-const char parsers_rcs[] = "$Id: parsers.c,v 1.1.1.1 2001/05/15 13:59:01 oes Exp $";
+const char parsers_rcs[] = "$Id: parsers.c,v 1.16 2001/06/29 13:32:42 oes Exp $";
/*********************************************************************
*
* File : $Source: /cvsroot/ijbswa/current/parsers.c,v $
* `client_x_forwarded_adder', `client_xtra_adder',
* `content_type', `crumble', `destroy_list', `enlist',
* `flush_socket', `free_http_request', `get_header',
- * `list_to_text', `match', `parse_http_request', `sed',
+ * `list_to_text', `parse_http_request', `sed',
* and `server_set_cookie'.
*
* Copyright : Written by and Copyright (C) 2001 the SourceForge
*
* Revisions :
* $Log: parsers.c,v $
+ * Revision 1.16 2001/06/29 13:32:42 oes
+ * - Fixed a comment
+ * - Adapted free_http_request
+ * - Removed logentry from cancelled commit
+ *
+ * Revision 1.15 2001/06/03 19:12:38 oes
+ * deleted const struct interceptors
+ *
+ * Revision 1.14 2001/06/01 18:49:17 jongfoster
+ * Replaced "list_share" with "list" - the tiny memory gain was not
+ * worth the extra complexity.
+ *
+ * Revision 1.13 2001/05/31 21:30:33 jongfoster
+ * Removed list code - it's now in list.[ch]
+ * Renamed "permission" to "action", and changed many features
+ * to use the actions file rather than the global config.
+ *
+ * Revision 1.12 2001/05/31 17:33:13 oes
+ *
+ * CRLF -> LF
+ *
+ * Revision 1.11 2001/05/29 20:11:19 joergs
+ * '/* inside comment' warning removed.
+ *
+ * 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 2001/05/28 17:26:33 jongfoster
+ * Fixing segfault if last header was crunched.
+ * Fixing Windows build (snprintf() is _snprintf() under Win32, but we
+ * can use the cross-platform sprintf() instead.)
+ *
+ * Revision 1.8 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 1.7 2001/05/27 13:19:06 oes
+ * Patched Joergs solution for the content-length in.
+ *
+ * Revision 1.6 2001/05/26 13:39:32 jongfoster
+ * Only crunches Content-Length header if applying RE filtering.
+ * Without this fix, Microsoft Windows Update wouldn't work.
+ *
+ * Revision 1.5 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 1.4 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 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 1.2 2001/05/17 23:02:36 oes
+ * - Made referrer option accept 'L' as a substitute for '§'
+ *
* Revision 1.1.1.1 2001/05/15 13:59:01 oes
* Initial import of version 2.9.3 source tree
*
#endif
#include "project.h"
+#include "list.h"
#include "parsers.h"
#include "encode.h"
#include "filters.h"
#include "errlog.h"
#include "jbsockets.h"
#include "miscutil.h"
+#include "cgi.h"
const char parsers_h_rcs[] = PARSERS_H_VERSION;
{ NULL, 0, NULL }
};
-const struct interceptors intercept_patterns[] = {
- { "show-proxy-args", 14, show_proxy_args },
-#ifdef TRUST_FILES
- { "ij-untrusted-url", 14, ij_untrusted_url },
-#endif /* def TRUST_FILES */
- { NULL, 0, NULL }
-};
const struct parsers server_patterns[] = {
{ "set-cookie:", 11, server_set_cookie },
{ "connection:", 11, crumble },
-#ifdef PCRS
+#if defined(PCRS) || defined(KILLPOPUPS)
{ "Content-Type:", 13, content_type },
- { "Content-Length:", 15, crumble },
+#endif /* defined(PCRS) || defined(KILLPOPUPS) */
+#ifdef PCRS
+ { "Content-Length:", 15, content_length },
#endif /* def PCRS */
{ NULL, 0, NULL }
};
};
-/*********************************************************************
- *
- * Function : match
- *
- * Description : Do a `strncmpic' on every pattern in pats.
- *
- * Parameters :
- * 1 : buf = a string to match to a list of patterns
- * 2 : pats = list of strings to compare against buf.
- *
- * Returns : Return the matching "struct parsers *",
- * or NULL if no pattern matches.
- *
- *********************************************************************/
-static const struct parsers *match(char *buf, const struct parsers *pats)
-{
- const struct parsers *v;
-
- if (buf == NULL)
- {
- /* hit me */
- log_error(LOG_LEVEL_ERROR, "NULL parameter to match()");
- return(NULL);
- }
-
- for (v = pats; v->str ; v++)
- {
- if (strncmpic(buf, v->str, v->len) == 0)
- {
- return(v);
- }
- }
- return(NULL);
-
-}
-
-
/*********************************************************************
*
* Function : flush_socket
}
-/*********************************************************************
- *
- * Function : enlist
- *
- * Description : Append a string into a specified string list.
- *
- * Parameters :
- * 1 : h = pointer to list 'dummy' header
- * 2 : s = string to add to the list
- *
- * Returns : N/A
- *
- *********************************************************************/
-void enlist(struct list *h, const char *s)
-{
- struct list *n = (struct list *)malloc(sizeof(*n));
- struct list *l;
-
- if (n)
- {
- n->str = strdup(s);
- n->next = NULL;
-
- if ((l = h->last))
- {
- l->next = n;
- }
- else
- {
- h->next = n;
- }
-
- h->last = n;
- }
-
-}
-
-
-/*********************************************************************
- *
- * Function : destroy_list
- *
- * Description : Destroy a string list (opposite of enlist)
- *
- * Parameters :
- * 1 : h = pointer to list 'dummy' header
- *
- * Returns : N/A
- *
- *********************************************************************/
-void destroy_list(struct list *h)
-{
- struct list *p, *n;
-
- for (p = h->next; p ; p = n)
- {
- n = p->next;
- freez(p->str);
- freez(p);
- }
-
- memset(h, '\0', sizeof(*h));
-
-}
-
-
-/*********************************************************************
- *
- * Function : list_to_text
- *
- * Description : "Flaten" a string list into 1 long \r\n delimited string.
- *
- * Parameters :
- * 1 : h = pointer to list 'dummy' header
- *
- * Returns : NULL on malloc error, else new long string.
- *
- *********************************************************************/
-static char *list_to_text(struct list *h)
-{
- struct list *p;
- char *ret = NULL;
- char *s;
- int size;
-
- size = 0;
-
- for (p = h->next; p ; p = p->next)
- {
- if (p->str)
- {
- size += strlen(p->str) + 2;
- }
- }
-
- if ((ret = (char *)malloc(size + 1)) == NULL)
- {
- return(NULL);
- }
-
- ret[size] = '\0';
-
- s = ret;
-
- for (p = h->next; p ; p = p->next)
- {
- if (p->str)
- {
- strcpy(s, p->str);
- s += strlen(s);
- *s++ = '\r'; *s++ = '\n';
- }
- }
-
- return(ret);
-
-}
-
-
/*********************************************************************
*
* Function : sed
char *hdr;
void (* const *f)();
- for (p = csp->headers->next; p ; p = p->next)
+ for (v = pats; v->str ; v++)
{
- log_error(LOG_LEVEL_HEADER, "scan: %s", p->str);
-
- if ((v = match(p->str, pats)))
+ for (p = csp->headers->next; p ; p = p->next)
{
- hdr = v->parser(v, p->str, csp);
- freez(p->str);
- p->str = hdr;
- }
+ /* Header crunch()ed in previous run? -> ignore */
+ if (p->str == NULL) continue;
+
+ if (v == pats) log_error(LOG_LEVEL_HEADER, "scan: %s", p->str);
+ if (strncmpic(p->str, v->str, v->len) == 0)
+ {
+ hdr = v->parser(v, p->str, csp);
+ freez(p->str);
+ p->str = hdr;
+ }
+ }
}
/* place any additional headers on the csp->headers list */
(*f)(csp);
}
- /* add the blank line at the end of the header */
- enlist(csp->headers, "");
+ /* add the blank line at the end of the header, if necessary */
+ if ( (csp->headers->last == NULL)
+ || (csp->headers->last->str == NULL)
+ || (*csp->headers->last->str != '\0') )
+ {
+ enlist(csp->headers, "");
+ }
hdr = list_to_text(csp->headers);
freez(http->hostport);
freez(http->path);
freez(http->ver);
+ freez(http->host_ip_addr_str);
}
}
-#ifdef PCRS
+#if defined(PCRS) || defined(KILLPOPUPS)
/*********************************************************************
*
* Function : content_type
*
- * Description : Is this a text/* or javascript MIME Type?
+ * Description : Is this a text/.* or javascript MIME Type?
*
* Parameters :
* 1 : v = ignored
return(strdup(s));
}
+#endif /* defined(PCRS) || defined(KILLPOPUPS) */
+
+
+#ifdef PCRS
+/*********************************************************************
+ *
+ * Function : content_length
+ *
+ * Description : Adjust Content-Length header if we have
+ * filtered this page through PCRS.
+ *
+ * Parameters :
+ * 1 : v = ignored
+ * 2 : s = header string we are "considering"
+ * 3 : csp = Current client state (buffers, headers, etc...)
+ *
+ * Returns : A duplicate string pointer to this header (ie. pass thru)
+ *
+ *********************************************************************/
+char *content_length(const struct parsers *v, char *s, struct client_state *csp)
+{
+ if (csp->content_length != 0) /* Content has been modified */
+ {
+ s = (char *) zalloc(100);
+ sprintf(s, "Content-Length: %d", csp->content_length);
+ log_error(LOG_LEVEL_HEADER, "Adjust Content-Length to %d", csp->content_length);
+ return(s);
+ }
+ else
+ {
+ return(strdup(s));
+ }
+}
#endif /* def PCRS */
*********************************************************************/
char *client_referrer(const struct parsers *v, char *s, struct client_state *csp)
{
+ const char * newval;
#ifdef FORCE_LOAD
/* Since the referrer can include the prefix even
* even if the request itself is non-forced, we must
strclean(s, FORCE_PREFIX);
#endif /* def FORCE_LOAD */
+#ifdef TRUST_FILES
csp->referrer = strdup(s);
+#endif /* def TRUST_FILES */
- if (referrer == NULL)
+ /*
+ * Are we sending referer?
+ */
+ if ((csp->action->flags & ACTION_HIDE_REFERER) == 0)
{
- log_error(LOG_LEVEL_HEADER, "crunch!");
- return(NULL);
+ return(strdup(s));
}
- if (*referrer == '.')
+ newval = csp->action->string[ACTION_STRING_REFERER];
+
+ /*
+ * Are we blocking referer?
+ */
+ if ((newval == NULL) || (0 == strcmpic(newval, "block")) )
{
- return(strdup(s));
+ log_error(LOG_LEVEL_HEADER, "crunch!");
+ return(NULL);
}
- if (*referrer == '@')
+ /*
+ * Are we forging referer?
+ */
+ if (0 == strcmpic(newval, "forge"))
{
- if (csp->send_user_cookie)
- {
- return(strdup(s));
- }
- else
- {
- log_error(LOG_LEVEL_HEADER, "crunch!");
- return(NULL);
- }
+ /*
+ * Forge a referer as http://[hostname:port of REQUEST]/
+ * to fool stupid checks for in-site links
+ */
+ log_error(LOG_LEVEL_HEADER, "crunch+forge!");
+ s = strsav(NULL, "Referer: ");
+ s = strsav(s, "http://");
+ s = strsav(s, csp->http->hostport);
+ s = strsav(s, "/");
+ return(s);
}
/*
- * New option § or L: Forge a referer as http://[hostname:port of REQUEST]/
- * to fool stupid checks for in-site links
+ * Have we got a fixed referer?
*/
-
- if (*referrer == '§' || *referrer == 'L')
+ if (0 == strncmpic(newval, "http://", 7))
{
- if (csp->send_user_cookie)
- {
- return(strdup(s));
- }
- else
- {
- log_error(LOG_LEVEL_HEADER, "crunch+forge!");
- s = strsav(NULL, "Referer: ");
- s = strsav(s, "http://");
- s = strsav(s, csp->http->hostport);
- s = strsav(s, "/");
- return(s);
- }
+ /*
+ * We have a specific (fixed) referer we want to send.
+ */
+
+ log_error(LOG_LEVEL_HEADER, "modified");
+
+ s = strsav( NULL, "Referer: " );
+ s = strsav( s, newval );
+ return(s);
}
- log_error(LOG_LEVEL_HEADER, "modified");
+ /* Should never get here! */
+ log_error(LOG_LEVEL_ERROR, "Bad parameter: +referer{%s}", newval);
- s = strsav( NULL, "Referer: " );
- s = strsav( s, referrer );
+ /*
+ * Forge is probably the best default.
+ *
+ * Forge a referer as http://[hostname:port of REQUEST]/
+ * to fool stupid checks for in-site links
+ */
+ log_error(LOG_LEVEL_HEADER, "crunch+forge!");
+ s = strsav(NULL, "Referer: ");
+ s = strsav(s, "http://");
+ s = strsav(s, csp->http->hostport);
+ s = strsav(s, "/");
return(s);
-
}
*********************************************************************/
char *client_uagent(const struct parsers *v, char *s, struct client_state *csp)
{
+ const char * newval;
+
#ifdef DETECT_MSIE_IMAGES
if (strstr (s, "MSIE "))
{
}
#endif /* def DETECT_MSIE_IMAGES */
- if (uagent == NULL)
- {
- log_error(LOG_LEVEL_HEADER, "default");
- return(strdup(DEFAULT_USER_AGENT));
- }
-
- if (*uagent == '.')
+ if ((csp->action->flags & ACTION_HIDE_USER_AGENT) == 0)
{
return(strdup(s));
}
- if (*uagent == '@')
+ newval = csp->action->string[ACTION_STRING_USER_AGENT];
+ if (newval == NULL)
{
- if (csp->send_user_cookie)
- {
- return(strdup(s));
- }
- else
- {
- log_error(LOG_LEVEL_HEADER, "default");
- return(strdup(DEFAULT_USER_AGENT));
- }
+ return(strdup(s));
}
log_error(LOG_LEVEL_HEADER, "modified");
s = strsav( NULL, "User-Agent: " );
- s = strsav( s, uagent );
+ s = strsav( s, newval );
return(s);
}
*********************************************************************/
char *client_ua(const struct parsers *v, char *s, struct client_state *csp)
{
- if (uagent == NULL)
- {
- log_error(LOG_LEVEL_HEADER, "crunch!");
- return(NULL);
- }
-
- if (*uagent == '.')
+ if ((csp->action->flags & ACTION_HIDE_USER_AGENT) == 0)
{
return(strdup(s));
}
-
- if (*uagent == '@')
+ else
{
- if (csp->send_user_cookie)
- {
- return(strdup(s));
- }
- else
- {
- log_error(LOG_LEVEL_HEADER, "crunch!");
- return(NULL);
- }
+ log_error(LOG_LEVEL_HEADER, "crunch!");
+ return(NULL);
}
-
- log_error(LOG_LEVEL_HEADER, "crunch!");
- return(NULL);
-
}
*********************************************************************/
char *client_from(const struct parsers *v, char *s, struct client_state *csp)
{
- /* if not set, zap it */
- if (from == NULL)
+ const char * newval;
+
+ if ((csp->action->flags & ACTION_HIDE_FROM) == 0)
{
- log_error(LOG_LEVEL_HEADER, "crunch!");
- return(NULL);
+ return(strdup(s));
}
- if (*from == '.')
+ newval = csp->action->string[ACTION_STRING_FROM];
+
+ /*
+ * Are we blocking referer?
+ */
+ if ((newval == NULL) || (0 == strcmpic(newval, "block")) )
{
- return(strdup(s));
+ log_error(LOG_LEVEL_HEADER, "crunch!");
+ return(NULL);
}
log_error(LOG_LEVEL_HEADER, " modified");
s = strsav( NULL, "From: " );
- s = strsav( s, from );
+ s = strsav( s, newval );
return(s);
}
*********************************************************************/
char *client_send_cookie(const struct parsers *v, char *s, struct client_state *csp)
{
- if (csp->send_user_cookie)
+ if ((csp->action->flags & ACTION_NO_COOKIE_READ) == 0)
{
enlist(csp->cookie_list, s + v->len + 1);
}
*********************************************************************/
char *client_x_forwarded(const struct parsers *v, char *s, struct client_state *csp)
{
- if (add_forwarded)
+ if ((csp->action->flags & ACTION_HIDE_FORWARDED) == 0)
{
+ /* Save it so we can re-add it later */
csp->x_forwarded = strdup(s);
}
*********************************************************************/
void client_cookie_adder(struct client_state *csp)
{
- struct list *l;
+ struct list *lst;
char *tmp = NULL;
char *e;
- for (l = csp->cookie_list->next; l ; l = l->next)
+ for (lst = csp->cookie_list->next; lst ; lst = lst->next)
{
if (tmp)
{
tmp = strsav(tmp, "; ");
}
- tmp = strsav(tmp, l->str);
+ tmp = strsav(tmp, lst->str);
}
- for (l = wafer_list->next; l ; l = l->next)
+ for (lst = csp->action->multi[ACTION_MULTI_WAFER]->next; lst ; lst = lst->next)
{
if (tmp)
{
tmp = strsav(tmp, "; ");
}
- if ((e = cookie_encode(l->str)))
+ if ((e = cookie_encode(lst->str)))
{
tmp = strsav(tmp, e);
freez(e);
*********************************************************************/
void client_xtra_adder(struct client_state *csp)
{
- struct list *l;
+ struct list *lst = csp->action->multi[ACTION_MULTI_ADD_HEADER];
- for (l = xtra_list->next; l ; l = l->next)
+ for (lst = lst->next; lst ; lst = lst->next)
{
- log_error(LOG_LEVEL_HEADER, "addh: %s", l->str);
- enlist(csp->headers, l->str);
+ log_error(LOG_LEVEL_HEADER, "addh: %s", lst->str);
+ enlist(csp->headers, lst->str);
}
}
{
char *p = NULL;
- if (add_forwarded == 0) return;
+ if ((csp->action->flags & ACTION_HIDE_FORWARDED) != 0)
+ {
+ return;
+ }
if (csp->x_forwarded)
{
char *server_set_cookie(const struct parsers *v, char *s, struct client_state *csp)
{
#ifdef JAR_FILES
- if (jar)
+ if (csp->config->jar)
{
- fprintf(jar, "%s\t%s\n", csp->http->host, (s + v->len + 1));
+ fprintf(csp->config->jar, "%s\t%s\n", csp->http->host, (s + v->len + 1));
}
#endif /* def JAR_FILES */
- if (csp->accept_server_cookie == 0)
+ if ((csp->action->flags & ACTION_NO_COOKIE_SET) != 0)
{
return(crumble(v, s, csp));
}