lib/util/rfc1738.c

   1 /*
   2  * Functions for RFC 3986 percent-encoding.
   3  *
   4  * NOTE:
   5  *
   6  * This file was originally imported from the Squid project but has been
   7  * significantly altered. The licence below is reproduced intact, but refers
   8  * to files in Squid's repository, not in Samba. See COPYING for the GPLv3
   9  * notice (being the later version mentioned below).
  10  */
  11
  12 /*
  13  * $Id$
  14  *
  15  * DEBUG:
  16  * AUTHOR: Harvest Derived
  17  *
  18  * SQUID Web Proxy Cache          http://www.squid-cache.org/
  19  * ----------------------------------------------------------
  20  *
  21  *  Squid is the result of efforts by numerous individuals from
  22  *  the Internet community; see the CONTRIBUTORS file for full
  23  *  details.   Many organizations have provided support for Squid's
  24  *  development; see the SPONSORS file for full details.  Squid is
  25  *  Copyrighted (C) 2001 by the Regents of the University of
  26  *  California; see the COPYRIGHT file for full details.  Squid
  27  *  incorporates software developed and/or copyrighted by other
  28  *  sources; see the CREDITS file for full details.
  29  *
  30  *  This program is free software; you can redistribute it and/or modify
  31  *  it under the terms of the GNU General Public License as published by
  32  *  the Free Software Foundation; either version 2 of the License, or
  33  *  (at your option) any later version.
  34  *
  35  *  This program is distributed in the hope that it will be useful,
  36  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  37  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  38  *  GNU General Public License for more details.
  39  *
  40  *  You should have received a copy of the GNU General Public License
  41  *  along with this program; if not, write to the Free Software
  42  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
  43  *
  44  */
  45
  46 #include "replace.h"
  47 #include <talloc.h>
  48 #include "lib/util/samba_util.h"
  49
  50 #define RFC1738_ENCODE 1
  51 #define RFC1738_RESERVED 2
  52
  53 /*
  54  * According to RFC 1738, "$-_.+!*'()," are not reserved or unsafe, but as
  55  * that has been obsolete since 2004, we sm instead for RFC 3986, where:
  56  *
  57  *  reserved =    : / ? # [ ] @ ! $ & ' ( ) * + , ; =
  58  *  unreserved = ALPHA DIGIT - . _ ~
  59  *
  60  * and whatever is not in either of those are what RFC 1738 called "unsafe",
  61  * meaning that they should are canonically but not mandatorily escaped.
  62  *
  63  * Characters below 0x20 or above 0x7E are always encoded.
  64  */
  65
  66 static const unsigned char escapees[127] = {
  67         [' '] = RFC1738_ENCODE,
  68         ['"'] = RFC1738_ENCODE,
  69         ['%'] = RFC1738_ENCODE,
  70         ['<'] = RFC1738_ENCODE,
  71         ['>'] = RFC1738_ENCODE,
  72         ['\\'] = RFC1738_ENCODE,
  73         ['^'] = RFC1738_ENCODE,
  74         ['`'] = RFC1738_ENCODE,
  75         ['{'] = RFC1738_ENCODE,
  76         ['|'] = RFC1738_ENCODE,
  77         ['}'] = RFC1738_ENCODE,
  78         /* reserved : / ? # [ ] @ ! $ & ' ( ) * + , ; = */
  79         [':'] = RFC1738_RESERVED,
  80         ['/'] = RFC1738_RESERVED,
  81         ['?'] = RFC1738_RESERVED,
  82         ['#'] = RFC1738_RESERVED,
  83         ['['] = RFC1738_RESERVED,
  84         [']'] = RFC1738_RESERVED,
  85         ['@'] = RFC1738_RESERVED,
  86         ['!'] = RFC1738_RESERVED,
  87         ['$'] = RFC1738_RESERVED,
  88         ['&'] = RFC1738_RESERVED,
  89         ['\''] = RFC1738_RESERVED,
  90         ['('] = RFC1738_RESERVED,
  91         [')'] = RFC1738_RESERVED,
  92         ['*'] = RFC1738_RESERVED,
  93         ['+'] = RFC1738_RESERVED,
  94         [','] = RFC1738_RESERVED,
  95         [';'] = RFC1738_RESERVED,
  96         ['='] = RFC1738_RESERVED,
  97 };
  98
  99 /*
 100  *  rfc1738_do_escape - fills a preallocated buffer with an escaped version of
 101  *  the given string.
 102  *
 103  *  For canonical escaping, mask should be RFC1738_ENCODE | RFC1738_RESERVED.
 104  *  For mandatory escaping, mask should be RFC1738_RESERVED.
 105  */
 106 static char *
 107 rfc1738_do_escape(char *buf, size_t bufsize,
 108                   const char *url, size_t len, unsigned char mask)
 109 {
 110         size_t i;
 111         size_t j = 0;
 112         for (i = 0; i < len; i++) {
 113                 unsigned int c = (unsigned char) url[i];
 114                 if (c > 126 || c < 32 || (escapees[c] & mask)) {
 115                         if (j + 3 >= bufsize) {
 116                                 return NULL;
 117                         }
 118                         (void) snprintf(&buf[j], 4, "%%%02X", c);
 119                         j += 3;
 120                 } else {
 121                         if (j + 1 >= bufsize) {
 122                                 return NULL;
 123                         }
 124                         buf[j] = c;
 125                         j++;
 126                 }
 127         }
 128         buf[j] = '\0';
 129         return buf;
 130 }
 131
 132 /*
 133  * rfc1738_escape_part - Returns a talloced buffer that contains the RFC 3986
 134  * compliant, escaped version of the given url segment.
 135  */
 136 char *
 137 rfc1738_escape_part(TALLOC_CTX *mem_ctx, const char *url)
 138 {
 139         size_t bufsize = 0;
 140         char *buf = NULL;
 141
 142         size_t len = strlen(url);
 143         if (len >= SIZE_MAX / 3) {
 144                 return NULL;
 145         }
 146
 147         bufsize = len * 3 + 1;
 148         buf = talloc_array(mem_ctx, char, bufsize);
 149         if (buf == NULL) {
 150                 return NULL;
 151         }
 152
 153         talloc_set_name_const(buf, buf);
 154
 155         return rfc1738_do_escape(buf, bufsize, url, len,
 156                                  RFC1738_ENCODE | RFC1738_RESERVED);
 157 }
 158
 159 /*
 160  * rfc1738_unescape() - Converts url-escaped characters in the string.
 161  *
 162  * The two characters following a '%' in a string should be hex digits that
 163  * describe an encoded byte. For example, "%25" is hex 0x25 or '%' in ASCII;
 164  * this is the only way to include a % in the unescaped string. Any character
 165  * can be escaped, including plain letters (e.g. "%61" for "a"). Anything
 166  * other than 2 hex characters following the % is an error.
 167  *
 168  * The conversion is done in-place, which is always safe as unescapes can only
 169  * shorten the string.
 170  *
 171  * Returns a pointer to the end of the string (that is, the '\0' byte), or
 172  * NULL on error, at which point s is in an undefined state.
 173  *
 174  * Note that after `char *e = rfc_unescape(s)`, `strlen(s)` will not equal
 175  * `e - s` if s originally contained "%00". You might want to check for this.
 176  */
 177
 178 _PUBLIC_ char *rfc1738_unescape(char *s)
 179 {
 180         size_t i, j;        /* i is write, j is read */
 181         for (i = 0, j = 0; s[j] != '\0'; i++, j++) {
 182                 if (s[j] == '%') {
 183                         uint8_t v;
 184                         bool ok;
 185
 186                         ok = hex_byte(&s[j+1], &v);
 187                         if (!ok) {
 188                                 return NULL;
 189                         }
 190                         j += 2; /* OK; hex_byte() has checked ahead */
 191                         s[i] = (unsigned char)v;
 192                 } else {
 193                         s[i] = s[j];
 194                 }
 195         }
 196         s[i] = '\0';
 197         return s + i;
 198 }