/*
- * $Id: rfc1738.c,v 1.4 1996/09/14 08:50:50 wessels Exp $
+ * Copyright (C) 1996-2018 The Squid Software Foundation and contributors
*
- * DEBUG:
- * AUTHOR: Harvest Derived
- *
- * SQUID Internet Object Cache http://www.nlanr.net/Squid/
- * --------------------------------------------------------
- *
- * Squid is the result of efforts by numerous individuals from the
- * Internet community. Development is led by Duane Wessels of the
- * National Laboratory for Applied Network Research and funded by
- * the National Science Foundation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-/*
- * Copyright (c) 1994, 1995. All rights reserved.
- *
- * The Harvest software was developed by the Internet Research Task
- * Force Research Group on Resource Discovery (IRTF-RD):
- *
- * Mic Bowman of Transarc Corporation.
- * Peter Danzig of the University of Southern California.
- * Darren R. Hardy of the University of Colorado at Boulder.
- * Udi Manber of the University of Arizona.
- * Michael F. Schwartz of the University of Colorado at Boulder.
- * Duane Wessels of the University of Colorado at Boulder.
- *
- * This copyright notice applies to software in the Harvest
- * ``src/'' directory only. Users should consult the individual
- * copyright notices in the ``components/'' subdirectories for
- * copyright information about other software bundled with the
- * Harvest source code distribution.
- *
- * TERMS OF USE
- *
- * The Harvest software may be used and re-distributed without
- * charge, provided that the software origin and research team are
- * cited in any use of the system. Most commonly this is
- * accomplished by including a link to the Harvest Home Page
- * (http://harvest.cs.colorado.edu/) from the query page of any
- * Broker you deploy, as well as in the query result pages. These
- * links are generated automatically by the standard Broker
- * software distribution.
- *
- * The Harvest software is provided ``as is'', without express or
- * implied warranty, and with no support nor obligation to assist
- * in its use, correction, modification or enhancement. We assume
- * no liability with respect to the infringement of copyrights,
- * trade secrets, or any patents, and are not responsible for
- * consequential damages. Proper use of the Harvest software is
- * entirely the responsibility of the user.
- *
- * DERIVATIVE WORKS
- *
- * Users may make derivative works from the Harvest software, subject
- * to the following constraints:
- *
- * - You must include the above copyright notice and these
- * accompanying paragraphs in all forms of derivative works,
- * and any documentation and other materials related to such
- * distribution and use acknowledge that the software was
- * developed at the above institutions.
- *
- * - You must notify IRTF-RD regarding your distribution of
- * the derivative work.
- *
- * - You must clearly notify users that your are distributing
- * a modified version and not the original Harvest software.
- *
- * - Any derivative product is also subject to these copyright
- * and use restrictions.
- *
- * Note that the Harvest software is NOT in the public domain. We
- * retain copyright, as specified above.
- *
- * HISTORY OF FREE SOFTWARE STATUS
- *
- * Originally we required sites to license the software in cases
- * where they were going to build commercial products/services
- * around Harvest. In June 1995 we changed this policy. We now
- * allow people to use the core Harvest software (the code found in
- * the Harvest ``src/'' directory) for free. We made this change
- * in the interest of encouraging the widest possible deployment of
- * the technology. The Harvest software is really a reference
- * implementation of a set of protocols and formats, some of which
- * we intend to standardize. We encourage commercial
- * re-implementations of code complying to this set of standards.
+ * Squid software is distributed under GPLv2+ license and includes
+ * contributions from numerous individuals and organizations.
+ * Please see the COPYING and CONTRIBUTORS files for details.
*/
-#include "config.h"
+#include "squid.h"
+#include "rfc1738.h"
-#if HAVE_STDIO_H
-#include <stdio.h>
-#endif
#if HAVE_STRING_H
#include <string.h>
#endif
-#include "util.h"
-#define BIG_BUFSIZ (BUFSIZ * 4)
-
-/*
+/*
* RFC 1738 defines that these characters should be escaped, as well
* any non-US-ASCII character or anything between 0x00 - 0x1F.
*/
-static char rfc1738_unsafe_chars[] =
-{
- (char) 0x3C, /* < */
- (char) 0x3E, /* > */
- (char) 0x22, /* " */
- (char) 0x23, /* # */
- (char) 0x25, /* % */
- (char) 0x7B, /* { */
- (char) 0x7D, /* } */
- (char) 0x7C, /* | */
- (char) 0x5C, /* \ */
- (char) 0x5E, /* ^ */
- (char) 0x7E, /* ~ */
- (char) 0x5B, /* [ */
- (char) 0x5D, /* ] */
- (char) 0x60, /* ` */
- (char) 0x27, /* ' */
- (char) 0x20 /* space */
+static char rfc1738_unsafe_chars[] = {
+ (char) 0x3C, /* < */
+ (char) 0x3E, /* > */
+ (char) 0x22, /* " */
+ (char) 0x23, /* # */
+#if 0 /* done in code */
+ (char) 0x20, /* space */
+ (char) 0x25, /* % */
+#endif
+ (char) 0x7B, /* { */
+ (char) 0x7D, /* } */
+ (char) 0x7C, /* | */
+ (char) 0x5C, /* \ */
+ (char) 0x5E, /* ^ */
+ (char) 0x7E, /* ~ */
+ (char) 0x5B, /* [ */
+ (char) 0x5D, /* ] */
+ (char) 0x60, /* ` */
+ (char) 0x27 /* ' */
+};
+
+static char rfc1738_reserved_chars[] = {
+ (char) 0x3b, /* ; */
+ (char) 0x2f, /* / */
+ (char) 0x3f, /* ? */
+ (char) 0x3a, /* : */
+ (char) 0x40, /* @ */
+ (char) 0x3d, /* = */
+ (char) 0x26 /* & */
};
/*
- * rfc1738_escape - Returns a static buffer contains the RFC 1738
+ * rfc1738_escape - Returns a static buffer contains the RFC 1738
* compliant, escaped version of the given url.
*/
char *
-rfc1738_escape(char *url)
+rfc1738_do_escape(const char *url, int flags)
{
- static char buf[BIG_BUFSIZ];
- char *p, *q;
- int i, do_escape;
+ static char *buf;
+ static size_t bufsize = 0;
+ const char *src;
+ char *dst;
+ unsigned int i, do_escape;
+
+ if (buf == NULL || strlen(url) * 3 > bufsize) {
+ xfree(buf);
+ bufsize = strlen(url) * 3 + 1;
+ buf = (char*)xcalloc(bufsize, 1);
+ }
+ for (src = url, dst = buf; *src != '\0' && dst < (buf + bufsize - 1); src++, dst++) {
- for (p = url, q = &buf[0]; *p != '\0'; p++, q++) {
- do_escape = 0;
+ /* a-z, A-Z and 0-9 are SAFE. */
+ if ((*src >= 'a' && *src <= 'z') || (*src >= 'A' && *src <= 'Z') || (*src >= '0' && *src <= '9')) {
+ *dst = *src;
+ continue;
+ }
- /* RFC 1738 defines these chars as unsafe */
- for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
- if (*p == rfc1738_unsafe_chars[i]) {
- do_escape = 1;
- break;
- }
- }
- /* RFC 1738 says any control chars (0x00-0x1F) are encoded */
- if (*p <= (char) 0x1F) {
- do_escape = 1;
- }
- /* RFC 1738 says 0x7f is encoded */
- if (*p == (char) 0x7F) {
- do_escape = 1;
- }
- /* RFC 1738 says any non-US-ASCII are encoded */
- if ((*p >= (char) 0x80) && (*p <= (char) 0xFF)) {
- do_escape = 1;
- }
- /* Do the triplet encoding, or just copy the char */
- if (do_escape == 1) {
- (void) sprintf(q, "%%%02x", (unsigned char) *p);
- q += sizeof(char) * 2;
- } else {
- *q = *p;
- }
+ do_escape = 0;
+
+ /* RFC 1738 defines these chars as unsafe */
+ if ((flags & RFC1738_ESCAPE_UNSAFE)) {
+ for (i = 0; i < sizeof(rfc1738_unsafe_chars); i++) {
+ if (*src == rfc1738_unsafe_chars[i]) {
+ do_escape = 1;
+ break;
+ }
+ }
+ /* Handle % separately */
+ if (!(flags & RFC1738_ESCAPE_NOPERCENT) && *src == '%')
+ do_escape = 1;
+ /* Handle space separately */
+ else if (!(flags & RFC1738_ESCAPE_NOSPACE) && *src <= ' ')
+ do_escape = 1;
+ }
+ /* RFC 1738 defines these chars as reserved */
+ if ((flags & RFC1738_ESCAPE_RESERVED) && do_escape == 0) {
+ for (i = 0; i < sizeof(rfc1738_reserved_chars); i++) {
+ if (*src == rfc1738_reserved_chars[i]) {
+ do_escape = 1;
+ break;
+ }
+ }
+ }
+ if ((flags & RFC1738_ESCAPE_CTRLS) && do_escape == 0) {
+ /* RFC 1738 says any control chars (0x00-0x1F) are encoded */
+ if ((unsigned char) *src <= (unsigned char) 0x1F)
+ do_escape = 1;
+ /* RFC 1738 says 0x7f is encoded */
+ else if (*src == (char) 0x7F)
+ do_escape = 1;
+ /* RFC 1738 says any non-US-ASCII are encoded */
+ else if (((unsigned char) *src >= (unsigned char) 0x80))
+ do_escape = 1;
+ }
+ /* Do the triplet encoding, or just copy the char */
+ if (do_escape == 1) {
+ (void) snprintf(dst, (bufsize-(dst-buf)), "%%%02X", (unsigned char) *src);
+ dst += sizeof(char) * 2;
+ } else {
+ *dst = *src;
+ }
}
- *q = '\0';
+ *dst = '\0';
return (buf);
}
/*
- * rfc1738_unescape() - Converts escaped characters (%xy numbers) in
+ * Converts a ascii hex code into a binary character.
+ */
+static int
+fromhex(char ch)
+{
+ if (ch >= '0' && ch <= '9')
+ return ch - '0';
+ if (ch >= 'a' && ch <= 'f')
+ return ch - 'a' + 10;
+ if (ch >= 'A' && ch <= 'F')
+ return ch - 'A' + 10;
+ return -1;
+}
+
+/*
+ * rfc1738_unescape() - Converts escaped characters (%xy numbers) in
* given the string. %% is a %. %ab is the 8-bit hexadecimal number "ab"
*/
void
rfc1738_unescape(char *s)
{
- char hexnum[3];
- int i, j; /* i is write, j is read */
- unsigned int x;
-
+ int i, j; /* i is write, j is read */
for (i = j = 0; s[j]; i++, j++) {
- s[i] = s[j];
- if (s[i] == '%') {
- hexnum[0] = s[++j];
- if (hexnum[0] != '%') {
- hexnum[1] = s[++j];
- hexnum[2] = '\0';
- sscanf(hexnum, "%x", &x);
- s[i] = (char) (0x0ff & x);
- } else {
- s[i] = '%';
- }
- }
+ s[i] = s[j];
+ if (s[j] != '%') {
+ /* normal case, nothing more to do */
+ } else if (s[j + 1] == '%') { /* %% case */
+ j++; /* Skip % */
+ } else {
+ /* decode */
+ int v1, v2, x;
+ v1 = fromhex(s[j + 1]);
+ if (v1 < 0)
+ continue; /* non-hex or \0 */
+ v2 = fromhex(s[j + 2]);
+ if (v2 < 0)
+ continue; /* non-hex or \0 */
+ x = v1 << 4 | v2;
+ if (x > 0 && x <= 255) {
+ s[i] = x;
+ j += 2;
+ }
+ }
}
s[i] = '\0';
}
+
projects / thirdparty / squid.git / blobdiff