lib/rfc1738.c

   1 /*
   2  * $Id: rfc1738.c,v 1.26 2003/12/19 06:12:40 wessels 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 #include "snprintf.h"
  46
  47 /*
  48  *  RFC 1738 defines that these characters should be escaped, as well
  49  *  any non-US-ASCII character or anything between 0x00 - 0x1F.
  50  */
  51 static char rfc1738_unsafe_chars[] =
  52 {
  53     (char) 0x3C,                /* < */
  54     (char) 0x3E,                /* > */
  55     (char) 0x22,                /* " */
  56     (char) 0x23,                /* # */
  57 #if 0                           /* done in code */
  58     (char) 0x25,                /* % */
  59 #endif
  60     (char) 0x7B,                /* { */
  61     (char) 0x7D,                /* } */
  62     (char) 0x7C,                /* | */
  63     (char) 0x5C,                /* \ */
  64     (char) 0x5E,                /* ^ */
  65     (char) 0x7E,                /* ~ */
  66     (char) 0x5B,                /* [ */
  67     (char) 0x5D,                /* ] */
  68     (char) 0x60,                /* ` */
  69     (char) 0x27,                /* ' */
  70     (char) 0x20                 /* space */
  71 };
  72
  73 static char rfc1738_reserved_chars[] =
  74 {
  75     (char) 0x3b,                /* ; */
  76     (char) 0x2f,                /* / */
  77     (char) 0x3f,                /* ? */
  78     (char) 0x3a,                /* : */
  79     (char) 0x40,                /* @ */
  80     (char) 0x3d,                /* = */
  81     (char) 0x26                 /* & */
  82 };
  83
  84 /*
  85  *  rfc1738_escape - Returns a static buffer contains the RFC 1738
  86  *  compliant, escaped version of the given url.
  87  */
  88 static char *
  89 rfc1738_do_escape(const char *url, int encode_reserved)
  90 {
  91     static char *buf;
  92     static size_t bufsize = 0;
  93     const char *p;
  94     char *q;
  95     unsigned int i, do_escape;
  96
  97     if (buf == NULL || strlen(url) * 3 > bufsize) {
  98         xfree(buf);
  99         bufsize = strlen(url) * 3 + 1;
 100         buf = xcalloc(bufsize, 1);
 101     }
 102     for (p = url, q = buf; *p != '\0'; p++, q++) {
 103         do_escape = 0;
 104
 105         /* RFC 1738 defines these chars as unsafe */
 106         for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
 107             if (*p == rfc1738_unsafe_chars[i]) {
 108                 do_escape = 1;
 109                 break;
 110             }
 111         }
 112         /* Handle % separately */
 113         if (encode_reserved >= 0 && *p == '%')
 114             do_escape = 1;
 115         /* RFC 1738 defines these chars as reserved */
 116         for (i = 0; i < sizeof(rfc1738_reserved_chars) && encode_reserved > 0; i++) {
 117             if (*p == rfc1738_reserved_chars[i]) {
 118                 do_escape = 1;
 119                 break;
 120             }
 121         }
 122         /* RFC 1738 says any control chars (0x00-0x1F) are encoded */
 123         if ((unsigned char) *p <= (unsigned char) 0x1F) {
 124             do_escape = 1;
 125         }
 126         /* RFC 1738 says 0x7f is encoded */
 127         if (*p == (char) 0x7F) {
 128             do_escape = 1;
 129         }
 130         /* RFC 1738 says any non-US-ASCII are encoded */
 131         if (((unsigned char) *p >= (unsigned char) 0x80)) {
 132             do_escape = 1;
 133         }
 134         /* Do the triplet encoding, or just copy the char */
 135         /* note: we do not need snprintf here as q is appropriately
 136          * allocated - KA */
 137
 138         if (do_escape == 1) {
 139             (void) sprintf(q, "%%%02x", (unsigned char) *p);
 140             q += sizeof(char) * 2;
 141         } else {
 142             *q = *p;
 143         }
 144     }
 145     *q = '\0';
 146     return (buf);
 147 }
 148
 149 /*
 150  * rfc1738_escape - Returns a static buffer that contains the RFC
 151  * 1738 compliant, escaped version of the given url.
 152  */
 153 char *
 154 rfc1738_escape(const char *url)
 155 {
 156     return rfc1738_do_escape(url, 0);
 157 }
 158
 159 /*
 160  * rfc1738_escape_unescaped - Returns a static buffer that contains
 161  * the RFC 1738 compliant, escaped version of the given url.
 162  */
 163 char *
 164 rfc1738_escape_unescaped(const char *url)
 165 {
 166     return rfc1738_do_escape(url, -1);
 167 }
 168
 169 /*
 170  * rfc1738_escape_part - Returns a static buffer that contains the
 171  * RFC 1738 compliant, escaped version of the given url segment.
 172  */
 173 char *
 174 rfc1738_escape_part(const char *url)
 175 {
 176     return rfc1738_do_escape(url, 1);
 177 }
 178
 179 /*
 180  *  rfc1738_unescape() - Converts escaped characters (%xy numbers) in
 181  *  given the string.  %% is a %. %ab is the 8-bit hexadecimal number "ab"
 182  */
 183 void
 184 rfc1738_unescape(char *s)
 185 {
 186     char hexnum[3];
 187     int i, j;                   /* i is write, j is read */
 188     unsigned int x;
 189     for (i = j = 0; s[j]; i++, j++) {
 190         s[i] = s[j];
 191         if (s[i] != '%')
 192             continue;
 193         if (s[j + 1] == '%') {  /* %% case */
 194             j++;
 195             continue;
 196         }
 197         if (s[j + 1] && s[j + 2]) {
 198             if (s[j + 1] == '0' && s[j + 2] == '0') {   /* %00 case */
 199                 j += 2;
 200                 continue;
 201             }
 202             hexnum[0] = s[j + 1];
 203             hexnum[1] = s[j + 2];
 204             hexnum[2] = '\0';
 205             if (1 == sscanf(hexnum, "%x", &x)) {
 206                 s[i] = (char) (0x0ff & x);
 207                 j += 2;
 208             }
 209         }
 210     }
 211     s[i] = '\0';
 212 }