_escape = 1;
}
/* Do the triplet encoding, or just copy the char */
if (do_escape == 1) {
(void) snprintf(dst, (bufsize-(dst-buf)), "%%%02X", (unsigned char) *src);
dst += sizeof(char) * 2;
} else {
*dst = *src;
}
}
*dst = '\0';
return (buf);
}
/*
* Converts a ascii hex code into a binary character.
*/
static int
fromhex(char ch)
{
if (ch >= '0' && ch <= '9')
return ch - '0';
if (ch >= 'a' && ch <= 'f')
return ch - 'a' + 10;
if (ch >= 'A' && ch <= 'F')
return ch - 'A' + 10;
return -1;
}
/*
* rfc1738_unescape() - Converts escaped characters (%xy numbers) in
* given the string. %% is a %. %ab is the 8-bit hexadecimal number "ab"
*/
void
rfc1738_unescape(char *s)
{
int i, j; /* i is write, j is read */
for (i = j = 0; s[j]; i++, j++) {
s[i] = s[j];
if (s[j] != '%') {
/* normal case, nothing more to do */
} else if (s[j + 1] == '%') { /* %% case */
j++; /* Skip % */
} else {
/* decode */
int v1, v2, x;
v1 = fromhex(s[j + 1]);
if (v1 < 0)
continue; /* non-hex or \0 */
v2 = fromhex(s[j + 2]);
if (v2 < 0)
continue; /* non-hex or \0 */
x = v1 << 4 | v2;
if (x > 0 && x <= 255) {
s[i] = x;
j += 2;
}
}
}
s[i] = '\0';
}
|