lib/util/rfc1738.c

   1 /*
   2  * NOTE:
   3  *
   4  * This file imported from the Squid project.  The licence below is
   5  * reproduced intact, but refers to files in Squid's repository, not
   6  * in Samba.  See COPYING for the GPLv3 notice (being the later
   7  * version mentioned below).
   8  *
   9  * This file has also been modified, in particular to use talloc to
  10  * allocate in rfc1738_escape()
  11  *
  12  * - Andrew Bartlett Oct-2009
  13  *
  14  */
  15
  16
  17 /*
  18  * $Id$
  19  *
  20  * DEBUG:
  21  * AUTHOR: Harvest Derived
  22  *
  23  * SQUID Web Proxy Cache          http://www.squid-cache.org/
  24  * ----------------------------------------------------------
  25  *
  26  *  Squid is the result of efforts by numerous individuals from
  27  *  the Internet community; see the CONTRIBUTORS file for full
  28  *  details.   Many organizations have provided support for Squid's
  29  *  development; see the SPONSORS file for full details.  Squid is
  30  *  Copyrighted (C) 2001 by the Regents of the University of
  31  *  California; see the COPYRIGHT file for full details.  Squid
  32  *  incorporates software developed and/or copyrighted by other
  33  *  sources; see the CREDITS file for full details.
  34  *
  35  *  This program is free software; you can redistribute it and/or modify
  36  *  it under the terms of the GNU General Public License as published by
  37  *  the Free Software Foundation; either version 2 of the License, or
  38  *  (at your option) any later version.
  39  *
  40  *  This program is distributed in the hope that it will be useful,
  41  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  42  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  43  *  GNU General Public License for more details.
  44  *
  45  *  You should have received a copy of the GNU General Public License
  46  *  along with this program; if not, write to the Free Software
  47  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
  48  *
  49  */
  50
  51 #include "includes.h"
  52
  53 #include "util.h"
  54
  55 /*
  56  *  RFC 1738 defines that these characters should be escaped, as well
  57  *  any non-US-ASCII character or anything between 0x00 - 0x1F.
  58  */
  59 static char rfc1738_unsafe_chars[] = {
  60     (char) 0x3C,                /* < */
  61     (char) 0x3E,                /* > */
  62     (char) 0x22,                /* " */
  63     (char) 0x23,                /* # */
  64 #if 0                           /* done in code */
  65     (char) 0x25,                /* % */
  66 #endif
  67     (char) 0x7B,                /* { */
  68     (char) 0x7D,                /* } */
  69     (char) 0x7C,                /* | */
  70     (char) 0x5C,                /* \ */
  71     (char) 0x5E,                /* ^ */
  72     (char) 0x7E,                /* ~ */
  73     (char) 0x5B,                /* [ */
  74     (char) 0x5D,                /* ] */
  75     (char) 0x60,                /* ` */
  76     (char) 0x27,                /* ' */
  77     (char) 0x20                 /* space */
  78 };
  79
  80 static char rfc1738_reserved_chars[] = {
  81     (char) 0x3b,                /* ; */
  82     (char) 0x2f,                /* / */
  83     (char) 0x3f,                /* ? */
  84     (char) 0x3a,                /* : */
  85     (char) 0x40,                /* @ */
  86     (char) 0x3d,                /* = */
  87     (char) 0x26                 /* & */
  88 };
  89
  90 /*
  91  *  rfc1738_escape - Returns a static buffer contains the RFC 1738
  92  *  compliant, escaped version of the given url.
  93  *
  94  */
  95 static char *
  96 rfc1738_do_escape(TALLOC_CTX *mem_ctx, const char *url, int encode_reserved)
  97 {
  98     size_t bufsize = 0;
  99     const char *p;
 100     char *buf;
 101     char *q;
 102     unsigned int i, do_escape;
 103
 104     bufsize = strlen(url) * 3 + 1;
 105     buf = talloc_array(mem_ctx, char, bufsize);
 106     if (!buf) {
 107             return NULL;
 108     }
 109
 110     talloc_set_name_const(buf, buf);
 111     buf[0] = '\0';
 112
 113     for (p = url, q = buf; *p != '\0' && q < (buf + bufsize - 1); p++, q++) {
 114         do_escape = 0;
 115
 116         /* RFC 1738 defines these chars as unsafe */
 117         for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
 118             if (*p == rfc1738_unsafe_chars[i]) {
 119                 do_escape = 1;
 120                 break;
 121             }
 122         }
 123         /* Handle % separately */
 124         if (encode_reserved >= 0 && *p == '%')
 125             do_escape = 1;
 126         /* RFC 1738 defines these chars as reserved */
 127         for (i = 0; i < sizeof(rfc1738_reserved_chars) && encode_reserved > 0; i++) {
 128             if (*p == rfc1738_reserved_chars[i]) {
 129                 do_escape = 1;
 130                 break;
 131             }
 132         }
 133         /* RFC 1738 says any control chars (0x00-0x1F) are encoded */
 134         if ((unsigned char) *p <= (unsigned char) 0x1F) {
 135             do_escape = 1;
 136         }
 137         /* RFC 1738 says 0x7f is encoded */
 138         if (*p == (char) 0x7F) {
 139             do_escape = 1;
 140         }
 141         /* RFC 1738 says any non-US-ASCII are encoded */
 142         if (((unsigned char) *p >= (unsigned char) 0x80)) {
 143             do_escape = 1;
 144         }
 145         /* Do the triplet encoding, or just copy the char */
 146         /* note: while we do not need snprintf here as q is appropriately
 147          * allocated, Samba does to avoid our macro banning it -- abartlet */
 148
 149         if (do_escape == 1) {
 150                 (void) snprintf(q, 4, "%%%02X", (unsigned char) *p);
 151             q += sizeof(char) * 2;
 152         } else {
 153             *q = *p;
 154         }
 155     }
 156     *q = '\0';
 157     return (buf);
 158 }
 159
 160 /*
 161  * rfc1738_escape - Returns a buffer that contains the RFC
 162  * 1738 compliant, escaped version of the given url. (escapes unsafe and % characters)
 163  */
 164 char *
 165 rfc1738_escape(TALLOC_CTX *mem_ctx, const char *url)
 166 {
 167         return rfc1738_do_escape(mem_ctx, url, 0);
 168 }
 169
 170 /*
 171  * rfc1738_escape_unescaped - Returns a buffer that contains
 172  * the RFC 1738 compliant, escaped version of the given url (escapes unsafe chars only)
 173  */
 174 char *
 175 rfc1738_escape_unescaped(TALLOC_CTX *mem_ctx, const char *url)
 176 {
 177         return rfc1738_do_escape(mem_ctx, url, -1);
 178 }
 179
 180 /*
 181  * rfc1738_escape_part - Returns a buffer that contains the RFC
 182  * 1738 compliant, escaped version of the given url segment. (escapes
 183  * unsafe, reserved and % chars) It would mangle the :// in http://,
 184  * and mangle paths (because of /).
 185  */
 186 char *
 187 rfc1738_escape_part(TALLOC_CTX *mem_ctx, const char *url)
 188 {
 189         return rfc1738_do_escape(mem_ctx, url, 1);
 190 }
 191
 192 /*
 193  *  rfc1738_unescape() - Converts escaped characters (%xy numbers) in
 194  *  given the string.  %% is a %. %ab is the 8-bit hexadecimal number "ab"
 195  */
 196 _PUBLIC_ void
 197 rfc1738_unescape(char *s)
 198 {
 199     char hexnum[3];
 200     int i, j;                   /* i is write, j is read */
 201     unsigned int x;
 202     for (i = j = 0; s[j]; i++, j++) {
 203         s[i] = s[j];
 204         if (s[i] != '%')
 205             continue;
 206         if (s[j + 1] == '%') {  /* %% case */
 207             j++;
 208             continue;
 209         }
 210         if (s[j + 1] && s[j + 2]) {
 211             if (s[j + 1] == '0' && s[j + 2] == '0') {   /* %00 case */
 212                 j += 2;
 213                 continue;
 214             }
 215             hexnum[0] = s[j + 1];
 216             hexnum[1] = s[j + 2];
 217             hexnum[2] = '\0';
 218             if (1 == sscanf(hexnum, "%x", &x)) {
 219                 s[i] = (char) (0x0ff & x);
 220                 j += 2;
 221             }
 222         }
 223     }
 224     s[i] = '\0';
 225 }