lib/rfc1738.c

   1 /*
   2  * DEBUG:
   3  * AUTHOR: Harvest Derived
   4  *
   5  * SQUID Web Proxy Cache          http://www.squid-cache.org/
   6  * ----------------------------------------------------------
   7  *
   8  *  Squid is the result of efforts by numerous individuals from
   9  *  the Internet community; see the CONTRIBUTORS file for full
  10  *  details.   Many organizations have provided support for Squid's
  11  *  development; see the SPONSORS file for full details.  Squid is
  12  *  Copyrighted (C) 2001 by the Regents of the University of
  13  *  California; see the COPYRIGHT file for full details.  Squid
  14  *  incorporates software developed and/or copyrighted by other
  15  *  sources; see the CREDITS file for full details.
  16  *
  17  *  This program is free software; you can redistribute it and/or modify
  18  *  it under the terms of the GNU General Public License as published by
  19  *  the Free Software Foundation; either version 2 of the License, or
  20  *  (at your option) any later version.
  21  *
  22  *  This program is distributed in the hope that it will be useful,
  23  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  24  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  25  *  GNU General Public License for more details.
  26  *
  27  *  You should have received a copy of the GNU General Public License
  28  *  along with this program; if not, write to the Free Software
  29  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
  30  *
  31  */
  32
  33 #include "squid.h"
  34 #include "rfc1738.h"
  35
  36 #if HAVE_STRING_H
  37 #include <string.h>
  38 #endif
  39
  40 /*
  41  *  RFC 1738 defines that these characters should be escaped, as well
  42  *  any non-US-ASCII character or anything between 0x00 - 0x1F.
  43  */
  44 static char rfc1738_unsafe_chars[] = {
  45     (char) 0x3C,                /* < */
  46     (char) 0x3E,                /* > */
  47     (char) 0x22,                /* " */
  48     (char) 0x23,                /* # */
  49 #if 0                           /* done in code */
  50     (char) 0x20,                /* space */
  51     (char) 0x25,                /* % */
  52 #endif
  53     (char) 0x7B,                /* { */
  54     (char) 0x7D,                /* } */
  55     (char) 0x7C,                /* | */
  56     (char) 0x5C,                /* \ */
  57     (char) 0x5E,                /* ^ */
  58     (char) 0x7E,                /* ~ */
  59     (char) 0x5B,                /* [ */
  60     (char) 0x5D,                /* ] */
  61     (char) 0x60,                /* ` */
  62     (char) 0x27                 /* ' */
  63 };
  64
  65 static char rfc1738_reserved_chars[] = {
  66     (char) 0x3b,                /* ; */
  67     (char) 0x2f,                /* / */
  68     (char) 0x3f,                /* ? */
  69     (char) 0x3a,                /* : */
  70     (char) 0x40,                /* @ */
  71     (char) 0x3d,                /* = */
  72     (char) 0x26                 /* & */
  73 };
  74
  75 /*
  76  *  rfc1738_escape - Returns a static buffer contains the RFC 1738
  77  *  compliant, escaped version of the given url.
  78  */
  79 char *
  80 rfc1738_do_escape(const char *url, int flags)
  81 {
  82     static char *buf;
  83     static size_t bufsize = 0;
  84     const char *src;
  85     char *dst;
  86     unsigned int i, do_escape;
  87
  88     if (buf == NULL || strlen(url) * 3 > bufsize) {
  89         xfree(buf);
  90         bufsize = strlen(url) * 3 + 1;
  91         buf = (char*)xcalloc(bufsize, 1);
  92     }
  93     for (src = url, dst = buf; *src != '\0' && dst < (buf + bufsize - 1); src++, dst++) {
  94
  95         /* a-z, A-Z and 0-9 are SAFE. */
  96         if ((*src >= 'a' && *src <= 'z') || (*src >= 'A' && *src <= 'Z') || (*src >= '0' && *src <= '9')) {
  97             *dst = *src;
  98             continue;
  99         }
 100
 101         do_escape = 0;
 102
 103         /* RFC 1738 defines these chars as unsafe */
 104         if ((flags & RFC1738_ESCAPE_UNSAFE)) {
 105             for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
 106                 if (*src == rfc1738_unsafe_chars[i]) {
 107                     do_escape = 1;
 108                     break;
 109                 }
 110             }
 111             /* Handle % separately */
 112             if (!(flags & RFC1738_ESCAPE_NOPERCENT) && *src == '%')
 113                 do_escape = 1;
 114             /* Handle space separately */
 115             else if (!(flags & RFC1738_ESCAPE_NOSPACE) && *src <= ' ')
 116                 do_escape = 1;
 117         }
 118         /* RFC 1738 defines these chars as reserved */
 119         if ((flags & RFC1738_ESCAPE_RESERVED) && do_escape == 0) {
 120             for (i = 0; i < sizeof(rfc1738_reserved_chars); i++) {
 121                 if (*src == rfc1738_reserved_chars[i]) {
 122                     do_escape = 1;
 123                     break;
 124                 }
 125             }
 126         }
 127         if ((flags & RFC1738_ESCAPE_CTRLS) && do_escape == 0) {
 128             /* RFC 1738 says any control chars (0x00-0x1F) are encoded */
 129             if ((unsigned char) *src <= (unsigned char) 0x1F)
 130                 do_escape = 1;
 131             /* RFC 1738 says 0x7f is encoded */
 132             else if (*src == (char) 0x7F)
 133                 do_escape = 1;
 134             /* RFC 1738 says any non-US-ASCII are encoded */
 135             else if (((unsigned char) *src >= (unsigned char) 0x80))
 136                 do_escape = 1;
 137         }
 138         /* Do the triplet encoding, or just copy the char */
 139         if (do_escape == 1) {
 140             (void) snprintf(dst, (bufsize-(dst-buf)), "%%%02X", (unsigned char) *src);
 141             dst += sizeof(char) * 2;
 142         } else {
 143             *dst = *src;
 144         }
 145     }
 146     *dst = '\0';
 147     return (buf);
 148 }
 149
 150 /*
 151  * Converts a ascii hex code into a binary character.
 152  */
 153 static int
 154 fromhex(char ch)
 155 {
 156     if (ch >= '0' && ch <= '9')
 157         return ch - '0';
 158     if (ch >= 'a' && ch <= 'f')
 159         return ch - 'a' + 10;
 160     if (ch >= 'A' && ch <= 'F')
 161         return ch - 'A' + 10;
 162     return -1;
 163 }
 164
 165 /*
 166  *  rfc1738_unescape() - Converts escaped characters (%xy numbers) in
 167  *  given the string.  %% is a %. %ab is the 8-bit hexadecimal number "ab"
 168  */
 169 void
 170 rfc1738_unescape(char *s)
 171 {
 172     int i, j;                   /* i is write, j is read */
 173     for (i = j = 0; s[j]; i++, j++) {
 174         s[i] = s[j];
 175         if (s[j] != '%') {
 176             /* normal case, nothing more to do */
 177         } else if (s[j + 1] == '%') {   /* %% case */
 178             j++;                /* Skip % */
 179         } else {
 180             /* decode */
 181             int v1, v2, x;
 182             v1 = fromhex(s[j + 1]);
 183             if (v1 < 0)
 184                 continue;  /* non-hex or \0 */
 185             v2 = fromhex(s[j + 2]);
 186             if (v2 < 0)
 187                 continue;  /* non-hex or \0 */
 188             x = v1 << 4 | v2;
 189             if (x > 0 && x <= 255) {
 190                 s[i] = x;
 191                 j += 2;
 192             }
 193         }
 194     }
 195     s[i] = '\0';
 196 }