-const char filters_rcs[] = "$Id: filters.c,v 1.1 2001/05/13 21:57:06 administrator Exp $";
+const char filters_rcs[] = "$Id: filters.c,v 1.34 2001/09/20 15:49:36 steudten Exp $";
/*********************************************************************
*
- * File : $Source: /home/administrator/cvs/ijb/filters.c,v $
+ * File : $Source: /cvsroot/ijbswa/current/filters.c,v $
*
* Purpose : Declares functions to parse/crunch headers and pages.
* Functions declared include:
* `acl_addr', `add_stats', `block_acl', `block_imageurl',
- * `block_url', `cookie_url', `domaincmp', `dsplit',
- * `filter_popups', `forward_url',
- * `ij_untrusted_url', `intercept_url', `re_process_buffer',
- * `show_proxy_args', and `trust_url'
+ * `block_url', `url_actions', `domaincmp', `dsplit',
+ * `filter_popups', `forward_url', 'redirect_url',
+ * `ij_untrusted_url', `intercept_url', `pcrs_filter_respose',
+ * `show_proxy_args', 'ijb_send_banner', and `trust_url'
*
* Copyright : Written by and Copyright (C) 2001 the SourceForge
* IJBSWA team. http://ijbswa.sourceforge.net
*
* Revisions :
* $Log: filters.c,v $
+ * Revision 1.34 2001/09/20 15:49:36 steudten
+ *
+ * Fix BUG: Change int size to size_t size in pcrs_filter_response().
+ * See cgi.c fill_template().
+ *
+ * Revision 1.33 2001/09/16 17:05:14 jongfoster
+ * Removing unused #include showarg.h
+ *
+ * Revision 1.32 2001/09/16 13:21:27 jongfoster
+ * Changes to use new list functions.
+ *
+ * Revision 1.31 2001/09/16 11:38:02 jongfoster
+ * Splitting fill_template() into 2 functions:
+ * template_load() loads the file
+ * template_fill() performs the PCRS regexps.
+ * This is because the CGI edit interface has a "table row"
+ * template which is used many times in the page - this
+ * change means it's only loaded from disk once.
+ *
+ * Revision 1.30 2001/09/16 11:00:10 jongfoster
+ * New function alloc_http_response, for symmetry with free_http_response
+ *
+ * Revision 1.29 2001/09/13 23:32:40 jongfoster
+ * Moving image data to cgi.c rather than cgi.h
+ * Fixing a GPF under Win32 (and any other OS that protects global
+ * constants from being written to).
+ *
+ * Revision 1.28 2001/09/10 10:18:51 oes
+ * Silenced compiler warnings
+ *
+ * Revision 1.27 2001/08/05 16:06:20 jongfoster
+ * Modifiying "struct map" so that there are now separate header and
+ * "map_entry" structures. This means that functions which modify a
+ * map no longer need to return a pointer to the modified map.
+ * Also, it no longer reverses the order of the entries (which may be
+ * important with some advanced template substitutions).
+ *
+ * Revision 1.26 2001/07/30 22:08:36 jongfoster
+ * Tidying up #defines:
+ * - All feature #defines are now of the form FEATURE_xxx
+ * - Permanently turned off WIN_GUI_EDIT
+ * - Permanently turned on WEBDAV and SPLIT_PROXY_ARGS
+ *
+ * Revision 1.25 2001/07/26 10:09:46 oes
+ * Made browser detection a little less naive
+ *
+ * Revision 1.24 2001/07/25 17:22:51 oes
+ * Added workaround for Netscape bug that prevents display of page when loading a component fails.
+ *
+ * Revision 1.23 2001/07/23 13:40:12 oes
+ * Fixed bug that caused document body to be dropped when pcrs joblist was empty.
+ *
+ * Revision 1.22 2001/07/18 12:29:34 oes
+ * - Made gif_deanimate_response respect
+ * csp->action->string[ACTION_STRING_DEANIMATE]
+ * - Logging cosmetics
+ *
+ * Revision 1.21 2001/07/13 13:59:53 oes
+ * - Introduced gif_deanimate_response which shares the
+ * generic content modification interface of pcrs_filter_response
+ * and acts as a wrapper to deanimate.c:gif_deanimate()
+ * - Renamed re_process_buffer to pcrs_filter_response
+ * - pcrs_filter_response now returns NULL on failiure
+ * - Removed all #ifdef PCRS
+ *
+ * Revision 1.20 2001/07/01 17:01:04 oes
+ * Added comments and missing return statement in is_untrusted_url()
+ *
+ * Revision 1.19 2001/06/29 21:45:41 oes
+ * Indentation, CRLF->LF, Tab-> Space
+ *
+ * Revision 1.18 2001/06/29 13:27:38 oes
+ * - Cleaned up, renamed and reorderd functions
+ * and improved comments
+ *
+ * - block_url:
+ * - Ported to CGI platform. Now delivers
+ * http_response or NULL
+ * - Unified HTML and GIF generation (moved image detection
+ * and GIF generation here from jcc.c:chat())
+ * - Fixed HTTP status to:
+ * - 403 (Forbidden) for the "blocked" HTML message
+ * - 200 (OK) for GIF answers
+ * - 302 (Redirect) for redirect to GIF
+ *
+ * - trust_url:
+ * - Ported to CGI platform. Now delivers
+ * http_response or NULL
+ * - Separated detection of untrusted URL into
+ * (bool)is_untrusted_url
+ * - Added enforcement of untrusted requests
+ *
+ * - Moved redirect_url() from cgi.c to here
+ * and ported it to the CGI platform
+ *
+ * - Removed logentry from cancelled commit
+ *
+ * Revision 1.17 2001/06/09 10:55:28 jongfoster
+ * Changing BUFSIZ ==> BUFFER_SIZE
+ *
+ * Revision 1.16 2001/06/07 23:10:26 jongfoster
+ * Allowing unanchored domain patterns to back off and retry
+ * if they partially match. Optimized right-anchored patterns.
+ * Moving ACL and forward files into config file.
+ * Replacing struct gateway with struct forward_spec
+ *
+ * Revision 1.15 2001/06/03 19:12:00 oes
+ * extracted-CGI relevant stuff
+ *
+ * Revision 1.14 2001/06/01 10:30:55 oes
+ * Added optional left-anchoring to domaincmp
+ *
+ * Revision 1.13 2001/05/31 21:21:30 jongfoster
+ * Permissionsfile / actions file changes:
+ * - Changed "permission" to "action" throughout
+ * - changes to file format to allow string parameters
+ * - Moved helper functions to actions.c
+ *
+ * Revision 1.12 2001/05/31 17:35:20 oes
+ *
+ * - Enhanced domain part globbing with infix and prefix asterisk
+ * matching and optional unanchored operation
+ *
+ * Revision 1.11 2001/05/29 11:53:23 oes
+ * "See why" link added to "blocked" page
+ *
+ * Revision 1.10 2001/05/29 09:50:24 jongfoster
+ * Unified blocklist/imagelist/permissionslist.
+ * File format is still under discussion, but the internal changes
+ * are (mostly) done.
+ *
+ * Also modified interceptor behaviour:
+ * - We now intercept all URLs beginning with one of the following
+ * prefixes (and *only* these prefixes):
+ * * http://i.j.b/
+ * * http://ijbswa.sf.net/config/
+ * * http://ijbswa.sourceforge.net/config/
+ * - New interceptors "home page" - go to http://i.j.b/ to see it.
+ * - Internal changes so that intercepted and fast redirect pages
+ * are not replaced with an image.
+ * - Interceptors now have the option to send a binary page direct
+ * to the client. (i.e. ijb-send-banner uses this)
+ * - Implemented show-url-info interceptor. (Which is why I needed
+ * the above interceptors changes - a typical URL is
+ * "http://i.j.b/show-url-info?url=www.somesite.com/banner.gif".
+ * The previous mechanism would not have intercepted that, and
+ * if it had been intercepted then it then it would have replaced
+ * it with an image.)
+ *
+ * Revision 1.9 2001/05/27 22:17:04 oes
+ *
+ * - re_process_buffer no longer writes the modified buffer
+ * to the client, which was very ugly. It now returns the
+ * buffer, which it is then written by chat.
+ *
+ * - content_length now adjusts the Content-Length: header
+ * for modified documents rather than crunch()ing it.
+ * (Length info in csp->content_length, which is 0 for
+ * unmodified documents)
+ *
+ * - For this to work, sed() is called twice when filtering.
+ *
+ * Revision 1.8 2001/05/26 17:13:28 jongfoster
+ * Filled in a function comment.
+ *
+ * Revision 1.7 2001/05/26 15:26:15 jongfoster
+ * ACL feature now provides more security by immediately dropping
+ * connections from untrusted hosts.
+ *
+ * Revision 1.6 2001/05/26 00:28:36 jongfoster
+ * Automatic reloading of config file.
+ * Removed obsolete SIGHUP support (Unix) and Reload menu option (Win32).
+ * Most of the global variables have been moved to a new
+ * struct configuration_spec, accessed through csp->config->globalname
+ * Most of the globals remaining are used by the Win32 GUI.
+ *
+ * Revision 1.5 2001/05/25 22:34:30 jongfoster
+ * Hard tabs->Spaces
+ *
+ * Revision 1.4 2001/05/22 18:46:04 oes
+ *
+ * - Enabled filtering banners by size rather than URL
+ * by adding patterns that replace all standard banner
+ * sizes with the "Junkbuster" gif to the re_filterfile
+ *
+ * - Enabled filtering WebBugs by providing a pattern
+ * which kills all 1x1 images
+ *
+ * - Added support for PCRE_UNGREEDY behaviour to pcrs,
+ * which is selected by the (nonstandard and therefore
+ * capital) letter 'U' in the option string.
+ * It causes the quantifiers to be ungreedy by default.
+ * Appending a ? turns back to greedy (!).
+ *
+ * - Added a new interceptor ijb-send-banner, which
+ * sends back the "Junkbuster" gif. Without imagelist or
+ * MSIE detection support, or if tinygif = 1, or the
+ * URL isn't recognized as an imageurl, a lame HTML
+ * explanation is sent instead.
+ *
+ * - Added new feature, which permits blocking remote
+ * script redirects and firing back a local redirect
+ * to the browser.
+ * The feature is conditionally compiled, i.e. it
+ * can be disabled with --disable-fast-redirects,
+ * plus it must be activated by a "fast-redirects"
+ * line in the config file, has its own log level
+ * and of course wants to be displayed by show-proxy-args
+ * Note: Boy, all the #ifdefs in 1001 locations and
+ * all the fumbling with configure.in and acconfig.h
+ * were *way* more work than the feature itself :-(
+ *
+ * - Because a generic redirect template was needed for
+ * this, tinygif = 3 now uses the same.
+ *
+ * - Moved GIFs, and other static HTTP response templates
+ * to project.h
+ *
+ * - Some minor fixes
+ *
+ * - Removed some >400 CRs again (Jon, you really worked
+ * a lot! ;-)
+ *
+ * Revision 1.3 2001/05/20 16:44:47 jongfoster
+ * Removing last hardcoded JunkBusters.com URLs.
+ *
+ * Revision 1.2 2001/05/20 01:21:20 jongfoster
+ * Version 2.9.4 checkin.
+ * - Merged popupfile and cookiefile, and added control over PCRS
+ * filtering, in new "permissionsfile".
+ * - Implemented LOG_LEVEL_FATAL, so that if there is a configuration
+ * file error you now get a message box (in the Win32 GUI) rather
+ * than the program exiting with no explanation.
+ * - Made killpopup use the PCRS MIME-type checking and HTTP-header
+ * skipping.
+ * - Removed tabs from "config"
+ * - Moved duplicated url parsing code in "loaders.c" to a new funcition.
+ * - Bumped up version number.
+ *
+ * Revision 1.1.1.1 2001/05/15 13:58:52 oes
+ * Initial import of version 2.9.3 source tree
+ *
*
*********************************************************************/
\f
#include <stdlib.h>
#include <ctype.h>
#include <string.h>
+#include <assert.h>
#ifndef _WIN32
#include <unistd.h>
#include "project.h"
#include "filters.h"
#include "encode.h"
-#include "jcc.h"
-#include "showargs.h"
#include "parsers.h"
#include "ssplit.h"
-#include "gateway.h"
-#include "jbsockets.h"
#include "errlog.h"
#include "jbsockets.h"
+#include "miscutil.h"
+#include "actions.h"
+#include "cgi.h"
+#include "list.h"
+#include "deanimate.h"
#ifdef _WIN32
#include "win32.h"
#define ijb_isdigit(__X) isdigit((int)(unsigned char)(__X))
-static const char CBLOCK[] =
-#ifdef AMIGA
- "HTTP/1.0 403 Request for blocked URL\n"
-#else /* ifndef AMIGA */
- "HTTP/1.0 202 Request for blocked URL\n"
-#endif /* ndef AMIGA */
- "Pragma: no-cache\n"
- "Last-Modified: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "Expires: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "Content-Type: text/html\n\n"
- "<html>\n"
- "<head>\n"
- "<title>Internet Junkbuster: Request for blocked URL</title>\n"
- "</head>\n"
- WHITEBG
- "<center><h1>"
- BANNER
- "</h1></center>\n"
- "<p align=center>Your request for <b>%s%s</b><br>\n"
- "was blocked because it matches the following pattern "
- "in the blockfile: <b>%s</b>\n</p>"
-#ifdef FORCE_LOAD
- "<p align=center><a href=\"http://" FORCE_PREFIX
- "%s%s\">Go there anyway.</a></p>"
-#endif /* def FORCE_LOAD */
- "</body>\n"
- "</html>\n";
-
-#ifdef TRUST_FILES
-static const char CTRUST[] =
-#ifdef AMIGA
- "HTTP/1.0 403 Request for untrusted URL\n"
-#else /* ifndef AMIGA */
- "HTTP/1.0 202 Request for untrusted URL\n"
-#endif /* ndef AMIGA */
- "Pragma: no-cache\n"
- "Last-Modified: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "Expires: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "Content-Type: text/html\n\n"
- "<html>\n"
- "<head>\n"
- "<title>Internet Junkbuster: Request for untrusted URL</title>\n"
- "</head>\n"
- WHITEBG
- "<center>"
- "<a href=http://internet.junkbuster.com/ij-untrusted-url?%s+%s+%s>"
- BANNER
- "</a>"
- "</center>"
- "</body>\n"
- "</html>\n";
-#endif /* def TRUST_FILES */
-
-
-#ifdef ACL_FILES
+#ifdef FEATURE_ACL
/*********************************************************************
*
* Function : block_acl
* Decide yes or no based on ACL file.
*
* Parameters :
- * 1 : src = Address the browser/user agent is requesting.
- * 2 : dst = The proxy or gateway address this is going to.
- * 3 : csp = Current client state (buffers, headers, etc...)
+ * 1 : dst = The proxy or gateway address this is going to.
+ * Or NULL to check all possible targets.
+ * 2 : csp = Current client state (buffers, headers, etc...)
+ * Also includes the client IP address.
*
* Returns : 0 = FALSE (don't block) and 1 = TRUE (do block)
*
*********************************************************************/
-int block_acl(struct access_control_addr *src, struct access_control_addr *dst, struct client_state *csp)
+int block_acl(struct access_control_addr *dst, struct client_state *csp)
{
- struct file_list *fl;
- struct access_control_list *a, *acl;
- struct access_control_addr s[1], d[1];
+ struct access_control_list *acl = csp->config->acl;
/* if not using an access control list, then permit the connection */
- if (((fl = csp->alist) == NULL) || ((acl = fl->f) == NULL))
+ if (acl == NULL)
{
return(0);
}
/* search the list */
- for (a = acl->next ; a ; a = a->next)
+ while (acl != NULL)
{
- *s = *src;
- *d = *dst;
-
- s->addr &= a->src->mask;
- d->addr &= a->dst->mask;
-
- if ((s->addr == a->src->addr)
- && (d->addr == a->dst->addr)
- && ((s->port == a->src->port)
- || (s->port == 0)
- || (a->src->port == 0))
- && ((d->port == a->dst->port)
- || (d->port == 0)
- || (a->dst->port == 0)))
+ if ((csp->ip_addr_long & acl->src->mask) == acl->src->addr)
{
- if (a->action == ACL_PERMIT)
+ if (dst == NULL)
{
- return(0);
+ /* Just want to check if they have any access */
+ if (acl->action == ACL_PERMIT)
+ {
+ return(0);
+ }
}
- else
+ else if ( ((dst->addr & acl->dst->mask) == acl->dst->addr)
+ && ((dst->port == acl->dst->port) || (acl->dst->port == 0)))
{
- return(1);
+ if (acl->action == ACL_PERMIT)
+ {
+ return(0);
+ }
+ else
+ {
+ return(1);
+ }
}
}
+ acl = acl->next;
}
return(1);
*
* Function : acl_addr
*
- * Description : Called from `load_aclfile'. FIXME: I can't say more.
+ * Description : Called from `load_aclfile' to parse an ACL address.
*
* Parameters :
- * 1 : aspec = (what?)
- * 2 : aca = (what?)
+ * 1 : aspec = String specifying ACL address.
+ * 2 : aca = struct access_control_addr to fill in.
*
* Returns : 0 => Ok, everything else is an error.
*
return(0);
}
-#endif /* def ACL_FILES */
+#endif /* def FEATURE_ACL */
/*********************************************************************
* Description : Called from `chat'. Check to see if we need to block this.
*
* Parameters :
- * 1 : http = http_request request to "check" for blocked
- * 2 : csp = Current client state (buffers, headers, etc...)
+ * 1 : csp = Current client state (buffers, headers, etc...)
*
- * Returns : NULL => unblocked, else string to HTML block description.
+ * Returns : NULL => unblocked, else HTTP block response
*
*********************************************************************/
-char *block_url(struct http_request *http, struct client_state *csp)
+struct http_response *block_url(struct client_state *csp)
{
- struct file_list *fl;
- struct block_spec *b;
- struct url_spec url[1];
+#ifdef FEATURE_IMAGE_BLOCKING
char *p;
- int n;
+#endif /* def FEATURE_IMAGE_BLOCKING */
+ struct http_response *rsp;
- if (((fl = csp->blist) == NULL) || ((b = fl->f) == NULL))
+ /*
+ * If it's not blocked, don't block it ;-)
+ */
+ if ((csp->action->flags & ACTION_BLOCK) == 0)
{
return(NULL);
}
- *url = dsplit(http->host);
-
- /* if splitting the domain fails, punt */
- if (url->dbuf == NULL) return(NULL);
-
- for (b = b->next; b ; b = b->next)
+ /*
+ * Else, prepare a response
+ */
+ if (NULL == (rsp = alloc_http_response()))
{
- if ((b->url->port == 0) || (b->url->port == http->port))
- {
- if ((b->url->domain[0] == '\0') || (domaincmp(b->url, url) == 0))
- {
- if ((b->url->path == NULL) ||
-#ifdef REGEX
- (regexec(b->url->preg, http->path, 0, NULL, 0) == 0)
-#else
- (strncmp(b->url->path, http->path, b->url->pathlen) == 0)
-#endif
- )
- {
- freez(url->dbuf);
- freez(url->dvec);
+ return NULL;
+ }
- if (b->reject == 0) return(NULL);
+ /*
+ * If it's an image-url, send back an image or redirect
+ * as specified by the relevant +image action
+ */
+#ifdef FEATURE_IMAGE_BLOCKING
+ if (((csp->action->flags & ACTION_IMAGE_BLOCKER) != 0)
+ && is_imageurl(csp))
+ {
+ /* determine HOW images should be blocked */
+ p = csp->action->string[ACTION_STRING_IMAGE_BLOCKER];
- n = strlen(CBLOCK);
- n += strlen(http->hostport);
- n += strlen(http->path);
- n += strlen(b->url->spec);
-#ifdef FORCE_LOAD
- n += strlen(http->hostport);
- n += strlen(http->path);
-#endif /* def FORCE_LOAD */
+ /* and handle accordingly: */
+ if ((p == NULL) || (0 == strcmpic(p, "logo")))
+ {
+ rsp->body = bindup(image_junkbuster_gif_data, image_junkbuster_gif_length);
+ rsp->content_length = image_junkbuster_gif_length;
+ enlist_unique_header(rsp->headers, "Content-Type", "image/gif");
+ }
- p = (char *)malloc(n);
+ else if (0 == strcmpic(p, "blank"))
+ {
+ rsp->body = bindup(image_blank_gif_data, image_blank_gif_length);
+ rsp->content_length = image_blank_gif_length;
+ enlist_unique_header(rsp->headers, "Content-Type", "image/gif");
+ }
-#ifdef FORCE_LOAD
- sprintf(p, CBLOCK, http->hostport, http->path, b->url->spec, http->hostport, http->path);
-#else
- sprintf(p, CBLOCK, http->hostport, http->path, b->url->spec);
-#endif /* def FORCE_LOAD */
+ else
+ {
+ rsp->status = strdup("302 Local Redirect from Junkbuster");
+ enlist_unique_header(rsp->headers, "Location", p);
+ }
+ }
+ else
+#endif /* def FEATURE_IMAGE_BLOCKING */
- return(p);
- }
- }
+ /*
+ * Else, generate an HTML "blocked" message:
+ */
+ {
+ struct map * exports = default_exports(csp, NULL);
+#ifdef FEATURE_FORCE_LOAD
+ map(exports, "force-prefix", 1, FORCE_PREFIX, 1);
+#else /* ifndef FEATURE_FORCE_LOAD */
+ map_block_killer(exports, "force-support");
+#endif /* ndef FEATURE_FORCE_LOAD */
+
+ map(exports, "hostport", 1, csp->http->hostport, 1);
+ map(exports, "hostport-html", 1, html_encode(csp->http->hostport), 0);
+ map(exports, "path", 1, csp->http->path, 1);
+ map(exports, "path-html", 1, html_encode(csp->http->path), 0);
+
+ rsp->body = template_load(csp, "blocked");
+ template_fill(&rsp->body, exports);
+ free_map(exports);
+
+ /*
+ * Workaround for stupid Netscape bug which prevents
+ * pages from being displayed if loading a referenced
+ * JavaScript or style sheet fails. So make it appear
+ * as if it succeeded.
+ */
+ if (csp->http->user_agent
+ && !strncmpic(csp->http->user_agent, "mozilla", 7)
+ && !strstr(csp->http->user_agent, "compatible")
+ && !strstr(csp->http->user_agent, "Opera"))
+ {
+ rsp->status = strdup("200 Request for blocked URL");
}
+ else
+ {
+ rsp->status = strdup("404 Request for blocked URL");
+ }
+
}
- freez(url->dbuf);
- freez(url->dvec);
- return(NULL);
+
+ return(finish_http_response(rsp));
}
-#if defined(DETECT_MSIE_IMAGES) || defined(USE_IMAGE_LIST)
+#ifdef FEATURE_TRUST
/*********************************************************************
*
- * Function : block_imageurl
+ * Function : trust_url FIXME: I should be called distrust_url
*
- * Description : Given a URL which is blocked, decide whether to
- * send the "blocked" image or HTML.
+ * Description : Calls is_untrusted_url to determine if the URL is trusted
+ * and if not, returns a HTTP 304 response with a reject message.
*
* Parameters :
- * 1 : http = URL to check.
- * 2 : csp = Current client state (buffers, headers, etc...)
+ * 1 : csp = Current client state (buffers, headers, etc...)
*
- * Returns : True (nonzero) if URL is in image list, false (0)
- * otherwise
+ * Returns : NULL => trusted, else http_response.
*
*********************************************************************/
-int block_imageurl(struct http_request *http, struct client_state *csp)
+struct http_response *trust_url(struct client_state *csp)
{
-#ifdef DETECT_MSIE_IMAGES
- if ((csp->accept_types
- & (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_IMAGE|ACCEPT_TYPE_MSIE_HTML))
- == (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_IMAGE))
+ struct http_response *rsp;
+ struct map * exports;
+ char buf[BUFFER_SIZE], *p = NULL;
+ struct url_spec **tl, *t;
+
+ /*
+ * Don't bother to work on trusted URLs
+ */
+ if (!is_untrusted_url(csp))
{
- return 1;
+ return NULL;
}
- else if ((csp->accept_types
- & (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_IMAGE|ACCEPT_TYPE_MSIE_HTML))
- == (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_HTML))
+
+ /*
+ * Else, prepare a response:
+ */
+ if (NULL == (rsp = alloc_http_response()))
{
- return 0;
+ return NULL;
}
-#endif
-
-#if defined(USE_IMAGE_LIST)
- return block_imageurl_using_imagelist(http, csp);
-#else
- /* Don't know - assume HTML */
- return 0;
-#endif
-}
-#endif /* defined(DETECT_MSIE_IMAGES) || defined(USE_IMAGE_LIST) */
+ exports = default_exports(csp, NULL);
-#ifdef USE_IMAGE_LIST
-/*********************************************************************
- *
- * Function : block_imageurl
- *
- * Description : Test if a URL is in the imagelist.
- *
- * Parameters :
- * 1 : http = URL to check.
- * 2 : csp = Current client state (buffers, headers, etc...)
- *
- * Returns : True (nonzero) if URL is in image list, false (0)
- * otherwise
- *
- *********************************************************************/
-int block_imageurl_using_imagelist(struct http_request *http, struct client_state *csp)
-{
- struct file_list *fl;
- struct block_spec *b;
- struct url_spec url[1];
+ /*
+ * Export the host, port, and referrer information
+ */
+ map(exports, "hostport", 1, csp->http->hostport, 1);
+ map(exports, "path", 1, csp->http->path, 1);
+ map(exports, "hostport-html", 1, html_encode(csp->http->hostport), 0);
+ map(exports, "path-html", 1, html_encode(csp->http->path), 0);
- if (((fl = csp->ilist) == NULL) || ((b = fl->f) == NULL))
+ if (csp->referrer && strlen(csp->referrer) > 9)
{
- return(0);
+ map(exports, "referrer", 1, csp->referrer + 9, 1);
+ map(exports, "referrer-html", 1, html_encode(csp->referrer + 9), 0);
+ }
+ else
+ {
+ map(exports, "referrer", 1, "unknown", 1);
+ map(exports, "referrer-html", 1, "unknown", 1);
}
- *url = dsplit(http->host);
-
- /* if splitting the domain fails, punt */
- if (url->dbuf == NULL) return(0);
+ /*
+ * Export the trust list
+ */
+ for (tl = csp->config->trust_list; (t = *tl) ; tl++)
+ {
+ sprintf(buf, "<li>%s</li>\n", t->spec);
+ p = strsav(p, buf);
+ }
+ map(exports, "trusted-referrers", 1, p, 0);
+ p = NULL;
- for (b = b->next; b ; b = b->next)
+ /*
+ * Export the trust info, if available
+ */
+ if (csp->config->trust_info->first)
{
+ struct list_entry *l;
- if ((b->url->port == 0) || (b->url->port == http->port))
+ for (l = csp->config->trust_info->first; l ; l = l->next)
{
- /* port matches, check domain */
- if ((b->url->domain[0] == '\0') || (domaincmp(b->url, url) == 0))
- {
- /* domain matches, check path */
- if ((b->url->path == NULL) ||
-#ifdef REGEX
- (regexec(b->url->preg, http->path, 0, NULL, 0) == 0)
-#else
- (strncmp(b->url->path, http->path, b->url->pathlen) == 0)
-#endif
- )
- {
- /* Matches */
- freez(url->dbuf);
- freez(url->dvec);
-
- if (b->reject == 0) return(0);
-
- return(1);
- }
- }
+ sprintf(buf, "<li> <a href=%s>%s</a><br>\n",l->str, l->str);
+ p = strsav(p, buf);
}
+ map(exports, "trust-info", 1, p, 0);
}
- freez(url->dbuf);
- freez(url->dvec);
- return(0);
+ else
+ {
+ map_block_killer(exports, "have-trust-info");
+ }
+
+ /*
+ * Export the force prefix or the force conditional block killer
+ */
+#ifdef FEATURE_FORCE_LOAD
+ map(exports, "force-prefix", 1, FORCE_PREFIX, 1);
+#else /* ifndef FEATURE_FORCE_LOAD */
+ map_block_killer(exports, "force-support");
+#endif /* ndef FEATURE_FORCE_LOAD */
+
+ /*
+ * Build the response
+ */
+ rsp->body = template_load(csp, "untrusted");
+ template_fill(&rsp->body, exports);
+ free_map(exports);
+
+ return(finish_http_response(rsp));
}
-#endif /* def USE_IMAGE_LIST */
+#endif /* def FEATURE_TRUST */
-#ifdef PCRS
+#ifdef FEATURE_FAST_REDIRECTS
/*********************************************************************
*
- * Function : re_process_buffer
+ * Function : redirect_url
*
- * Description : Apply all jobs from the joblist (aka. Perl regexp's) to
- * the text buffer that's been accumulated in csp->iob->buf.
- * Then, write the modified buffer out to the client
- * (Maybe this should happen from jcc.c via flush_socket
- * for better readability).
+ * Description : Checks for redirection URLs and returns a HTTP redirect
+ * to the destination URL, if necessary
*
* Parameters :
* 1 : csp = Current client state (buffers, headers, etc...)
*
- * Returns : N/A
+ * Returns : NULL if URL was clean, HTTP redirect otherwise.
*
*********************************************************************/
-void re_process_buffer(struct client_state *csp)
+struct http_response *redirect_url(struct client_state *csp)
{
- int hits=0;
- int size = csp->iob->eod - csp->iob->cur;
- char *old=csp->iob->cur, *new = NULL;
- pcrs_job *job, *joblist;
-
- struct file_list *fl;
- struct re_filterfile_spec *b;
+ char *p, *q;
+ struct http_response *rsp;
- /* Sanity first ;-) */
- if (size <= 0) return;
+ p = q = csp->http->path;
+ log_error(LOG_LEVEL_REDIRECTS, "checking path for redirects: %s", p);
- if ( ( NULL == (fl = csp->rlist) ) || ( NULL == (b = fl->f) ) )
+ /*
+ * find the last URL encoded in the request
+ */
+ while ((p = strstr(p, "http://")))
{
- log_error(LOG_LEVEL_ERROR, "Unable to get current state of regexp filtering.");
- return;
+ q = p++;
}
- joblist = b->joblist;
+ /*
+ * if there was any, generate and return a HTTP redirect
+ */
+ if (q != csp->http->path)
+ {
+ log_error(LOG_LEVEL_REDIRECTS, "redirecting to: %s", q);
+ if (NULL == (rsp = alloc_http_response()))
+ {
+ return NULL;
+ }
- log_error(LOG_LEVEL_REF, "re_filtering %s%s (size %d) ...",
- csp->http->hostport, csp->http->path, size);
+ rsp->status = strdup("302 Local Redirect from Junkbuster");
+ enlist_unique_header(rsp->headers, "Location", q);
- /* Apply all jobs from the joblist */
- for (job = joblist; NULL != job; job = job->next)
+ return(finish_http_response(rsp));
+ }
+ else
{
- hits += pcrs_exec_substitution(job, old, size, &new, &size);
- if (old != csp->iob->cur) free(old);
- old=new;
+ return(NULL);
}
- log_error(LOG_LEVEL_REF, " produced %d hits (new size %d).", hits, size);
+}
+#endif /* def FEATURE_FAST_REDIRECTS */
+
- if (write_socket(csp->cfd, old, size) != size)
+#ifdef FEATURE_IMAGE_BLOCKING
+/*********************************************************************
+ *
+ * Function : is_imageurl
+ *
+ * Description : Given a URL, decide whether it is an image or not,
+ * using either the info from a previous +image action
+ * or, #ifdef FEATURE_IMAGE_DETECT_MSIE, the info from
+ * the browser's accept header.
+ *
+ * Parameters :
+ * 1 : csp = Current client state (buffers, headers, etc...)
+ *
+ * Returns : True (nonzero) if URL is an image, false (0)
+ * otherwise
+ *
+ *********************************************************************/
+int is_imageurl(struct client_state *csp)
+{
+#ifdef FEATURE_IMAGE_DETECT_MSIE
+ if ((csp->accept_types
+ & (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_IMAGE|ACCEPT_TYPE_MSIE_HTML))
+ == (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_IMAGE))
+ {
+ return 1;
+ }
+ else if ((csp->accept_types
+ & (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_IMAGE|ACCEPT_TYPE_MSIE_HTML))
+ == (ACCEPT_TYPE_IS_MSIE|ACCEPT_TYPE_MSIE_HTML))
{
- log_error(LOG_LEVEL_ERROR, "write to client failed.");
+ return 0;
}
+#endif /* def FEATURE_IMAGE_DETECT_MSIE */
- /* fwiw, reset the iob */
- IOB_RESET(csp);
- freez(new);
- return;
+ return ((csp->action->flags & ACTION_IMAGE) != 0);
}
-#endif /* def PCRS */
+#endif /* def FEATURE_IMAGE_BLOCKING */
-#ifdef TRUST_FILES
+#ifdef FEATURE_COOKIE_JAR
/*********************************************************************
*
- * Function : trust_url
+ * Function : is_untrusted_url
+ *
+ * Description : Should we "distrust" this URL (and block it)?
*
- * Description : Should we "trust" this URL? See "trustfile" line in config.
+ * Yes if it matches a line in the trustfile, or if the
+ * referrer matches a line starting with "+" in the
+ * trustfile.
+ * No otherwise.
*
* Parameters :
- * 1 : http = http_request request for requested URL
- * 2 : csp = Current client state (buffers, headers, etc...)
+ * 1 : csp = Current client state (buffers, headers, etc...)
*
- * Returns : NULL => trusted, else string to HTML "untrusted" description.
+ * Returns : 0 => trusted, 1 => untrusted
*
*********************************************************************/
-char *trust_url(struct http_request *http, struct client_state *csp)
+int is_untrusted_url(struct client_state *csp)
{
struct file_list *fl;
struct block_spec *b;
struct url_spec url[1], **tl, *t;
- char *p, *h;
- char *hostport, *path, *refer;
struct http_request rhttp[1];
- int n;
+ char *p, *h;
+ /*
+ * If we don't have a trustlist, we trust everybody
+ */
if (((fl = csp->tlist) == NULL) || ((b = fl->f) == NULL))
{
- return(NULL);
+ return(0);
}
- *url = dsplit(http->host);
+
+ /*
+ * Do we trust the request URL itself?
+ */
+ *url = dsplit(csp->http->host);
/* if splitting the domain fails, punt */
- if (url->dbuf == NULL) return(NULL);
+ if (url->dbuf == NULL) return(0);
memset(rhttp, '\0', sizeof(*rhttp));
for (b = b->next; b ; b = b->next)
{
- if ((b->url->port == 0) || (b->url->port == http->port))
+ if ((b->url->port == 0) || (b->url->port == csp->http->port))
{
if ((b->url->domain[0] == '\0') || (domaincmp(b->url, url) == 0))
{
if ((b->url->path == NULL) ||
#ifdef REGEX
- (regexec(b->url->preg, http->path, 0, NULL, 0) == 0)
+ (regexec(b->url->preg, csp->http->path, 0, NULL, 0) == 0)
#else
- (strncmp(b->url->path, http->path, b->url->pathlen) == 0)
+ (strncmp(b->url->path, csp->http->path, b->url->pathlen) == 0)
#endif
)
{
freez(url->dbuf);
freez(url->dvec);
- if (b->reject == 0) return(NULL);
-
- hostport = url_encode(http->hostport);
- path = url_encode(http->path);
-
- if (csp->referrer)
- {
- refer = url_encode(csp->referrer);
- }
- else
- {
- refer = url_encode("undefined");
- }
-
- n = strlen(CTRUST);
- n += strlen(hostport);
- n += strlen(path);
- n += strlen(refer);
-
- p = (char *)malloc(n);
-
- sprintf(p, CTRUST, hostport, path, refer);
-
- freez(hostport);
- freez(path);
- freez(refer);
+ if (b->reject == 0) return(0);
- return(p);
+ return(1);
}
}
}
if ((csp->referrer == NULL)|| (strlen(csp->referrer) <= 9))
{
/* no referrer was supplied */
- goto trust_url_not_trusted;
+ return(1);
}
/* forge a URL from the referrer so we can use
p = strsav(p, " HTTP/1.0");
parse_http_request(p, rhttp, csp);
+ freez(p);
if (rhttp->cmd == NULL)
{
- freez(p);
- goto trust_url_not_trusted;
+ return(1);
}
- freez(p);
+ /*
+ * If not, do we maybe trust its referrer?
+ */
*url = dsplit(rhttp->host);
/* if splitting the domain fails, punt */
- if (url->dbuf == NULL) goto trust_url_not_trusted;
+ if (url->dbuf == NULL) return(1);
- for (tl = trust_list; (t = *tl) ; tl++)
+ for (tl = csp->config->trust_list; (t = *tl) ; tl++)
{
if ((t->port == 0) || (t->port == rhttp->port))
{
freez(url->dbuf);
freez(url->dvec);
- if ((fp = fopen(trustfile, "a")))
+ if ((fp = fopen(csp->config->trustfile, "a")))
{
h = NULL;
h = strsav(h, "~");
- h = strsav(h, http->hostport);
+ h = strsav(h, csp->http->hostport);
- p = http->path;
+ p = csp->http->path;
if ((*p++ == '/')
&& (*p++ == '~'))
{
if ((p = strchr(p, '/')))
{
*p = '\0';
- h = strsav(h, http->path);
+ h = strsav(h, csp->http->path); /* FIXME: p?! */
h = strsav(h, "/");
}
}
- free_http_request(rhttp);
-
fprintf(fp, "%s\n", h);
freez(h);
fclose(fp);
}
- return(NULL);
+ return(0);
}
}
}
}
-
-trust_url_not_trusted:
- free_http_request(rhttp);
-
- hostport = url_encode(http->hostport);
- path = url_encode(http->path);
-
- if (csp->referrer)
- {
- refer = url_encode(csp->referrer);
- }
- else
- {
- refer = url_encode("undefined");
- }
-
- n = strlen(CTRUST);
- n += strlen(hostport);
- n += strlen(path);
- n += strlen(refer);
-
- p = (char *)malloc(n);
- sprintf(p, CTRUST, hostport, path, refer);
-
- freez(hostport);
- freez(path);
- freez(refer);
-
- return(p);
-
+ return(1);
}
-#endif /* def TRUST_FILES */
+#endif /* def FEATURE_COOKIE_JAR */
/*********************************************************************
*
- * Function : intercept_url
+ * Function : pcrs_filter_response
*
- * Description : checks the URL `basename' against a list of URLs to
- * snarf. If it matches, it calls the associated function
- * which returns an HTML page to send back to the client.
- * Right now, we snarf:
- * "show-proxy-args", and
- * "ij-untrusted-url" (optional w/TRUST_FILES)
+ * 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.
*
* Parameters :
- * 1 : http = http_request request, check `basename's of blocklist
- * 2 : csp = Current client state (buffers, headers, etc...)
- *
- * Returns : NULL for no recognized URLs, or an HTML description page.
+ * 1 : csp = Current client state (buffers, headers, etc...)
*
+ * Returns : a pointer to the (newly allocated) modified buffer.
+ * or NULL in case something went wrong
+ *
*********************************************************************/
-char *intercept_url(struct http_request *http, struct client_state *csp)
+char *pcrs_filter_response(struct client_state *csp)
{
- char *basename;
- const struct interceptors *v;
-
- basename = strrchr(http->path, '/');
+ int hits=0;
+ size_t size;
- if (basename == NULL) return(NULL);
+ char *old = csp->iob->cur, *new = NULL;
+ pcrs_job *job;
- basename ++; /* first char past the last slash */
+ struct file_list *fl;
+ struct re_filterfile_spec *b;
- if (*basename)
+ /* Sanity first */
+ if (csp->iob->cur >= csp->iob->eod)
{
- for (v = intercept_patterns; v->str; v++)
- {
- if (strncmp(basename, v->str, v->len) == 0)
- {
- return((v->interceptor)(http, csp));
- }
- }
+ return(NULL);
}
+ size = csp->iob->eod - csp->iob->cur;
- return(NULL);
+ /*
+ * If the body has a "chunked" transfer-encoding,
+ * get rid of it first, adjusting size and iob->eod
+ */
+ if (csp->flags & CSP_FLAG_CHUNKED)
+ {
+ log_error(LOG_LEVEL_RE_FILTER, "Need to de-chunk first");
+ if (0 == (size = remove_chunked_transfer_coding(csp->iob->cur, size)))
+ {
+ return(NULL);
+ }
+ csp->iob->eod = csp->iob->cur + size;
+ csp->flags |= CSP_FLAG_MODIFIED;
+ }
+
+ if ( ( NULL == (fl = csp->rlist) ) || ( NULL == (b = fl->f) ) )
+ {
+ log_error(LOG_LEVEL_ERROR, "Unable to get current state of regexp filtering.");
+ return(NULL);
+ }
+
+ if ( NULL == b->joblist )
+ {
+ log_error(LOG_LEVEL_RE_FILTER, "Empty joblist. Nothing to do.");
+ return(NULL);
+ }
+
+ log_error(LOG_LEVEL_RE_FILTER, "re_filtering %s%s (size %d) ...",
+ csp->http->hostport, csp->http->path, size);
+
+ /* 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;
+ }
+
+ log_error(LOG_LEVEL_RE_FILTER, " produced %d hits (new size %d).", hits, size);
+
+ /*
+ * If there were no hits, destroy our copy and let
+ * chat() use the original in csp->iob
+ */
+ if (!hits)
+ {
+ free(new);
+ return(NULL);
+ }
+
+ csp->flags |= CSP_FLAG_MODIFIED;
+ csp->content_length = size;
+ IOB_RESET(csp);
+
+ return(new);
+
+}
+
+
+/*********************************************************************
+ *
+ * Function : gif_deanimate_response
+ *
+ * Description : Deanimate the GIF image that has been accumulated in
+ * csp->iob->buf, 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.
+ *
+ *********************************************************************/
+char *gif_deanimate_response(struct client_state *csp)
+{
+ struct binbuffer *in, *out;
+ char *p;
+ int size = csp->iob->eod - csp->iob->cur;
+
+ /*
+ * If the body has a "chunked" transfer-encoding,
+ * get rid of it first, adjusting size and iob->eod
+ */
+ if (csp->flags & CSP_FLAG_CHUNKED)
+ {
+ log_error(LOG_LEVEL_DEANIMATE, "Need to de-chunk first");
+ if (0 == (size = remove_chunked_transfer_coding(csp->iob->cur, size)))
+ {
+ return(NULL);
+ }
+ csp->iob->eod = csp->iob->cur + size;
+ csp->flags |= CSP_FLAG_MODIFIED;
+ }
+
+ if ( (NULL == (in = (struct binbuffer *)zalloc(sizeof *in )))
+ || (NULL == (out = (struct binbuffer *)zalloc(sizeof *out))) )
+ {
+ log_error(LOG_LEVEL_DEANIMATE, "failed! (no mem)");
+ return NULL;
+ }
+
+ in->buffer = csp->iob->cur;
+ in->size = size;
+
+ if (gif_deanimate(in, out, strncmp("last", csp->action->string[ACTION_STRING_DEANIMATE], 4)))
+ {
+ log_error(LOG_LEVEL_DEANIMATE, "failed! (gif parsing)");
+ free(in);
+ buf_free(out);
+ return(NULL);
+ }
+ 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;
+ free(in);
+ free(out);
+ return(p);
+ }
+
+}
+
+
+/*********************************************************************
+ *
+ * Function : remove_chunked_transfer_coding
+ *
+ * Description : In-situ remove the "chunked" transfer coding as defined
+ * in rfc2616 from a buffer.
+ *
+ * Parameters :
+ * 1 : buffer = Pointer to the text buffer
+ * 2 : size = Number of bytes to be processed
+ *
+ * Returns : The new size, i.e. the number of bytes from buffer which
+ * are occupied by the stripped body, or 0 in case something
+ * went wrong
+ *
+ *********************************************************************/
+int remove_chunked_transfer_coding(char *buffer, const size_t size)
+{
+ size_t newsize = 0;
+ unsigned int chunksize = 0;
+ char *from_p, *to_p;
+
+ assert(buffer);
+ from_p = to_p = buffer;
+
+ if (sscanf(buffer, "%x", &chunksize) != 1)
+ {
+ log_error(LOG_LEVEL_ERROR, "Invalid first chunksize while stripping \"chunked\" transfer coding");
+ return(0);
+ }
+
+ while (chunksize > 0)
+ {
+ if (NULL == (from_p = strstr(from_p, "\r\n")))
+ {
+ log_error(LOG_LEVEL_ERROR, "Parse error while stripping \"chunked\" transfer coding");
+ return(0);
+ }
+ newsize += chunksize;
+ from_p += 2;
+
+ memmove(to_p, from_p, (size_t) chunksize);
+ to_p = buffer + newsize;
+ from_p += chunksize + 2;
+
+ if (sscanf(from_p, "%x", &chunksize) != 1)
+ {
+ log_error(LOG_LEVEL_ERROR, "Parse error while stripping \"chunked\" transfer coding");
+ return(0);
+ }
+ }
+
+ /* FIXME: Should this get its own loglevel? */
+ log_error(LOG_LEVEL_RE_FILTER, "De-chunking successful. Shrunk from %d to %d\n", size, newsize);
+ return(newsize);
}
/*********************************************************************
*
- * Function : cookie_url
+ * Function : url_actions
*
- * Description : Accept this cookie, or no? See "cookiefile" setting.
+ * Description : Gets the actions for this URL.
*
* Parameters :
* 1 : http = http_request request for blocked URLs
* 2 : csp = Current client state (buffers, headers, etc...)
*
- * Returns : NULL => accept, cookie_spec pointer to crunch.
+ * Returns : N/A
*
*********************************************************************/
-struct cookie_spec *cookie_url(struct http_request *http, struct client_state *csp)
+void url_actions(struct http_request *http,
+ struct client_state *csp)
{
struct file_list *fl;
- struct cookie_spec *b;
+ struct url_actions *b;
+
+ init_current_action(csp->action);
+
+ if (((fl = csp->actions_list) == NULL) || ((b = fl->f) == NULL))
+ {
+ return;
+ }
+
+ apply_url_actions(csp->action, http, b);
+
+}
+
+
+/*********************************************************************
+ *
+ * Function : apply_url_actions
+ *
+ * Description : Applies a list of URL actions.
+ *
+ * Parameters :
+ * 1 : action = Destination.
+ * 2 : http = Current URL
+ * 3 : b = list of URL actions to apply
+ *
+ * Returns : N/A
+ *
+ *********************************************************************/
+void apply_url_actions(struct current_action_spec *action,
+ struct http_request *http,
+ struct url_actions *b)
+{
struct url_spec url[1];
- if (((fl = csp->clist) == NULL) || ((b = fl->f) == NULL))
+ if (b == NULL)
{
- return(NULL);
+ /* Should never happen */
+ return;
}
*url = dsplit(http->host);
/* if splitting the domain fails, punt */
- if (url->dbuf == NULL) return(NULL);
+ if (url->dbuf == NULL)
+ {
+ return;
+ }
for (b = b->next; NULL != b; b = b->next)
{
#endif
)
{
- freez(url->dbuf);
- freez(url->dvec);
- return(b);
+ merge_current_action(action, b->action);
}
}
}
freez(url->dbuf);
freez(url->dvec);
- return(NULL);
-
}
* 1 : http = http_request request for current URL
* 2 : csp = Current client state (buffers, headers, etc...)
*
- * Returns : Return gw_default for no forward match,
- * else a gateway pointer to a specific forwarding proxy.
+ * Returns : Pointer to forwarding information.
*
*********************************************************************/
-const struct gateway *forward_url(struct http_request *http, struct client_state *csp)
+const struct forward_spec * forward_url(struct http_request *http,
+ struct client_state *csp)
{
- struct file_list *fl;
- struct forward_spec *b;
+ static const struct forward_spec fwd_default[1] = { FORWARD_SPEC_INITIALIZER };
+ struct forward_spec *fwd = csp->config->forward;
struct url_spec url[1];
- if (((fl = csp->flist) == NULL) || ((b = fl->f) == NULL))
+ if (fwd == NULL)
{
- return(gw_default);
+ return(fwd_default);
}
*url = dsplit(http->host);
/* if splitting the domain fails, punt */
- if (url->dbuf == NULL) return(gw_default);
+ if (url->dbuf == NULL)
+ {
+ return(fwd_default);
+ }
- for (b = b->next; b ; b = b->next)
+ while (fwd != NULL)
{
- if ((b->url->port == 0) || (b->url->port == http->port))
+ if ((fwd->url->port == 0) || (fwd->url->port == http->port))
{
- if ((b->url->domain[0] == '\0') || (domaincmp(b->url, url) == 0))
+ if ((fwd->url->domain[0] == '\0') || (domaincmp(fwd->url, url) == 0))
{
- if ((b->url->path == NULL) ||
+ if ((fwd->url->path == NULL) ||
#ifdef REGEX
- (regexec(b->url->preg, http->path, 0, NULL, 0) == 0)
+ (regexec(fwd->url->preg, http->path, 0, NULL, 0) == 0)
#else
- (strncmp(b->url->path, http->path, b->url->pathlen) == 0)
+ (strncmp(fwd->url->path, http->path, fwd->url->pathlen) == 0)
#endif
)
{
freez(url->dbuf);
freez(url->dvec);
- return(b->gw);
+ return(fwd);
}
}
}
+ fwd = fwd->next;
}
freez(url->dbuf);
freez(url->dvec);
- return(gw_default);
+ return(fwd_default);
}
struct url_spec dsplit(char *domain)
{
struct url_spec ret[1];
- char *v[BUFSIZ];
+ char *v[BUFFER_SIZE];
int size;
char *p;
memset(ret, '\0', sizeof(*ret));
- if ((p = strrchr(domain, '.')))
+ if (domain[strlen(domain) - 1] == '.')
{
- if (*(++p) == '\0')
- {
- ret->toplevel = 1;
- }
+ ret->unanchored |= ANCHOR_RIGHT;
+ }
+
+ if (domain[0] == '.')
+ {
+ ret->unanchored |= ANCHOR_LEFT;
}
ret->dbuf = strdup(domain);
/*********************************************************************
*
- * Function : domaincmp
+ * Function : simple_domaincmp
*
- * Description : Compare domain names.
- * domaincmp("a.b.c" , "a.b.c") => 0 (MATCH)
- * domaincmp("a*.b.c", "a.b.c") => 0 (MATCH)
- * domaincmp("b.c" , "a.b.c") => 0 (MATCH)
- * domaincmp("" , "a.b.c") => 0 (MATCH)
+ * Description : Domain-wise Compare fqdn's. The comparison is
+ * both left- and right-anchored. The individual
+ * domain names are compared with simplematch().
+ * This is only used by domaincmp.
*
* Parameters :
- * 1 : pattern = a domain that may contain a '*' as a wildcard.
- * 2 : fqdn = domain name against which the patterns are compared.
+ * 1 : pv = array of patterns to compare
+ * 2 : fv = array of domain components to compare
+ * 3 : len = length of the arrays (both arrays are the
+ * same length - if they weren't, it couldn't
+ * possibly be a match).
*
* Returns : 0 => domains are equivalent, else no match.
*
*********************************************************************/
-int domaincmp(struct url_spec *pattern, struct url_spec *fqdn)
+static int simple_domaincmp(char **pv, char **fv, int len)
{
- char **pv, **fv; /* vectors */
- int pn, fn; /* counters */
- char *p, *f; /* chars */
-
- pv = pattern->dvec;
- pn = pattern->dcnt;
-
- fv = fqdn->dvec;
- fn = fqdn->dcnt;
+ int n;
- while ((pn > 0) && (fn > 0))
+ for (n = 0; n < len; n++)
{
- p = pv[--pn];
- f = fv[--fn];
-
- while (*p && *f && (*p == tolower(*f)))
+ if (simplematch(pv[n], fv[n]))
{
- p++, f++;
+ return 1;
}
-
- if ((*p != tolower(*f)) && (*p != '*')) return(1);
}
- if (pn > 0) return(1);
-
- return(0);
+ return 0;
}
-/* intercept functions */
-
/*********************************************************************
*
- * Function : show_proxy_args
+ * Function : domaincmp
*
- * Description : This "crunch"es "http:/any.thing/show-proxy-args" and
- * returns a web page describing the current status of IJB.
+ * Description : Domain-wise Compare fqdn's. Governed by the bimap in
+ * pattern->unachored, the comparison is un-, left-,
+ * right-anchored, or both.
+ * The individual domain names are compared with
+ * simplematch().
*
* Parameters :
- * 1 : http = ignored
- * 2 : csp = Current client state (buffers, headers, etc...)
+ * 1 : pattern = a domain that may contain a '*' as a wildcard.
+ * 2 : fqdn = domain name against which the patterns are compared.
*
- * Returns : A string that contains the current status of IJB.
+ * Returns : 0 => domains are equivalent, else no match.
*
*********************************************************************/
-char *show_proxy_args(struct http_request *http, struct client_state *csp)
+int domaincmp(struct url_spec *pattern, struct url_spec *fqdn)
{
- char *s = NULL;
-
-#ifdef SPLIT_PROXY_ARGS
- FILE * fp;
- char buf[BUFSIZ];
- char * p;
- const char * filename = NULL;
- const char * file_description = NULL;
- char * query_string = strrchr(http->path, '?');
- char which_file = '\0';
+ char **pv, **fv; /* vectors */
+ int plen, flen;
+ int unanchored = pattern->unanchored & (ANCHOR_RIGHT | ANCHOR_LEFT);
+ plen = pattern->dcnt;
+ flen = fqdn->dcnt;
- if (query_string != NULL)
+ if (flen < plen)
{
- /* first char past the last '?' (maybe '\0')*/
- which_file = query_string[1];
+ /* fqdn is too short to match this pattern */
+ return 1;
}
- switch (which_file)
- {
- case 'b':
- if (csp->blist)
- {
- filename = csp->blist->filename;
- file_description = "Block List";
- }
- break;
- case 'c':
- if (csp->clist)
- {
- filename = csp->clist->filename;
- file_description = "Cookie List";
- }
- break;
- case 'f':
- if (csp->flist)
- {
- filename = csp->flist->filename;
- file_description = "Forward List";
- }
- break;
-
-#ifdef ACL_FILES
- case 'a':
- if (csp->alist)
- {
- filename = csp->alist->filename;
- file_description = "Access Control List";
- }
- break;
-#endif /* def ACL_FILES */
-
-#ifdef USE_IMAGE_LIST
- case 'i':
- if (csp->ilist)
- {
- filename = csp->ilist->filename;
- file_description = "Image List";
- }
- break;
-#endif /* def USE_IMAGE_LIST */
-#ifdef KILLPOPUPS
- case 'p':
- if (csp->plist)
- {
- filename = csp->plist->filename;
- file_description = "Popup list";
- }
- break;
-#endif /* def KILLPOPUPS */
-
-#ifdef PCRS
- case 'r':
- if (csp->rlist)
- {
- filename = csp->rlist->filename;
- file_description = "RE Filter List";
- }
- break;
-#endif /* def PCRS */
+ pv = pattern->dvec;
+ fv = fqdn->dvec;
-#ifdef TRUST_FILES
- case 't':
- if (csp->tlist)
- {
- filename = csp->tlist->filename;
- file_description = "Trust List";
- }
- break;
-#endif /* def TRUST_FILES */
+ if (unanchored == ANCHOR_LEFT)
+ {
+ /*
+ * Right anchored.
+ *
+ * Convert this into a fully anchored pattern with
+ * the fqdn and pattern the same length
+ */
+ fv += (flen - plen); /* flen - plen >= 0 due to check above */
+ return simple_domaincmp(pv, fv, plen);
}
-
- if (filename)
+ else if (unanchored == 0)
{
- /* Display specified file */
- /* FIXME: Add HTTP headers so this isn't cached */
- s = strsav(s,
- "HTTP/1.0 200 OK\n"
- "Server: IJ/" VERSION "\n"
- "Content-type: text/html\n"
- "Pragma: no-cache\n"
- "Last-Modified: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "Expires: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "\n"
-
- "<html>"
- "<head>"
- "<title>Internet Junkbuster Proxy Status - ");
- s = strsav(s, file_description);
- s = strsav(s,
- "</title>"
- "</head>\n"
- "<body bgcolor=\"#f8f8f0\" link=\"#000078\" alink=\"#ff0022\" vlink=\"#787878\">\n"
- "<center>\n"
- "<h1>" BANNER "\n");
- s = strsav(s, file_description);
- s = strsav(s,
- "</h1></center>\n"
- "<p><a href=\"show-proxy-args\">Back to proxy status</a></p>\n"
- "<h2>");
- s = strsav(s, file_description);
- s = strsav(s,
- "</h2>\n"
- "Contents of file "<code>");
- p = html_encode(filename);
- s = strsav(s, p);
- freez(p);
- s = strsav(s,
- "</code>":<br>\n"
- "</p>\n"
- "<pre>");
-
- if ((fp = fopen(filename, "r")) == NULL)
+ /* Fully anchored, check length */
+ if (flen != plen)
{
- s = strsav(s, "</pre><h1>ERROR OPENING FILE!</h1><pre>");
+ return 1;
}
- else
- {
- while (fgets(buf, sizeof(buf), fp))
- {
- p = html_encode(buf);
- if (p)
- {
- s = strsav(s, p);
- freez(p);
- s = strsav(s, "<br>");
- }
- }
- fclose(fp);
- }
-
- s = strsav(s,
- "</pre>\n"
- "<br>\n"
- "<p><a href=\"show-proxy-args\">Back to proxy status</a></p>\n"
- "<br>\n"
- "<small><small><p>\n"
- "Code and documentation of the " BANNER " Proxy"
- "<sup><small>TM</small></sup>\n"
- "<a href=\"http://www.junkbusters.com/ht/en/legal.html#copy\">\n" "Copyright</a>© 1997 Junkbusters Corporation\n"
- "<a href=\"http://www.junkbusters.com/ht/en/legal.html#marks\"><sup><small>TM</small></sup></a><br>\n"
- "Copying and distribution permitted under the"
- "<a href=\"http://www.gnu.org/copyleft/gpl.html\">\n"
- "<small>GNU</small></a> "
- "General Public License.\n"
- "</small>"
- "<address><kbd>webmaster@junkbusters.com</kbd></address>"
- "</small>"
- "</body></html>\n");
- return(s);
- }
-#endif /* def SPLIT_PROXY_ARGS */
-
- s = strsav(s, proxy_args->header);
- s = strsav(s, proxy_args->invocation);
-#ifdef STATISTICS
- s = add_stats(s);
-#endif /* def STATISTICS */
- s = strsav(s, proxy_args->gateways);
-
-#ifdef SPLIT_PROXY_ARGS
- s = strsav(s,
- "<h2>The following files are in use:</h2>\n"
- "<p>(Click a filename to view it)</p>\n"
- "<ul>\n");
-
- if (csp->blist)
- {
- s = strsav(s, "<li>Block List: <a href=\"show-proxy-args?block\"><code>");
- s = strsav(s, csp->blist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-
- if (csp->clist)
- {
- s = strsav(s, "<li>Cookie List: <a href=\"show-proxy-args?cookie\"><code>");
- s = strsav(s, csp->clist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-
- if (csp->flist)
- {
- s = strsav(s, "<li>Forward List: <a href=\"show-proxy-args?forward\"><code>");
- s = strsav(s, csp->flist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-
-#ifdef ACL_FILES
- if (csp->alist)
- {
- s = strsav(s, "<li>Access Control List: <a href=\"show-proxy-args?acl\"><code>");
- s = strsav(s, csp->alist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-#endif /* def ACL_FILES */
-
-#ifdef USE_IMAGE_LIST
- if (csp->ilist)
- {
- s = strsav(s, "<li>Image List: <a href=\"show-proxy-args?image\"><code>");
- s = strsav(s, csp->ilist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-#endif /* def USE_IMAGE_LIST */
-
-#ifdef KILLPOPUPS
- if (csp->plist)
- {
- s = strsav(s, "<li>Popup List: <a href=\"show-proxy-args?popup\"><code>");
- s = strsav(s, csp->plist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-#endif /* def KILLPOPUPS */
-
-#ifdef PCRS
- if (csp->rlist)
- {
- s = strsav(s, "<li>RE Filter List: <a href=\"show-proxy-args?re\"><code>");
- s = strsav(s, csp->rlist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-#endif /* def PCRS */
-
-#ifdef TRUST_FILES
- if (csp->tlist)
- {
- s = strsav(s, "<li>Trust List: <a href=\"show-proxy-args?trust\"><code>");
- s = strsav(s, csp->tlist->filename);
- s = strsav(s, "</code></a></li>\n");
- }
-#endif /* def TRUST_FILES */
-
- s = strsav(s, "</ul>");
-
-#else /* ifndef SPLIT_PROXY_ARGS */
- if (csp->blist)
- {
- s = strsav(s, csp->blist->proxy_args);
- }
-
- if (csp->clist)
- {
- s = strsav(s, csp->clist->proxy_args);
- }
-
- if (csp->flist)
- {
- s = strsav(s, csp->flist->proxy_args);
- }
-
-#ifdef ACL_FILES
- if (csp->alist)
- {
- s = strsav(s, csp->alist->proxy_args);
- }
-#endif /* def ACL_FILES */
-
-#ifdef USE_IMAGE_LIST
- if (csp->ilist)
- {
- s = strsav(s, csp->ilist->proxy_args);
- }
-#endif /* def USE_IMAGE_LIST */
-
-#ifdef KILLPOPUPS
- if (csp->plist)
- {
- s = strsav(s, csp->plist->proxy_args);
- }
-#endif /* def KILLPOPUPS */
-
-#ifdef PCRS
- if (csp->rlist)
- {
- s = strsav(s, csp->rlist->proxy_args);
+ return simple_domaincmp(pv, fv, plen);
}
-#endif /* def PCRS */
-
-#ifdef TRUST_FILES
- if (csp->tlist)
+ else if (unanchored == ANCHOR_RIGHT)
{
- s = strsav(s, csp->tlist->proxy_args);
- }
-#endif /* def TRUST_FILES */
-
-#endif /* ndef SPLIT_PROXY_ARGS */
-
- s = strsav(s, proxy_args->trailer);
-
- return(s);
-
-}
-
-
-#ifdef TRUST_FILES
-/*********************************************************************
- *
- * Function : ij_untrusted_url
- *
- * Description : This "crunch"es "http:/any.thing/ij-untrusted-url" and
- * returns a web page describing why it was untrusted.
- *
- * Parameters :
- * 1 : http = http_request request for crunched URL
- * 2 : csp = Current client state (buffers, headers, etc...)
- *
- * Returns : A string that contains why this was untrusted.
- *
- *********************************************************************/
-char *ij_untrusted_url(struct http_request *http, struct client_state *csp)
-{
- int n;
- char *hostport, *path, *refer, *p, *v[9];
- char buf[BUFSIZ];
- struct url_spec **tl, *t;
-
-
- static const char format[] =
- "HTTP/1.0 200 OK\r\n"
- "Pragma: no-cache\n"
- "Last-Modified: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "Expires: Thu Jul 31, 1997 07:42:22 pm GMT\n"
- "Content-Type: text/html\n\n"
- "<html>\n"
- "<head>\n"
- "<title>Internet Junkbuster: Request for untrusted URL</title>\n"
- "</head>\n"
- BODY
- "<center><h1>"
- BANNER
- "</h1></center>"
- "The " BANNER " Proxy "
- "<A href=\"" HOME_PAGE_URL "\">"
- "(" HOME_PAGE_URL ") </A>"
- "intercepted the request for %s%s\n"
- "because the URL is not trusted.\n"
- "<br><br>\n";
-
- if ((n = ssplit(http->path, "?+", v, SZ(v), 0, 0)) == 4)
- {
- hostport = url_decode(v[1]);
- path = url_decode(v[2]);
- refer = url_decode(v[3]);
+ /* Left anchored, ignore all extra in fqdn */
+ return simple_domaincmp(pv, fv, plen);
}
else
{
- hostport = strdup("undefined_host");
- path = strdup("/undefined_path");
- refer = strdup("undefined");
- }
-
- n = sizeof(format);
- n += strlen(hostport);
- n += strlen(path );
-
- if ((p = (char *)malloc(n)))
- {
- sprintf(p, format, hostport, path);
- }
-
- strsav(p, "The referrer in this request was <strong>");
- strsav(p, refer);
- strsav(p, "</strong><br>\n");
-
- freez(hostport);
- freez(path );
- freez(refer );
-
- p = strsav(p, "<h3>The following referrers are trusted</h3>\n");
-
- for (tl = trust_list; (t = *tl) ; tl++)
- {
- sprintf(buf, "%s<br>\n", t->spec);
- p = strsav(p, buf);
- }
-
- if (trust_info->next)
- {
- struct list *l;
-
- strcpy(buf,
- "<p>"
- "You can learn more about what this means "
- "and what you may be able to do about it by "
- "reading the following documents:<br>\n"
- "<ol>\n"
- );
-
- p = strsav(p, buf);
-
- for (l = trust_info->next; l ; l = l->next)
+ /* Unanchored */
+ int n;
+ int maxn = flen - plen;
+ for (n = 0; n <= maxn; n++)
{
- sprintf(buf,
- "<li> <a href=%s>%s</a><br>\n",
- l->str, l->str);
- p = strsav(p, buf);
+ if (!simple_domaincmp(pv, fv, plen))
+ {
+ return 0;
+ }
+ /*
+ * Doesn't match from start of fqdn
+ * Try skipping first part of fqdn
+ */
+ fv++;
}
-
- p = strsav(p, "</ol>\n");
- }
-
- p = strsav(p, "</body>\n" "</html>\n");
-
- return(p);
-
-}
-#endif /* def TRUST_FILES */
-
-
-#ifdef STATISTICS
-/*********************************************************************
- *
- * Function : add_stats
- *
- * Description : Statistics function of JB. Called by `show_proxy_args'.
- *
- * Parameters :
- * 1 : s = string that holds the proxy args description page
- *
- * Returns : A pointer to the descriptive status web page.
- *
- *********************************************************************/
-char *add_stats(char *s)
-{
- /*
- * Output details of the number of requests rejected and
- * accepted. This is switchable in the junkbuster config.
- * Does nothing if this option is not enabled.
- */
-
- float perc_rej; /* Percentage of http requests rejected */
- char out_str[81];
- int local_urls_read = urls_read;
- int local_urls_rejected = urls_rejected;
-
- /*
- * Need to alter the stats not to include the fetch of this
- * page.
- *
- * Can't do following thread safely! doh!
- *
- * urls_read--;
- * urls_rejected--; * This will be incremented subsequently *
- */
-
- s = strsav(s,"<h2>Statistics for this " BANNER ":</h2>\n");
-
- if (local_urls_read == 0)
- {
-
- s = strsav(s,"No activity so far!\n");
-
- }
- else
- {
-
- perc_rej = (float)local_urls_rejected * 100.0F /
- (float)local_urls_read;
-
- sprintf(out_str,
- "%d requests received, %d filtered "
- "(%6.2f %%).",
- local_urls_read,
- local_urls_rejected, perc_rej);
-
- s = strsav(s,out_str);
+ return 1;
}
- return(s);
}
-#endif /* def STATISTICS */
/*