lib/rfc1738.c

   1 /*
   2  * $Id: rfc1738.c,v 1.28 2007/12/06 02:37:15 amosjeffries Exp $
   3  *
   4  * DEBUG:
   5  * AUTHOR: Harvest Derived
   6  *
   7  * SQUID Web Proxy Cache          http://www.squid-cache.org/
   8  * ----------------------------------------------------------
   9  *
  10  *  Squid is the result of efforts by numerous individuals from
  11  *  the Internet community; see the CONTRIBUTORS file for full
  12  *  details.   Many organizations have provided support for Squid's
  13  *  development; see the SPONSORS file for full details.  Squid is
  14  *  Copyrighted (C) 2001 by the Regents of the University of
  15  *  California; see the COPYRIGHT file for full details.  Squid
  16  *  incorporates software developed and/or copyrighted by other
  17  *  sources; see the CREDITS file for full details.
  18  *
  19  *  This program is free software; you can redistribute it and/or modify
  20  *  it under the terms of the GNU General Public License as published by
  21  *  the Free Software Foundation; either version 2 of the License, or
  22  *  (at your option) any later version.
  23  *
  24  *  This program is distributed in the hope that it will be useful,
  25  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  26  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  27  *  GNU General Public License for more details.
  28  *
  29  *  You should have received a copy of the GNU General Public License
  30  *  along with this program; if not, write to the Free Software
  31  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
  32  *
  33  */
  34
  35 #include "config.h"
  36
  37 #if HAVE_STDIO_H
  38 #include <stdio.h>
  39 #endif
  40 #if HAVE_STRING_H
  41 #include <string.h>
  42 #endif
  43
  44 #include "util.h"
  45
  46 /*
  47  *  RFC 1738 defines that these characters should be escaped, as well
  48  *  any non-US-ASCII character or anything between 0x00 - 0x1F.
  49  */
  50 static char rfc1738_unsafe_chars[] = {
  51     (char) 0x3C,                /* < */
  52     (char) 0x3E,                /* > */
  53     (char) 0x22,                /* " */
  54     (char) 0x23,                /* # */
  55 #if 0                           /* done in code */
  56     (char) 0x25,                /* % */
  57 #endif
  58     (char) 0x7B,                /* { */
  59     (char) 0x7D,                /* } */
  60     (char) 0x7C,                /* | */
  61     (char) 0x5C,                /* \ */
  62     (char) 0x5E,                /* ^ */
  63     (char) 0x7E,                /* ~ */
  64     (char) 0x5B,                /* [ */
  65     (char) 0x5D,                /* ] */
  66     (char) 0x60,                /* ` */
  67     (char) 0x27,                /* ' */
  68     (char) 0x20                 /* space */
  69 };
  70
  71 static char rfc1738_reserved_chars[] = {
  72     (char) 0x3b,                /* ; */
  73     (char) 0x2f,                /* / */
  74     (char) 0x3f,                /* ? */
  75     (char) 0x3a,                /* : */
  76     (char) 0x40,                /* @ */
  77     (char) 0x3d,                /* = */
  78     (char) 0x26                 /* & */
  79 };
  80
  81 /*
  82  *  rfc1738_escape - Returns a static buffer contains the RFC 1738
  83  *  compliant, escaped version of the given url.
  84  */
  85 static char *
  86 rfc1738_do_escape(const char *url, int encode_reserved)
  87 {
  88     static char *buf;
  89     static size_t bufsize = 0;
  90     const char *p;
  91     char *q;
  92     unsigned int i, do_escape;
  93
  94     if (buf == NULL || strlen(url) * 3 > bufsize) {
  95         xfree(buf);
  96         bufsize = strlen(url) * 3 + 1;
  97         buf = xcalloc(bufsize, 1);
  98     }
  99     for (p = url, q = buf; *p != '\0' && q < (buf + bufsize - 1); p++, q++) {
 100         do_escape = 0;
 101
 102         /* RFC 1738 defines these chars as unsafe */
 103         for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
 104             if (*p == rfc1738_unsafe_chars[i]) {
 105                 do_escape = 1;
 106                 break;
 107             }
 108         }
 109         /* Handle % separately */
 110         if (encode_reserved >= 0 && *p == '%')
 111             do_escape = 1;
 112         /* RFC 1738 defines these chars as reserved */
 113         for (i = 0; i < sizeof(rfc1738_reserved_chars) && encode_reserved > 0; i++) {
 114             if (*p == rfc1738_reserved_chars[i]) {
 115                 do_escape = 1;
 116                 break;
 117             }
 118         }
 119         /* RFC 1738 says any control chars (0x00-0x1F) are encoded */
 120         if ((unsigned char) *p <= (unsigned char) 0x1F) {
 121             do_escape = 1;
 122         }
 123         /* RFC 1738 says 0x7f is encoded */
 124         if (*p == (char) 0x7F) {
 125             do_escape = 1;
 126         }
 127         /* RFC 1738 says any non-US-ASCII are encoded */
 128         if (((unsigned char) *p >= (unsigned char) 0x80)) {
 129             do_escape = 1;
 130         }
 131         /* Do the triplet encoding, or just copy the char */
 132         /* note: we do not need snprintf here as q is appropriately
 133          * allocated - KA */
 134
 135         if (do_escape == 1) {
 136             (void) sprintf(q, "%%%02X", (unsigned char) *p);
 137             q += sizeof(char) * 2;
 138         } else {
 139             *q = *p;
 140         }
 141     }
 142     *q = '\0';
 143     return (buf);
 144 }
 145
 146 /*
 147  * rfc1738_escape - Returns a static buffer that contains the RFC
 148  * 1738 compliant, escaped version of the given url.
 149  */
 150 char *
 151 rfc1738_escape(const char *url)
 152 {
 153     return rfc1738_do_escape(url, 0);
 154 }
 155
 156 /*
 157  * rfc1738_escape_unescaped - Returns a static buffer that contains
 158  * the RFC 1738 compliant, escaped version of the given url.
 159  */
 160 char *
 161 rfc1738_escape_unescaped(const char *url)
 162 {
 163     return rfc1738_do_escape(url, -1);
 164 }
 165
 166 /*
 167  * rfc1738_escape_part - Returns a static buffer that contains the
 168  * RFC 1738 compliant, escaped version of the given url segment.
 169  */
 170 char *
 171 rfc1738_escape_part(const char *url)
 172 {
 173     return rfc1738_do_escape(url, 1);
 174 }
 175
 176 /*
 177  *  rfc1738_unescape() - Converts escaped characters (%xy numbers) in
 178  *  given the string.  %% is a %. %ab is the 8-bit hexadecimal number "ab"
 179  */
 180 void
 181 rfc1738_unescape(char *s)
 182 {
 183     char hexnum[3];
 184     int i, j;                   /* i is write, j is read */
 185     unsigned int x;
 186     for (i = j = 0; s[j]; i++, j++) {
 187         s[i] = s[j];
 188         if (s[i] != '%')
 189             continue;
 190         if (s[j + 1] == '%') {  /* %% case */
 191             j++;
 192             continue;
 193         }
 194         if (s[j + 1] && s[j + 2]) {
 195             if (s[j + 1] == '0' && s[j + 2] == '0') {   /* %00 case */
 196                 j += 2;
 197                 continue;
 198             }
 199             hexnum[0] = s[j + 1];
 200             hexnum[1] = s[j + 2];
 201             hexnum[2] = '\0';
 202             if (1 == sscanf(hexnum, "%x", &x)) {
 203                 s[i] = (char) (0x0ff & x);
 204                 j += 2;
 205             }
 206         }
 207     }
 208     s[i] = '\0';
 209 }