lib/html_quote.c

   1 /*
   2  * $Id$
   3  *
   4  * DEBUG:
   5  * AUTHOR: Robert Collins
   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  *  HTML defines these characters as special entities that should be quoted.
  48  */
  49 static struct {
  50     unsigned char code;
  51     const char *quote;
  52 } htmlstandardentities[] =
  53
  54 {
  55     /* NOTE: The quoted form MUST not be larger than 6 character.
  56      * see close to the MemPool commend below
  57      */
  58     {
  59         '<', "&lt;"
  60     },
  61     {
  62         '>', "&gt;"
  63     },
  64     {
  65         '"', "&quot;"
  66     },
  67     {
  68         '&', "&amp;"
  69     },
  70     {
  71         '\'', "&#39;"
  72     },
  73     {
  74         0, NULL
  75     }
  76 };
  77
  78 /*
  79  *  html_do_quote - Returns a static buffer containing the quoted
  80  *  string.
  81  */
  82 char *
  83 html_quote(const char *string)
  84 {
  85     static char *buf;
  86     static size_t bufsize = 0;
  87     const char *src;
  88     char *dst;
  89     int i;
  90
  91     /* XXX This really should be implemented using a MemPool, but
  92      * MemPools are not yet available in lib...
  93      */
  94     if (buf == NULL || strlen(string) * 6 > bufsize) {
  95         xfree(buf);
  96         bufsize = strlen(string) * 6 + 1;
  97         buf = xcalloc(bufsize, 1);
  98     }
  99     for (src = string, dst = buf; *src; src++) {
 100         const char *escape = NULL;
 101         const unsigned char ch = *src;
 102
 103         /* Walk thru the list of HTML Entities that must be quoted to
 104          * display safely
 105          */
 106         for (i = 0; htmlstandardentities[i].code; i++) {
 107             if (ch == htmlstandardentities[i].code) {
 108                 escape = htmlstandardentities[i].quote;
 109                 break;
 110             }
 111         }
 112         /* Encode control chars just to be on the safe side, and make
 113          * sure all 8-bit characters are encoded to protect from buggy
 114          * clients
 115          */
 116         if (!escape && (ch <= 0x1F || ch >= 0x7f) && ch != '\n' && ch != '\r' && ch != '\t') {
 117             static char dec_encoded[7];
 118             snprintf(dec_encoded, sizeof dec_encoded, "&#%3d;", (int) ch);
 119             escape = dec_encoded;
 120         }
 121         if (escape) {
 122             /* Ok, An escaped form was found above. Use it */
 123             strncpy(dst, escape, 6);
 124             dst += strlen(escape);
 125         } else {
 126             /* Apparently there is no need to escape this character */
 127             *dst++ = ch;
 128         }
 129     }
 130     /* Nullterminate and return the result */
 131     *dst = '\0';
 132     return (buf);
 133 }