-const char urlmatch_rcs[] = "$Id: urlmatch.c JGF $";
+const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.9 2002/04/04 00:36:36 gliptak Exp $";
/*********************************************************************
*
* File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $
* patterns.
*
* Copyright : Written by and Copyright (C) 2001 the SourceForge
- * IJBSWA team. http://ijbswa.sourceforge.net
+ * Privoxy team. http://www.privoxy.org/
*
* Based on the Internet Junkbuster originally written
* by and Copyright (C) 1997 Anonymous Coders and
*
* Revisions :
* $Log: urlmatch.c,v $
+ * 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!
+ *
+ * Revision 1.6 2002/03/24 13:25:43 swa
+ * name change related issues
+ *
+ * Revision 1.5 2002/03/13 00:27:05 jongfoster
+ * Killing warnings
+ *
+ * Revision 1.4 2002/03/07 03:46:17 oes
+ * Fixed compiler warnings
+ *
+ * Revision 1.3 2002/03/03 14:51:11 oes
+ * Fixed CLF logging: Added ocmd member for client's request to struct http_request
+ *
+ * Revision 1.2 2002/01/21 00:14:09 jongfoster
+ * Correcting comment style
+ * Fixing an uninitialized memory bug in create_url_spec()
+ *
+ * Revision 1.1 2002/01/17 20:53:46 jongfoster
+ * Moving all our URL and URL pattern parsing code to the same file - it
+ * was scattered around in filters.c, loaders.c and parsers.c.
+ *
+ * Providing a single, simple url_match(pattern,url) function - rather than
+ * the 3-line match routine which was repeated all over the place.
+ *
+ * Renaming free_url to free_url_spec, since it frees a struct url_spec.
+ *
+ * Providing parse_http_url() so that URLs can be parsed without faking a
+ * HTTP request line for parse_http_request() or repeating the parsing
+ * code (both of which were techniques that were actually in use).
+ *
+ * Standardizing that struct http_request is used to represent a URL, and
+ * struct url_spec is used to represent a URL pattern. (Before, URLs were
+ * represented as seperate variables and a partially-filled-in url_spec).
+ *
*
*********************************************************************/
\f
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))
-
/*********************************************************************
*
assert(http);
freez(http->cmd);
+ freez(http->ocmd);
freez(http->gpc);
freez(http->host);
freez(http->url);
*/
{
char *vec[BUFFER_SIZE];
- int size;
+ size_t size;
char *p;
http->dbuffer = strdup(http->host);
if (http->dcount <= 0)
{
- // Error: More than SZ(vec) components in domain
- // or: no components in domain
+ /*
+ * Error: More than SZ(vec) components in domain
+ * or: no components in domain
+ */
free_http_request(http);
return JB_ERR_PARSE;
}
* When finished, free with unload_url().
*
* Parameters :
- * 1 : url = Target url_spec to be filled in. Must be
- * zeroed out before the call (e.g. using zalloc).
+ * 1 : url = Target url_spec to be filled in. Will be
+ * zeroed before use.
* 2 : buf = Source pattern, null terminated. NOTE: The
* contents of this buffer are destroyed by this
* function. If this function succeeds, the
assert(url);
assert(buf);
+ /* Zero memory */
+ memset(url, '\0', sizeof(*url));
+
/* save a copy of the orignal specification */
if ((url->spec = strdup(buf)) == NULL)
{
return JB_ERR_MEMORY;
}
- if ((p = strchr(buf, '/')))
+ if ((p = strchr(buf, '/')) != NULL)
{
if (NULL == (url->path = strdup(p)))
{
url->path = NULL;
url->pathlen = 0;
}
-#ifdef REGEX
if (url->path)
{
int errcode;
freez(url->spec);
freez(url->path);
+ regfree(url->preg);
freez(url->preg);
return JB_ERR_PARSE;
}
}
-#endif
if ((p = strchr(buf, ':')) == NULL)
{
url->port = 0;
if (buf[0] != '\0')
{
char *v[150];
- int size;
+ size_t size;
/* Parse domain part */
if (buf[strlen(buf) - 1] == '.')
{
freez(url->spec);
freez(url->path);
-#ifdef REGEX
+ regfree(url->preg);
freez(url->preg);
-#endif /* def REGEX */
return JB_ERR_MEMORY;
}
{
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;
{
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;
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