lib/rfc1738.c

   1 /*
   2  * $Id: rfc1738.c,v 1.5 1996/09/17 16:32:26 wessels Exp $
   3  *
   4  * DEBUG:
   5  * AUTHOR: Harvest Derived
   6  *
   7  * SQUID Internet Object Cache  http://www.nlanr.net/Squid/
   8  * --------------------------------------------------------
   9  *
  10  *  Squid is the result of efforts by numerous individuals from the
  11  *  Internet community.  Development is led by Duane Wessels of the
  12  *  National Laboratory for Applied Network Research and funded by
  13  *  the National Science Foundation.
  14  *
  15  *  This program is free software; you can redistribute it and/or modify
  16  *  it under the terms of the GNU General Public License as published by
  17  *  the Free Software Foundation; either version 2 of the License, or
  18  *  (at your option) any later version.
  19  *
  20  *  This program is distributed in the hope that it will be useful,
  21  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  22  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  23  *  GNU General Public License for more details.
  24  *
  25  *  You should have received a copy of the GNU General Public License
  26  *  along with this program; if not, write to the Free Software
  27  *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  28  *
  29  */
  30
  31 /*
  32  * Copyright (c) 1994, 1995.  All rights reserved.
  33  *
  34  *   The Harvest software was developed by the Internet Research Task
  35  *   Force Research Group on Resource Discovery (IRTF-RD):
  36  *
  37  *         Mic Bowman of Transarc Corporation.
  38  *         Peter Danzig of the University of Southern California.
  39  *         Darren R. Hardy of the University of Colorado at Boulder.
  40  *         Udi Manber of the University of Arizona.
  41  *         Michael F. Schwartz of the University of Colorado at Boulder.
  42  *         Duane Wessels of the University of Colorado at Boulder.
  43  *
  44  *   This copyright notice applies to software in the Harvest
  45  *   ``src/'' directory only.  Users should consult the individual
  46  *   copyright notices in the ``components/'' subdirectories for
  47  *   copyright information about other software bundled with the
  48  *   Harvest source code distribution.
  49  *
  50  * TERMS OF USE
  51  *
  52  *   The Harvest software may be used and re-distributed without
  53  *   charge, provided that the software origin and research team are
  54  *   cited in any use of the system.  Most commonly this is
  55  *   accomplished by including a link to the Harvest Home Page
  56  *   (http://harvest.cs.colorado.edu/) from the query page of any
  57  *   Broker you deploy, as well as in the query result pages.  These
  58  *   links are generated automatically by the standard Broker
  59  *   software distribution.
  60  *
  61  *   The Harvest software is provided ``as is'', without express or
  62  *   implied warranty, and with no support nor obligation to assist
  63  *   in its use, correction, modification or enhancement.  We assume
  64  *   no liability with respect to the infringement of copyrights,
  65  *   trade secrets, or any patents, and are not responsible for
  66  *   consequential damages.  Proper use of the Harvest software is
  67  *   entirely the responsibility of the user.
  68  *
  69  * DERIVATIVE WORKS
  70  *
  71  *   Users may make derivative works from the Harvest software, subject
  72  *   to the following constraints:
  73  *
  74  *     - You must include the above copyright notice and these
  75  *       accompanying paragraphs in all forms of derivative works,
  76  *       and any documentation and other materials related to such
  77  *       distribution and use acknowledge that the software was
  78  *       developed at the above institutions.
  79  *
  80  *     - You must notify IRTF-RD regarding your distribution of
  81  *       the derivative work.
  82  *
  83  *     - You must clearly notify users that your are distributing
  84  *       a modified version and not the original Harvest software.
  85  *
  86  *     - Any derivative product is also subject to these copyright
  87  *       and use restrictions.
  88  *
  89  *   Note that the Harvest software is NOT in the public domain.  We
  90  *   retain copyright, as specified above.
  91  *
  92  * HISTORY OF FREE SOFTWARE STATUS
  93  *
  94  *   Originally we required sites to license the software in cases
  95  *   where they were going to build commercial products/services
  96  *   around Harvest.  In June 1995 we changed this policy.  We now
  97  *   allow people to use the core Harvest software (the code found in
  98  *   the Harvest ``src/'' directory) for free.  We made this change
  99  *   in the interest of encouraging the widest possible deployment of
 100  *   the technology.  The Harvest software is really a reference
 101  *   implementation of a set of protocols and formats, some of which
 102  *   we intend to standardize.  We encourage commercial
 103  *   re-implementations of code complying to this set of standards.
 104  */
 105
 106 #include "config.h"
 107
 108 #if HAVE_STDIO_H
 109 #include <stdio.h>
 110 #endif
 111 #if HAVE_STRING_H
 112 #include <string.h>
 113 #endif
 114
 115 #include "util.h"
 116 #define BIG_BUFSIZ (BUFSIZ * 4)
 117
 118 /*
 119  *  RFC 1738 defines that these characters should be escaped, as well
 120  *  any non-US-ASCII character or anything between 0x00 - 0x1F.
 121  */
 122 static char rfc1738_unsafe_chars[] =
 123 {
 124     (char) 0x3C,                /* < */
 125     (char) 0x3E,                /* > */
 126     (char) 0x22,                /* " */
 127     (char) 0x23,                /* # */
 128     (char) 0x25,                /* % */
 129     (char) 0x7B,                /* { */
 130     (char) 0x7D,                /* } */
 131     (char) 0x7C,                /* | */
 132     (char) 0x5C,                /* \ */
 133     (char) 0x5E,                /* ^ */
 134     (char) 0x7E,                /* ~ */
 135     (char) 0x5B,                /* [ */
 136     (char) 0x5D,                /* ] */
 137     (char) 0x60,                /* ` */
 138     (char) 0x27,                /* ' */
 139     (char) 0x20                 /* space */
 140 };
 141
 142 /*
 143  *  rfc1738_escape - Returns a static buffer contains the RFC 1738
 144  *  compliant, escaped version of the given url.
 145  */
 146 char *
 147 rfc1738_escape(char *url)
 148 {
 149     static char buf[BIG_BUFSIZ];
 150     char *p, *q;
 151     int i, do_escape;
 152
 153     for (p = url, q = &buf[0]; *p != '\0'; p++, q++) {
 154         do_escape = 0;
 155
 156         /* RFC 1738 defines these chars as unsafe */
 157         for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
 158             if (*p == rfc1738_unsafe_chars[i]) {
 159                 do_escape = 1;
 160                 break;
 161             }
 162         }
 163         /* RFC 1738 says any control chars (0x00-0x1F) are encoded */
 164         if ((unsigned char) *p <= (unsigned char) 0x1F) {
 165             do_escape = 1;
 166         }
 167         /* RFC 1738 says 0x7f is encoded */
 168         if (*p == (char) 0x7F) {
 169             do_escape = 1;
 170         }
 171         /* RFC 1738 says any non-US-ASCII are encoded */
 172         if (((unsigned char) *p >= (unsigned char) 0x80) &&
 173             ((unsigned char) *p <= (unsigned char) 0xFF)) {
 174             do_escape = 1;
 175         }
 176         /* Do the triplet encoding, or just copy the char */
 177         if (do_escape == 1) {
 178             (void) sprintf(q, "%%%02x", (unsigned char) *p);
 179             q += sizeof(char) * 2;
 180         } else {
 181             *q = *p;
 182         }
 183     }
 184     *q = '\0';
 185     return (buf);
 186 }
 187
 188 /*
 189  *  rfc1738_unescape() - Converts escaped characters (%xy numbers) in
 190  *  given the string.  %% is a %. %ab is the 8-bit hexadecimal number "ab"
 191  */
 192 void
 193 rfc1738_unescape(char *s)
 194 {
 195     char hexnum[3];
 196     int i, j;                   /* i is write, j is read */
 197     unsigned int x;
 198
 199     for (i = j = 0; s[j]; i++, j++) {
 200         s[i] = s[j];
 201         if (s[i] == '%') {
 202             hexnum[0] = s[++j];
 203             if (hexnum[0] != '%') {
 204                 hexnum[1] = s[++j];
 205                 hexnum[2] = '\0';
 206                 sscanf(hexnum, "%x", &x);
 207                 s[i] = (char) (0x0ff & x);
 208             } else {
 209                 s[i] = '%';
 210             }
 211         }
 212     }
 213     s[i] = '\0';
 214 }