-const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.7 2002/03/26 22:29:55 swa Exp $";
+const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.15 2007/01/28 16:11:23 fabiankeil Exp $";
/*********************************************************************
*
* File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $
* Purpose : Declares functions to match URLs against URL
* patterns.
*
- * Copyright : Written by and Copyright (C) 2001 the SourceForge
+ * Copyright : Written by and Copyright (C) 2001-2003, 2006-2007 the SourceForge
* Privoxy team. http://www.privoxy.org/
*
* Based on the Internet Junkbuster originally written
*
* Revisions :
* $Log: urlmatch.c,v $
+ * Revision 1.15 2007/01/28 16:11:23 fabiankeil
+ * Accept WebDAV methods for subversion
+ * in parse_http_request(). Closes FR 1581425.
+ *
+ * Revision 1.14 2007/01/06 14:23:56 fabiankeil
+ * Fix gcc43 warnings. Mark *csp as immutable
+ * for parse_http_url() and url_match().
+ * Replace a sprintf call with snprintf.
+ *
+ * Revision 1.13 2006/12/06 19:50:54 fabiankeil
+ * parse_http_url() now handles intercepted
+ * HTTP request lines as well. Moved parts
+ * of parse_http_url()'s code into
+ * init_domain_components() so that it can
+ * be reused in chat().
+ *
+ * Revision 1.12 2006/07/18 14:48:47 david__schmidt
+ * Reorganizing the repository: swapping out what was HEAD (the old 3.1 branch)
+ * with what was really the latest development (the v_3_0_branch branch)
+ *
+ * Revision 1.10.2.7 2003/05/17 15:57:24 oes
+ * - parse_http_url now checks memory allocation failure for
+ * duplication of "*" URL and rejects "*something" URLs
+ * Closes bug #736344
+ * - Added a comment to what might look like a bug in
+ * create_url_spec (see !bug #736931)
+ * - Comment cosmetics
+ *
+ * Revision 1.10.2.6 2003/05/07 12:39:48 oes
+ * Fix typo: Default port for https URLs is 443, not 143.
+ * Thanks to Scott Tregear for spotting this one.
+ *
+ * Revision 1.10.2.5 2003/02/28 13:09:29 oes
+ * Fixed a rare double free condition as per Bug #694713
+ *
+ * Revision 1.10.2.4 2003/02/28 12:57:44 oes
+ * Moved freeing of http request structure to its owner
+ * as per Dan Price's observations in Bug #694713
+ *
+ * Revision 1.10.2.3 2002/11/12 16:50:40 oes
+ * Fixed memory leak in parse_http_request() reported by Oliver Stoeneberg. Fixes bug #637073
+ *
+ * Revision 1.10.2.2 2002/09/25 14:53:15 oes
+ * Added basic support for OPTIONS and TRACE HTTP methods:
+ * parse_http_url now recognizes the "*" URI as well as
+ * the OPTIONS and TRACE method keywords.
+ *
+ * Revision 1.10.2.1 2002/06/06 19:06:44 jongfoster
+ * Adding support for proprietary Microsoft WebDAV extensions
+ *
+ * Revision 1.10 2002/05/12 21:40:37 jongfoster
+ * - Removing some unused code
+ *
+ * Revision 1.9 2002/04/04 00:36:36 gliptak
+ * always use pcre for matching
+ *
+ * Revision 1.8 2002/04/03 23:32:47 jongfoster
+ * Fixing memory leak on error
+ *
* Revision 1.7 2002/03/26 22:29:55 swa
* we have a new homepage!
*
const char urlmatch_h_rcs[] = URLMATCH_H_VERSION;
-/* Fix a problem with Solaris. There should be no effect on other
- * platforms.
- * Solaris's isspace() is a macro which uses it's argument directly
- * as an array index. Therefore we need to make sure that high-bit
- * characters generate +ve values, and ideally we also want to make
- * the argument match the declared parameter type of "int".
- *
- * Why did they write a character function that can't take a simple
- * "char" argument? Doh!
- */
-#define ijb_isupper(__X) isupper((int)(unsigned char)(__X))
-#define ijb_tolower(__X) tolower((int)(unsigned char)(__X))
-
/*********************************************************************
*
http->dcount = 0;
}
+/*********************************************************************
+ *
+ * Function : init_domain_components
+ *
+ * Description : Splits the domain name so we can compare it
+ * against wildcards. It used to be part of
+ * parse_http_url, but was separated because the
+ * same code is required in chat in case of
+ * intercepted requests.
+ *
+ * Parameters :
+ * 1 : http = pointer to the http structure to hold elements.
+ *
+ * Returns : JB_ERR_OK on success
+ * JB_ERR_MEMORY on out of memory
+ * JB_ERR_PARSE on malformed command/URL
+ * or >100 domains deep.
+ *
+ *********************************************************************/
+jb_err init_domain_components(struct http_request *http)
+{
+ char *vec[BUFFER_SIZE];
+ size_t size;
+ char *p;
+
+ http->dbuffer = strdup(http->host);
+ if (NULL == http->dbuffer)
+ {
+ return JB_ERR_MEMORY;
+ }
+
+ /* map to lower case */
+ for (p = http->dbuffer; *p ; p++)
+ {
+ *p = (char)tolower((int)(unsigned char)*p);
+ }
+
+ /* split the domain name into components */
+ http->dcount = ssplit(http->dbuffer, ".", vec, SZ(vec), 1, 1);
+
+ if (http->dcount <= 0)
+ {
+ /*
+ * Error: More than SZ(vec) components in domain
+ * or: no components in domain
+ */
+ log_error(LOG_LEVEL_ERROR, "More than SZ(vec) components in domain or none at all.");
+ return JB_ERR_PARSE;
+ }
+
+ /* save a copy of the pointers in dvec */
+ size = (size_t)http->dcount * sizeof(*http->dvec);
+
+ http->dvec = (char **)malloc(size);
+ if (NULL == http->dvec)
+ {
+ return JB_ERR_MEMORY;
+ }
+
+ memcpy(http->dvec, vec, size);
+
+ return JB_ERR_OK;
+}
/*********************************************************************
*
*
* Returns : JB_ERR_OK on success
* JB_ERR_MEMORY on out of memory
- * JB_ERR_CGI_PARAMS on malformed command/URL
- * or >100 domains deep.
+ * JB_ERR_PARSE on malformed command/URL
+ * or >100 domains deep.
*
*********************************************************************/
jb_err parse_http_url(const char * url,
struct http_request *http,
- struct client_state *csp)
+ const struct client_state *csp)
{
+ int host_available = 1; /* A proxy can dream. */
+
/*
* Zero out the results structure
*/
}
+ /*
+ * Check for * URI. If found, we're done.
+ */
+ if (*http->url == '*')
+ {
+ if ( NULL == (http->path = strdup("*"))
+ || NULL == (http->hostport = strdup("")) )
+ {
+ return JB_ERR_MEMORY;
+ }
+ if (http->url[1] != '\0')
+ {
+ return JB_ERR_PARSE;
+ }
+ return JB_ERR_OK;
+ }
+
+
/*
* Split URL into protocol,hostport,path.
*/
url_noproto += 8;
http->ssl = 1;
}
+ else if (*url_noproto == '/')
+ {
+ /*
+ * Short request line without protocol and host.
+ * Most likely because the client's request
+ * was intercepted and redirected into Privoxy.
+ */
+ http->ssl = 0;
+ http->host = NULL;
+ host_available = 0;
+ }
else
{
http->ssl = 0;
http->hostport = strdup(url_noproto);
}
- free(buf);
+ freez(buf);
if ( (http->path == NULL)
|| (http->hostport == NULL))
{
- free(buf);
- free_http_request(http);
return JB_ERR_MEMORY;
}
}
+ if (!host_available)
+ {
+ /* Without host, there is nothing left to do here */
+ return JB_ERR_OK;
+ }
/*
* Split hostport into user/password (ignored), host, port.
buf = strdup(http->hostport);
if (buf == NULL)
{
- free_http_request(http);
return JB_ERR_MEMORY;
}
else
{
/* No port specified. */
- http->port = (http->ssl ? 143 : 80);
+ http->port = (http->ssl ? 443 : 80);
}
http->host = strdup(host);
if (http->host == NULL)
{
- free_http_request(http);
return JB_ERR_MEMORY;
}
}
-
/*
* Split domain name so we can compare it against wildcards
*/
- {
- char *vec[BUFFER_SIZE];
- size_t size;
- char *p;
-
- http->dbuffer = strdup(http->host);
- if (NULL == http->dbuffer)
- {
- free_http_request(http);
- return JB_ERR_MEMORY;
- }
-
- /* map to lower case */
- for (p = http->dbuffer; *p ; p++)
- {
- *p = tolower((int)(unsigned char)*p);
- }
+ return init_domain_components(http);
- /* split the domain name into components */
- http->dcount = ssplit(http->dbuffer, ".", vec, SZ(vec), 1, 1);
-
- if (http->dcount <= 0)
- {
- /*
- * Error: More than SZ(vec) components in domain
- * or: no components in domain
- */
- free_http_request(http);
- return JB_ERR_PARSE;
- }
-
- /* save a copy of the pointers in dvec */
- size = http->dcount * sizeof(*http->dvec);
-
- http->dvec = (char **)malloc(size);
- if (NULL == http->dvec)
- {
- free_http_request(http);
- return JB_ERR_MEMORY;
- }
-
- memcpy(http->dvec, vec, size);
- }
-
-
- return JB_ERR_OK;
}
*********************************************************************/
jb_err parse_http_request(const char *req,
struct http_request *http,
- struct client_state *csp)
+ const struct client_state *csp)
{
char *buf;
char *v[10];
|| (0 == strcmpic(v[0], "post"))
|| (0 == strcmpic(v[0], "put"))
|| (0 == strcmpic(v[0], "delete"))
+ || (0 == strcmpic(v[0], "options"))
+ || (0 == strcmpic(v[0], "trace"))
/* or a webDAV extension (RFC2518) */
|| (0 == strcmpic(v[0], "propfind"))
|| (0 == strcmpic(v[0], "mkcol"))
|| (0 == strcmpic(v[0], "lock"))
|| (0 == strcmpic(v[0], "unlock"))
+
+ /* Or a Microsoft webDAV extension for Exchange 2000. See: */
+ /* http://lists.w3.org/Archives/Public/w3c-dist-auth/2002JanMar/0001.html */
+ /* http://msdn.microsoft.com/library/en-us/wss/wss/_webdav_methods.asp */
+ || (0 == strcmpic(v[0], "bcopy"))
+ || (0 == strcmpic(v[0], "bmove"))
+ || (0 == strcmpic(v[0], "bdelete"))
+ || (0 == strcmpic(v[0], "bpropfind"))
+ || (0 == strcmpic(v[0], "bproppatch"))
+
+ /* Or another Microsoft webDAV extension for Exchange 2000. See: */
+ /* http://systems.cs.colorado.edu/grunwald/MobileComputing/Papers/draft-cohen-gena-p-base-00.txt */
+ /* http://lists.w3.org/Archives/Public/w3c-dist-auth/2002JanMar/0001.html */
+ /* http://msdn.microsoft.com/library/en-us/wss/wss/_webdav_methods.asp */
+ || (0 == strcmpic(v[0], "subscribe"))
+ || (0 == strcmpic(v[0], "unsubscribe"))
+ || (0 == strcmpic(v[0], "notify"))
+ || (0 == strcmpic(v[0], "poll"))
+
+ /*
+ * Or yet another WebDAV extension, this time for
+ * Web Distributed Authoring and Versioning (RFC3253)
+ */
+ || (0 == strcmpic(v[0], "version-control"))
+ || (0 == strcmpic(v[0], "report"))
+ || (0 == strcmpic(v[0], "checkout"))
+ || (0 == strcmpic(v[0], "checkin"))
+ || (0 == strcmpic(v[0], "uncheckout"))
+ || (0 == strcmpic(v[0], "mkworkspace"))
+ || (0 == strcmpic(v[0], "update"))
+ || (0 == strcmpic(v[0], "label"))
+ || (0 == strcmpic(v[0], "merge"))
+ || (0 == strcmpic(v[0], "baseline-control"))
+ || (0 == strcmpic(v[0], "mkactivity"))
)
{
/* Normal */
else
{
/* Unknown HTTP method */
+ log_error(LOG_LEVEL_ERROR, "Unknown HTTP method detected: %s", v[0]);
free(buf);
return JB_ERR_PARSE;
}
|| (http->ver == NULL) )
{
free(buf);
- free_http_request(http);
return JB_ERR_MEMORY;
}
+ free(buf);
return JB_ERR_OK;
+
}
* Function : create_url_spec
*
* Description : Creates a "url_spec" structure from a string.
- * When finished, free with unload_url().
+ * When finished, free with free_url_spec().
*
* Parameters :
* 1 : url = Target url_spec to be filled in. Will be
assert(url);
assert(buf);
- /* Zero memory */
+ /*
+ * Zero memory
+ */
memset(url, '\0', sizeof(*url));
- /* save a copy of the orignal specification */
+ /*
+ * Save a copy of the orignal specification
+ */
if ((url->spec = strdup(buf)) == NULL)
{
return JB_ERR_MEMORY;
url->path = NULL;
url->pathlen = 0;
}
-#ifdef REGEX
if (url->path)
{
int errcode;
return JB_ERR_MEMORY;
}
- sprintf(rebuf, "^(%s)", url->path);
+ snprintf(rebuf, sizeof(rebuf), "^(%s)", url->path);
errcode = regcomp(url->preg, rebuf,
(REG_EXTENDED|REG_NOSUB|REG_ICASE));
return JB_ERR_PARSE;
}
}
-#endif
if ((p = strchr(buf, ':')) == NULL)
{
url->port = 0;
char *v[150];
size_t size;
- /* Parse domain part */
+ /*
+ * Parse domain part
+ */
if (buf[strlen(buf) - 1] == '.')
{
url->unanchored |= ANCHOR_RIGHT;
url->unanchored |= ANCHOR_LEFT;
}
- /* split domain into components */
-
+ /*
+ * Split domain into components
+ */
url->dbuffer = strdup(buf);
if (NULL == url->dbuffer)
{
freez(url->spec);
freez(url->path);
-#ifdef REGEX
regfree(url->preg);
freez(url->preg);
-#endif /* def REGEX */
return JB_ERR_MEMORY;
}
- /* map to lower case */
+ /*
+ * Map to lower case
+ */
for (p = url->dbuffer; *p ; p++)
{
- *p = tolower((int)(unsigned char)*p);
+ *p = (char)tolower((int)(unsigned char)*p);
}
- /* split the domain name into components */
+ /*
+ * Split the domain name into components
+ */
url->dcount = ssplit(url->dbuffer, ".", v, SZ(v), 1, 1);
if (url->dcount < 0)
{
freez(url->spec);
freez(url->path);
-#ifdef REGEX
regfree(url->preg);
freez(url->preg);
-#endif /* def REGEX */
freez(url->dbuffer);
url->dcount = 0;
return JB_ERR_MEMORY;
else if (url->dcount != 0)
{
- /* save a copy of the pointers in dvec */
- size = url->dcount * sizeof(*url->dvec);
+ /*
+ * Save a copy of the pointers in dvec
+ */
+ size = (size_t)url->dcount * sizeof(*url->dvec);
url->dvec = (char **)malloc(size);
if (NULL == url->dvec)
{
freez(url->spec);
freez(url->path);
-#ifdef REGEX
regfree(url->preg);
freez(url->preg);
-#endif /* def REGEX */
freez(url->dbuffer);
url->dcount = 0;
return JB_ERR_MEMORY;
memcpy(url->dvec, v, size);
}
+ /*
+ * else dcount == 0 in which case we needn't do anything,
+ * since dvec will never be accessed and the pattern will
+ * match all domains.
+ */
}
return JB_ERR_OK;
freez(url->dbuffer);
freez(url->dvec);
freez(url->path);
-#ifdef REGEX
if (url->preg)
{
regfree(url->preg);
freez(url->preg);
}
-#endif
-
}
return ((pattern->port == 0) || (pattern->port == url->port))
&& ((pattern->dbuffer == NULL) || (domain_match(pattern, url) == 0))
&& ((pattern->path == NULL) ||
-#ifdef REGEX
(regexec(pattern->preg, url->path, 0, NULL, 0) == 0)
-#else
- (strncmp(pattern->path, url->path, pattern->pathlen) == 0)
-#endif
);
}
projects / privoxy.git / blobdiff