-const char filters_rcs[] = "$Id: filters.c,v 1.41 2001/11/13 00:14:07 jongfoster Exp $";
+const char filters_rcs[] = "$Id: filters.c,v 1.56 2002/04/05 15:51:24 oes Exp $";
/*********************************************************************
*
* File : $Source: /cvsroot/ijbswa/current/filters.c,v $
* 'ijb_send_banner', and `trust_url'
*
* 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: filters.c,v $
+ * Revision 1.56 2002/04/05 15:51:24 oes
+ * - bugfix: error-pages now get correct request protocol
+ * - fix for invalid HTML in trust info
+ *
+ * Revision 1.55 2002/04/02 16:13:51 oes
+ * Fix: No "Go there anyway" for SSL
+ *
+ * Revision 1.54 2002/04/02 14:55:56 oes
+ * Bugfix: is_untrusted_url() now depends on FEATURE_TRUST, not FEATURE_COOKIE_JAR
+ *
+ * Revision 1.53 2002/03/26 22:29:54 swa
+ * we have a new homepage!
+ *
+ * Revision 1.52 2002/03/24 16:35:57 jongfoster
+ * Removing logo
+ *
+ * Revision 1.51 2002/03/24 15:23:33 jongfoster
+ * Name changes
+ *
+ * Revision 1.50 2002/03/24 13:25:43 swa
+ * name change related issues
+ *
+ * Revision 1.49 2002/03/16 20:29:14 oes
+ * Cosmetics
+ *
+ * Revision 1.48 2002/03/13 20:25:34 oes
+ * Better logging for content filters
+ *
+ * Revision 1.47 2002/03/13 00:30:52 jongfoster
+ * Killing warnings
+ * Added option of always sending redirect for imageblock,
+ * currently disabled with #if 0.
+ *
+ * Revision 1.46 2002/03/12 01:42:49 oes
+ * Introduced modular filters
+ *
+ * Revision 1.45 2002/03/08 16:47:50 oes
+ * Added choice beween GIF and PNG built-in images
+ *
+ * Revision 1.44 2002/03/07 03:49:31 oes
+ * - Fixed compiler warnings etc
+ * - Changed built-in images from GIF to PNG
+ * (with regard to Unisys patent issue)
+ * - Added a 4x4 pattern PNG which is less intrusive
+ * than the logo but also clearly marks the deleted banners
+ *
+ * Revision 1.43 2002/01/22 23:51:59 jongfoster
+ * Replacing strsav() with the safer string_append().
+ *
+ * Adding missing html_encode() to error message generators. Where encoded
+ * and unencoded versions of a string were provided, removing the unencoded
+ * one.
+ *
+ * Revision 1.42 2002/01/17 21:00:32 jongfoster
+ * Moving all our URL and URL pattern parsing code to urlmatch.c.
+ *
+ * Using 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.
+ *
+ * Using parse_http_url() to parse URLs without faking a HTTP
+ * request line for parse_http_request().
+ *
* Revision 1.41 2001/11/13 00:14:07 jongfoster
* Fixing stupid bug now I've figured out what || means.
* (It always returns 0 or 1, not one of it's paramaters.)
* a lot! ;-)
*
* Revision 1.3 2001/05/20 16:44:47 jongfoster
- * Removing last hardcoded JunkBusters.com URLs.
+ * Removing last hardcoded Junkbusters.com URLs.
*
* Revision 1.2 2001/05/20 01:21:20 jongfoster
* Version 2.9.4 checkin.
*
* Function : acl_addr
*
- * Description : Called from `load_aclfile' to parse an ACL address.
+ * Description : Called from `load_config' to parse an ACL address.
*
* Parameters :
* 1 : aspec = String specifying ACL address.
masklength = 32;
port = 0;
- if ((p = strchr(aspec, '/')))
+ if ((p = strchr(aspec, '/')) != NULL)
{
*p++ = '\0';
return(-1);
}
- if ((p = strchr(aspec, ':')))
+ if ((p = strchr(aspec, ':')) != NULL)
{
*p++ = '\0';
aca->addr = ntohl(resolve_hostname_to_ip(aspec));
- if (aca->addr == -1)
+ if (aca->addr == INADDR_NONE)
{
- log_error(LOG_LEVEL_ERROR, "can't resolve address for %s", aspec);
return(-1);
}
/* determine HOW images should be blocked */
p = csp->action->string[ACTION_STRING_IMAGE_BLOCKER];
+#if 1 /* Two alternative strategies, use this one for now: */
+
/* and handle accordingly: */
- if ((p == NULL) || (0 == strcmpic(p, "logo")))
+ if ((p == NULL) || (0 == strcmpic(p, "pattern")))
{
- rsp->body = bindup(image_junkbuster_gif_data, image_junkbuster_gif_length);
+ rsp->body = bindup(image_pattern_data, image_pattern_length);
if (rsp->body == NULL)
{
free_http_response(rsp);
return cgi_error_memory();
}
- rsp->content_length = image_junkbuster_gif_length;
+ rsp->content_length = image_pattern_length;
- if (enlist_unique_header(rsp->headers, "Content-Type", "image/gif"))
+ if (enlist_unique_header(rsp->headers, "Content-Type", BUILTIN_IMAGE_MIMETYPE))
{
free_http_response(rsp);
return cgi_error_memory();
else if (0 == strcmpic(p, "blank"))
{
- rsp->body = bindup(image_blank_gif_data, image_blank_gif_length);
+ rsp->body = bindup(image_blank_data, image_blank_length);
if (rsp->body == NULL)
{
free_http_response(rsp);
return cgi_error_memory();
}
- rsp->content_length = image_blank_gif_length;
+ rsp->content_length = image_blank_length;
- if (enlist_unique_header(rsp->headers, "Content-Type", "image/gif"))
+ if (enlist_unique_header(rsp->headers, "Content-Type", BUILTIN_IMAGE_MIMETYPE))
{
free_http_response(rsp);
return cgi_error_memory();
else
{
- rsp->status = strdup("302 Local Redirect from Junkbuster");
+ rsp->status = strdup("302 Local Redirect from Privoxy");
if (rsp->status == NULL)
{
free_http_response(rsp);
return cgi_error_memory();
}
}
+
+#else /* Following code is disabled for now */
+
+ /* and handle accordingly: */
+ if ((p == NULL) || (0 == strcmpic(p, "pattern")))
+ {
+ p = CGI_PREFIX "send-banner?type=pattern";
+ }
+ else if (0 == strcmpic(p, "blank"))
+ {
+ p = CGI_PREFIX "send-banner?type=blank";
+ }
+ rsp->status = strdup("302 Local Redirect from Privoxy");
+ if (rsp->status == NULL)
+ {
+ free_http_response(rsp);
+ return cgi_error_memory();
+ }
+
+ if (enlist_unique_header(rsp->headers, "Location", p))
+ {
+ free_http_response(rsp);
+ return cgi_error_memory();
+ }
+#endif /* Preceeding code is disabled for now */
}
else
#endif /* def FEATURE_IMAGE_BLOCKING */
#ifdef FEATURE_FORCE_LOAD
err = map(exports, "force-prefix", 1, FORCE_PREFIX, 1);
-#else /* ifndef FEATURE_FORCE_LOAD */
- err = map_block_killer(exports, "force-support");
+ if (csp->http->ssl != 0)
#endif /* ndef FEATURE_FORCE_LOAD */
+ {
+ err = map_block_killer(exports, "force-support");
+ }
+ if (!err) err = map(exports, "protocol", 1, csp->http->ssl ? "https://" : "http://", 1);
if (!err) err = map(exports, "hostport", 1, html_encode(csp->http->hostport), 0);
if (!err) err = map(exports, "path", 1, html_encode(csp->http->path), 0);
}
/*
- * Export the host, port, and referrer information
+ * Export the protocol, host, port, and referrer information
*/
err = map(exports, "hostport", 1, csp->http->hostport, 1);
+ if (!err) err = map(exports, "protocol", 1, csp->http->ssl ? "https://" : "http://", 1);
if (!err) err = map(exports, "path", 1, csp->http->path, 1);
- if (!err) err = map(exports, "hostport-html", 1, html_encode(csp->http->hostport), 0);
- if (!err) err = map(exports, "path-html", 1, html_encode(csp->http->path), 0);
if (NULL != (p = get_header_value(csp->headers, "Referer:")))
{
- if (!err) err = map(exports, "referrer", 1, p, 1);
- if (!err) err = map(exports, "referrer-html", 1, html_encode(p), 0);
+ if (!err) err = map(exports, "referrer", 1, html_encode(p), 0);
}
else
{
if (!err) err = map(exports, "referrer", 1, "unknown", 1);
- if (!err) err = map(exports, "referrer-html", 1, "unknown", 1);
}
if (err)
* Export the trust list
*/
p = strdup("");
- for (tl = csp->config->trust_list; (t = *tl) ; tl++)
+ for (tl = csp->config->trust_list; (t = *tl) != NULL ; tl++)
{
sprintf(buf, "<li>%s</li>\n", t->spec);
string_append(&p, buf);
p = strdup("");
for (l = csp->config->trust_info->first; l ; l = l->next)
{
- sprintf(buf, "<li> <a href=%s>%s</a><br>\n",l->str, l->str);
+ sprintf(buf, "<li> <a href=\"%s\">%s</a><br>\n",l->str, l->str);
string_append(&p, buf);
}
err = map(exports, "trust-info", 1, p, 0);
/*
* find the last URL encoded in the request
*/
- while ((p = strstr(p, "http://")))
+ while ((p = strstr(p, "http://")) != NULL)
{
q = p++;
}
}
if ( enlist_unique_header(rsp->headers, "Location", q)
- || (NULL == (rsp->status = strdup("302 Local Redirect from Junkbuster"))) )
+ || (NULL == (rsp->status = strdup("302 Local Redirect from Privoxy"))) )
{
free_http_response(rsp);
return cgi_error_memory();
#endif /* def FEATURE_IMAGE_BLOCKING */
-#ifdef FEATURE_COOKIE_JAR
+#ifdef FEATURE_TRUST
/*********************************************************************
*
* Function : is_untrusted_url
struct block_spec *b;
struct url_spec **trusted_url;
struct http_request rhttp[1];
- char *p, *h;
+ const char * referer;
jb_err err;
/*
}
}
- if (NULL == (h = get_header_value(csp->headers, "Referer:")))
+ if (NULL == (referer = get_header_value(csp->headers, "Referer:")))
{
/* no referrer was supplied */
return 1;
}
- /*
- * If not, do we maybe trust its referrer?
- */
-
/*
- * Parse the URL from the referrer
+ * If not, do we maybe trust its referrer?
*/
-
- err = parse_http_url(h, rhttp, csp);
+ err = parse_http_url(referer, rhttp, csp);
if (err)
{
return 1;
FILE *fp;
- if ((fp = fopen(csp->config->trustfile, "a")))
+ if (NULL != (fp = fopen(csp->config->trustfile, "a")))
{
- h = NULL;
+ char * path;
+ char * path_end;
+ char * new_entry = strdup("~");
- h = strsav(h, "~");
- h = strsav(h, csp->http->hostport);
+ string_append(&new_entry, csp->http->hostport);
- p = csp->http->path;
- if ((*p++ == '/')
- && (*p++ == '~'))
+ path = csp->http->path;
+ if ( (path[0] == '/')
+ && (path[1] == '~')
+ && ((path_end = strchr(path + 2, '/')) != NULL))
{
/* since this path points into a user's home space
* be sure to include this spec in the trustfile.
*/
- if ((p = strchr(p, '/')))
+ int path_len = path_end - path; /* save offset */
+ path = strdup(path); /* Copy string */
+ if (path != NULL)
{
- *p = '\0'; /* FIXME: writing to csp->http->path is a bad idea */
- h = strsav(h, csp->http->path);
- h = strsav(h, "/");
+ path_end = path + path_len; /* regenerate ptr to new buffer */
+ *(path_end + 1) = '\0'; /* Truncate path after '/' */
}
+ string_join(&new_entry, path);
+ }
+
+ if (new_entry != NULL)
+ {
+ fprintf(fp, "%s\n", new_entry);
+ free(new_entry);
+ }
+ else
+ {
+ /* FIXME: No way to handle out-of memory, so mostly ignoring it */
+ log_error(LOG_LEVEL_ERROR, "Out of memory adding pattern to trust file");
}
- fprintf(fp, "%s\n", h);
- freez(h);
fclose(fp);
}
return 0;
}
return 1;
}
-#endif /* def FEATURE_COOKIE_JAR */
+#endif /* def FEATURE_TRUST */
/*********************************************************************
*
* Function : pcrs_filter_response
*
- * Description : Apply all the pcrs jobs from the joblist (re_filterfile)
- * to the text buffer that's been accumulated in
- * csp->iob->buf and set csp->content_length to the modified
- * size and raise the CSP_FLAG_MODIFIED flag if appropriate.
+ * Description : Ecexute all text substitutions from all applying
+ * +filter actions on the text buffer that's been accumulated
+ * in csp->iob->buf. If this changes the contents, set
+ * csp->content_length to the modified size and raise the
+ * CSP_FLAG_MODIFIED flag.
*
* Parameters :
* 1 : csp = Current client state (buffers, headers, etc...)
*
* Returns : a pointer to the (newly allocated) modified buffer.
- * or NULL in case something went wrong
+ * or NULL if there were no hits or something went wrong
*
*********************************************************************/
char *pcrs_filter_response(struct client_state *csp)
struct file_list *fl;
struct re_filterfile_spec *b;
+ struct list_entry *filtername;
- /* Sanity first */
+ /*
+ * Sanity first
+ */
if (csp->iob->cur >= csp->iob->eod)
{
return(NULL);
}
size = csp->iob->eod - csp->iob->cur;
+ if ( ( NULL == (fl = csp->rlist) ) || ( NULL == fl->f) )
+ {
+ log_error(LOG_LEVEL_ERROR, "Unable to get current state of regexp filtering.");
+ return(NULL);
+ }
+
/*
* If the body has a "chunked" transfer-encoding,
* get rid of it first, adjusting size and iob->eod
csp->flags |= CSP_FLAG_MODIFIED;
}
- if ( ( NULL == (fl = csp->rlist) ) || ( NULL == (b = fl->f) ) )
+ /*
+ * For all applying +filter actions, look if a filter by that
+ * name exists and if yes, execute it's pcrs_joblist on the
+ * buffer.
+ */
+ for (b = fl->f; b; b = b->next)
{
- log_error(LOG_LEVEL_ERROR, "Unable to get current state of regexp filtering.");
- return(NULL);
- }
+ for (filtername = csp->action->multi[ACTION_MULTI_FILTER]->first;
+ filtername ; filtername = filtername->next)
+ {
+ if (strcmp(b->name, filtername->str) == 0)
+ {
+ int current_hits = 0;
- if ( NULL == b->joblist )
- {
- log_error(LOG_LEVEL_RE_FILTER, "Empty joblist. Nothing to do.");
- return(NULL);
- }
+ if ( NULL == b->joblist )
+ {
+ log_error(LOG_LEVEL_RE_FILTER, "Filter %s has empty joblist. Nothing to do.", b->name);
+ return(NULL);
+ }
- log_error(LOG_LEVEL_RE_FILTER, "re_filtering %s%s (size %d) ...",
- csp->http->hostport, csp->http->path, size);
+ log_error(LOG_LEVEL_RE_FILTER, "re_filtering %s%s (size %d) with filter %s...",
+ csp->http->hostport, csp->http->path, size, b->name);
- /* Apply all jobs from the joblist */
- for (job = b->joblist; NULL != job; job = job->next)
- {
- hits += pcrs_execute(job, old, size, &new, &size);
- if (old != csp->iob->cur) free(old);
- old=new;
- }
+ /* Apply all jobs from the joblist */
+ for (job = b->joblist; NULL != job; job = job->next)
+ {
+ current_hits += pcrs_execute(job, old, size, &new, &size);
+ if (old != csp->iob->cur) free(old);
+ old=new;
+ }
- log_error(LOG_LEVEL_RE_FILTER, " produced %d hits (new size %d).", hits, size);
+ log_error(LOG_LEVEL_RE_FILTER, " ...produced %d hits (new size %d).", current_hits, size);
+ hits += current_hits;
+ }
+ }
+ }
/*
* If there were no hits, destroy our copy and let
{
struct binbuffer *in, *out;
char *p;
- int size = csp->iob->eod - csp->iob->cur;
+ size_t size = csp->iob->eod - csp->iob->cur;
/*
* If the body has a "chunked" transfer-encoding,
}
else
{
- log_error(LOG_LEVEL_DEANIMATE, "Success! GIF shrunk from %d bytes to %d.", size, out->offset);
+ if ((int)size == out->offset)
+ {
+ log_error(LOG_LEVEL_DEANIMATE, "GIF not changed.");
+ }
+ else
+ {
+ log_error(LOG_LEVEL_DEANIMATE, "Success! GIF shrunk from %d bytes to %d.", size, out->offset);
+ }
csp->content_length = out->offset;
csp->flags |= CSP_FLAG_MODIFIED;
p = out->buffer;