X-Git-Url: http://www.privoxy.org/gitweb/?a=blobdiff_plain;f=filters.c;h=48506d57cfb1294c4b8858c77909d95a858f0bf2;hb=0387d3626e82986c9f271890eac35a173b494b99;hp=29cee4788a9b1f77688c0cb80d33b8020b7dcf63;hpb=c75584ebcc79f939fb4ec9c8f842cef6692640c7;p=privoxy.git diff --git a/filters.c b/filters.c index 29cee478..48506d57 100644 --- a/filters.c +++ b/filters.c @@ -1,15 +1,15 @@ -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 1.13 2001/05/31 21:21:30 jongfoster 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', + * `block_url', `url_actions', `domaincmp', `dsplit', + * `filter_popups', `forward_url', 'redirect_url', * `ij_untrusted_url', `intercept_url', `re_process_buffer', - * `show_proxy_args', and `trust_url' + * `show_proxy_args', 'ijb_send_banner', and `trust_url' * * Copyright : Written by and Copyright (C) 2001 the SourceForge * IJBSWA team. http://ijbswa.sourceforge.net @@ -38,6 +38,136 @@ const char filters_rcs[] = "$Id: filters.c,v 1.1 2001/05/13 21:57:06 administrat * * Revisions : * $Log: filters.c,v $ + * 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 + * * *********************************************************************/ @@ -68,6 +198,8 @@ const char filters_rcs[] = "$Id: filters.c,v 1.1 2001/05/13 21:57:06 administrat #include "jbsockets.h" #include "errlog.h" #include "jbsockets.h" +#include "miscutil.h" +#include "actions.h" #ifdef _WIN32 #include "win32.h" @@ -103,13 +235,13 @@ static const char CBLOCK[] = "

" BANNER "

\n" - "

Your request for %s%s
\n" - "was blocked because it matches the following pattern " - "in the blockfile: %s\n

" + "

Your request for %s%s\n" + "was blocked.
See why" #ifdef FORCE_LOAD - "

Go there anyway.

" + " or " + "go there anyway." #endif /* def FORCE_LOAD */ + "

\n" "\n" "\n"; @@ -130,7 +262,7 @@ static const char CTRUST[] = "\n" WHITEBG "
" - "" + "" BANNER "" "
" @@ -148,21 +280,23 @@ static const char CTRUST[] = * 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]; /* if not using an access control list, then permit the connection */ - if (((fl = csp->alist) == NULL) || ((acl = fl->f) == NULL)) + if (((fl = csp->alist) == NULL) || + ((acl = (struct access_control_list *) fl->f) == NULL)) { return(0); } @@ -170,28 +304,27 @@ int block_acl(struct access_control_addr *src, struct access_control_addr *dst, /* search the list */ for (a = acl->next ; a ; a = a->next) { - *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 & a->src->mask) == a->src->addr) { - if (a->action == ACL_PERMIT) + if (dst == NULL) { - return(0); + /* Just want to check if they have any access */ + if (a->action == ACL_PERMIT) + { + return(0); + } } - else + else if ( ((dst->addr & a->dst->mask) == a->dst->addr) + && ((dst->port == a->dst->port) || (a->dst->port == 0))) { - return(1); + if (a->action == ACL_PERMIT) + { + return(0); + } + else + { + return(1); + } } } } @@ -205,11 +338,11 @@ int block_acl(struct access_control_addr *src, struct access_control_addr *dst, * * 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. * @@ -292,71 +425,39 @@ int acl_addr(char *aspec, struct access_control_addr *aca) *********************************************************************/ char *block_url(struct http_request *http, struct client_state *csp) { - struct file_list *fl; - struct block_spec *b; - struct url_spec url[1]; char *p; int n; + int factor = 2; - if (((fl = csp->blist) == NULL) || ((b = fl->f) == NULL)) + 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 { - 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); - - if (b->reject == 0) return(NULL); - - 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); + factor++; #endif /* def FORCE_LOAD */ - p = (char *)malloc(n); + n = strlen(CBLOCK); + n += factor * strlen(http->hostport); + n += factor * strlen(http->path); + + p = (char *)malloc(n); #ifdef FORCE_LOAD - sprintf(p, CBLOCK, http->hostport, http->path, b->url->spec, http->hostport, http->path); + sprintf(p, CBLOCK, http->hostport, http->path, http->hostport, http->path, + http->hostport, http->path); #else - sprintf(p, CBLOCK, http->hostport, http->path, b->url->spec); + sprintf(p, CBLOCK, http->hostport, http->path, http->hostport, http->path); #endif /* def FORCE_LOAD */ - return(p); - } - } - } + return(p); } - freez(url->dbuf); - freez(url->dvec); - return(NULL); - } -#if defined(DETECT_MSIE_IMAGES) || defined(USE_IMAGE_LIST) +#ifdef IMAGE_BLOCKING /********************************************************************* * * Function : block_imageurl @@ -389,81 +490,9 @@ int block_imageurl(struct http_request *http, struct client_state *csp) } #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) */ - - -#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]; - - if (((fl = csp->ilist) == NULL) || ((b = fl->f) == NULL)) - { - return(0); - } - - *url = dsplit(http->host); - - /* if splitting the domain fails, punt */ - if (url->dbuf == NULL) return(0); - - for (b = b->next; b ; b = b->next) - { - - if ((b->url->port == 0) || (b->url->port == http->port)) - { - /* 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); - } - } - } - } - freez(url->dbuf); - freez(url->dvec); - return(0); - + return ((csp->action->flags & ACTION_IMAGE) != 0); } -#endif /* def USE_IMAGE_LIST */ +#endif /* def IMAGE_BLOCKING */ #ifdef PCRS @@ -472,18 +501,17 @@ int block_imageurl_using_imagelist(struct http_request *http, struct client_stat * Function : re_process_buffer * * 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). + * the text buffer that's been accumulated in csp->iob->buf + * and set csp->content_length to the modified size. * * Parameters : * 1 : csp = Current client state (buffers, headers, etc...) * - * Returns : N/A + * Returns : a pointer to the (newly allocated) modified buffer. + * * *********************************************************************/ -void re_process_buffer(struct client_state *csp) +char *re_process_buffer(struct client_state *csp) { int hits=0; int size = csp->iob->eod - csp->iob->cur; @@ -494,18 +522,21 @@ void re_process_buffer(struct client_state *csp) struct re_filterfile_spec *b; /* Sanity first ;-) */ - if (size <= 0) return; + if (size <= 0) + { + return(strdup("")); + } if ( ( NULL == (fl = csp->rlist) ) || ( NULL == (b = fl->f) ) ) { log_error(LOG_LEVEL_ERROR, "Unable to get current state of regexp filtering."); - return; + return(strdup("")); } joblist = b->joblist; - log_error(LOG_LEVEL_REF, "re_filtering %s%s (size %d) ...", + 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 */ @@ -516,17 +547,13 @@ void re_process_buffer(struct client_state *csp) old=new; } - log_error(LOG_LEVEL_REF, " produced %d hits (new size %d).", hits, size); + log_error(LOG_LEVEL_RE_FILTER, " produced %d hits (new size %d).", hits, size); - if (write_socket(csp->cfd, old, size) != size) - { - log_error(LOG_LEVEL_ERROR, "write to client failed."); - } + csp->content_length = size; /* fwiw, reset the iob */ IOB_RESET(csp); - freez(new); - return; + return(new); } #endif /* def PCRS */ @@ -651,7 +678,7 @@ char *trust_url(struct http_request *http, struct client_state *csp) /* if splitting the domain fails, punt */ if (url->dbuf == NULL) goto trust_url_not_trusted; - for (tl = trust_list; (t = *tl) ; tl++) + for (tl = csp->config->trust_list; (t = *tl) ; tl++) { if ((t->port == 0) || (t->port == rhttp->port)) { @@ -675,7 +702,7 @@ char *trust_url(struct http_request *http, struct client_state *csp) freez(url->dbuf); freez(url->dvec); - if ((fp = fopen(trustfile, "a"))) + if ((fp = fopen(csp->config->trustfile, "a"))) { h = NULL; @@ -742,6 +769,26 @@ trust_url_not_trusted: #endif /* def TRUST_FILES */ +static const char C_HOME_PAGE[] = + "HTTP/1.0 200 OK\n" + "Pragma: no-cache\n" + "Expires: Thu Jul 31, 1997 07:42:22 pm GMT\n" + "Content-Type: text/html\n\n" + "\n" + "\n" + "Internet Junkbuster: Information\n" + "\n" + BODY + "

" + BANNER + "

\n" + "

JunkBuster web site

\n" + "

Proxy configuration

\n" + "

Look up a URL

\n" + "\n" + "\n"; + + /********************************************************************* * * Function : intercept_url @@ -757,64 +804,181 @@ trust_url_not_trusted: * 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. + * Returns : 1 if it intercepts & handles the request. * *********************************************************************/ -char *intercept_url(struct http_request *http, struct client_state *csp) +int intercept_url(struct http_request *http, struct client_state *csp) { - char *basename; + char *basename = NULL; const struct interceptors *v; - basename = strrchr(http->path, '/'); + if (0 == strcmpic(http->host,"i.j.b")) + { + /* + * Catch http://i.j.b/... + */ + basename = http->path; + } + else if ( ( (0 == strcmpic(http->host,"ijbswa.sourceforge.net")) + || (0 == strcmpic(http->host,"ijbswa.sf.net")) ) + && (0 == strncmpic(http->path,"/config", 7)) + && ((http->path[7] == '/') || (http->path[7] == '\0'))) + { + /* + * Catch http://ijbswa.sourceforge.net/config/... + * and http://ijbswa.sf.net/config/... + */ + basename = http->path + 7; + } - if (basename == NULL) return(NULL); + if (!basename) + { + /* Don't want to intercept */ + return(0); + } - basename ++; /* first char past the last slash */ + /* We have intercepted it. */ - if (*basename) + /* remove any leading slash */ + if (*basename == '/') { - for (v = intercept_patterns; v->str; v++) + basename++; + } + + log_error(LOG_LEVEL_GPC, "%s%s intercepted!", http->hostport, http->path); + log_error(LOG_LEVEL_CLF, "%s - - [%T] \"%s\" 200 3", + csp->ip_addr_str, http->cmd); + + for (v = intercept_patterns; v->str; v++) + { + if (strncmp(basename, v->str, v->len) == 0) { - if (strncmp(basename, v->str, v->len) == 0) + char * p = ((v->interceptor)(http, csp)); + + if (p != NULL) { - return((v->interceptor)(http, csp)); + /* Send HTML redirection result */ + write_socket(csp->cfd, p, strlen(p)); + + freez(p); } + return(1); } } - return(NULL); + write_socket(csp->cfd, C_HOME_PAGE, strlen(C_HOME_PAGE)); + return(1); } +#ifdef FAST_REDIRECTS +/********************************************************************* + * + * Function : redirect_url + * + * Description : Checks for redirection URLs and returns a HTTP redirect + * to the destination URL. + * + * Parameters : + * 1 : http = http_request request, check `basename's of blocklist + * 2 : csp = Current client state (buffers, headers, etc...) + * + * Returns : NULL if URL was clean, HTTP redirect otherwise. + * + *********************************************************************/ +char *redirect_url(struct http_request *http, struct client_state *csp) +{ + char *p, *q; + + p = q = csp->http->path; + log_error(LOG_LEVEL_REDIRECTS, "checking path: %s", p); + + /* find the last URL encoded in the request */ + while (p = strstr(p, "http://")) + { + q = p++; + } + + /* if there was any, generate and return a HTTP redirect */ + if (q != csp->http->path) + { + log_error(LOG_LEVEL_REDIRECTS, "redirecting to: %s", q); + + p = (char *)malloc(strlen(HTTP_REDIRECT_TEMPLATE) + strlen(q)); + sprintf(p, HTTP_REDIRECT_TEMPLATE, q); + return(p); + } + else + { + return(NULL); + } + +} +#endif /* def FAST_REDIRECTS */ /********************************************************************* * - * 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) { @@ -830,9 +994,7 @@ struct cookie_spec *cookie_url(struct http_request *http, struct client_state *c #endif ) { - freez(url->dbuf); - freez(url->dvec); - return(b); + merge_current_action(action, b->action); } } } @@ -840,8 +1002,6 @@ struct cookie_spec *cookie_url(struct http_request *http, struct client_state *c freez(url->dbuf); freez(url->dvec); - return(NULL); - } @@ -927,13 +1087,14 @@ struct url_spec dsplit(char *domain) 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); @@ -957,6 +1118,7 @@ struct url_spec dsplit(char *domain) memcpy(ret->dvec, v, size); } + return(*ret); } @@ -966,11 +1128,11 @@ struct url_spec dsplit(char *domain) * * Function : 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. Governed by the bimap in + * pattern->unachored, the comparison is un-, left-, + * right-anchored, or both. + * The individual domain names are compared with + * trivialmatch(). * * Parameters : * 1 : pattern = a domain that may contain a '*' as a wildcard. @@ -986,27 +1148,29 @@ int domaincmp(struct url_spec *pattern, struct url_spec *fqdn) char *p, *f; /* chars */ pv = pattern->dvec; - pn = pattern->dcnt; - fv = fqdn->dvec; - fn = fqdn->dcnt; + fn = pn = 0; - while ((pn > 0) && (fn > 0)) + while (fn < fqdn->dcnt && pn < pattern->dcnt) { - p = pv[--pn]; - f = fv[--fn]; + p = pv[pn]; + f = fv[fn]; - while (*p && *f && (*p == tolower(*f))) + if (simplematch(p, f)) { - p++, f++; + if(pn || !(pattern->unanchored & ANCHOR_LEFT)) + { + return 1; + } } - - if ((*p != tolower(*f)) && (*p != '*')) return(1); + else + { + pn++; + } + fn++; } - if (pn > 0) return(1); - - return(0); + return ((pn < pattern->dcnt) || ((fn < fqdn->dcnt) && !(pattern->unanchored & ANCHOR_RIGHT))); } @@ -1048,18 +1212,11 @@ char *show_proxy_args(struct http_request *http, struct client_state *csp) } switch (which_file) { - case 'b': - if (csp->blist) - { - filename = csp->blist->filename; - file_description = "Block List"; - } - break; - case 'c': - if (csp->clist) + case 'p': + if (csp->actions_list) { - filename = csp->clist->filename; - file_description = "Cookie List"; + filename = csp->actions_list->filename; + file_description = "Actions List"; } break; case 'f': @@ -1080,26 +1237,6 @@ char *show_proxy_args(struct http_request *http, struct client_state *csp) 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) @@ -1186,28 +1323,20 @@ char *show_proxy_args(struct http_request *http, struct client_state *csp) "

Back to proxy status

\n" "
\n" "

\n" - "Code and documentation of the " BANNER " Proxy" - "TM\n" - "\n" "Copyright© 1997 Junkbusters Corporation\n" - "TM
\n" - "Copying and distribution permitted under the" - "\n" - "GNU " - "General Public License.\n" - "" - "

webmaster@junkbusters.com
" - "" + "The " BANNER " Proxy - \n" + "" HOME_PAGE_URL "\n" + "" "\n"); return(s); } #endif /* def SPLIT_PROXY_ARGS */ - s = strsav(s, proxy_args->header); - s = strsav(s, proxy_args->invocation); + s = strsav(s, csp->config->proxy_args_header); + s = strsav(s, csp->config->proxy_args_invocation); #ifdef STATISTICS s = add_stats(s); #endif /* def STATISTICS */ - s = strsav(s, proxy_args->gateways); + s = strsav(s, csp->config->proxy_args_gateways); #ifdef SPLIT_PROXY_ARGS s = strsav(s, @@ -1215,17 +1344,10 @@ char *show_proxy_args(struct http_request *http, struct client_state *csp) "

(Click a filename to view it)

\n" ""); #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); @@ -1306,20 +1405,6 @@ char *show_proxy_args(struct http_request *http, struct client_state *csp) } #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) { @@ -1336,13 +1421,212 @@ char *show_proxy_args(struct http_request *http, struct client_state *csp) #endif /* ndef SPLIT_PROXY_ARGS */ - s = strsav(s, proxy_args->trailer); + s = strsav(s, csp->config->proxy_args_trailer); return(s); } +static const char C_URL_INFO_HEADER[] = + "HTTP/1.0 200 OK\n" + "Pragma: no-cache\n" + "Expires: Thu Jul 31, 1997 07:42:22 pm GMT\n" + "Content-Type: text/html\n\n" + "\n" + "\n" + "Internet Junkbuster: URL Info\n" + "\n" + BODY + "

" + BANNER + "

\n" + "

Information for: http://%s

\n"; +static const char C_URL_INFO_FOOTER[] = + "\n

\n" + "\n" + "\n"; + +static const char C_URL_INFO_FORM[] = + "HTTP/1.0 200 OK\n" + "Pragma: no-cache\n" + "Expires: Thu Jul 31, 1997 07:42:22 pm GMT\n" + "Content-Type: text/html\n\n" + "\n" + "\n" + "Internet Junkbuster: URL Info\n" + "\n" + BODY + "

" + BANNER + "

\n" + "
\n" + "

Please enter a URL, without the leading "http://":

" + "

" + "

\n" + "
\n" + "\n" + "\n"; + + + /********************************************************************* + * + * Function : ijb_show_url_info + * + * Description : (please fill me in) + * + * Parameters : + * 1 : http = http_request request for crunched URL + * 2 : csp = Current client state (buffers, headers, etc...) + * + * Returns : ???FIXME + * + *********************************************************************/ +char *ijb_show_url_info(struct http_request *http, struct client_state *csp) +{ + char * query_string = strchr(http->path, '?'); + char * host = NULL; + + if (query_string != NULL) + { + query_string = url_decode(query_string + 1); + if (strncmpic(query_string, "url=", 4) == 0) + { + host = strdup(query_string + 4); + } + freez(query_string); + } + if (host != NULL) + { + char * result; + char * path; + char * s; + int port = 80; + struct file_list *fl; + struct url_actions *b; + struct url_spec url[1]; + struct current_action_spec action[1]; + + init_current_action(action); + + result = (char *)malloc(sizeof(C_URL_INFO_HEADER) + 2 * strlen(host)); + sprintf(result, C_URL_INFO_HEADER, host, host); + + s = current_action_to_text(action); + result = strsav(result, "

Defaults:

\n

{"); + result = strsav(result, s); + result = strsav(result, " }

\n

Patterns affecting the URL:

\n

\n"); + freez(s); + + s = strchr(host, '/'); + if (s != NULL) + { + path = strdup(s); + *s = '\0'; + } + else + { + path = strdup(""); + } + s = strchr(host, ':'); + if (s != NULL) + { + *s++ = '\0'; + port = atoi(s); + } + + if (((fl = csp->actions_list) == NULL) || ((b = fl->f) == NULL)) + { + freez(host); + freez(path); + result = strsav(result, C_URL_INFO_FOOTER); + return result; + } + + *url = dsplit(host); + + /* if splitting the domain fails, punt */ + if (url->dbuf == NULL) + { + freez(host); + freez(path); + result = strsav(result, C_URL_INFO_FOOTER); + return result; + } + + for (b = b->next; NULL != b; b = b->next) + { + if ((b->url->port == 0) || (b->url->port == port)) + { + if ((b->url->domain[0] == '\0') || (domaincmp(b->url, url) == 0)) + { + if ((b->url->path == NULL) || +#ifdef REGEX + (regexec(b->url->preg, path, 0, NULL, 0) == 0) +#else + (strncmp(b->url->path, path, b->url->pathlen) == 0) +#endif + ) + { + s = actions_to_text(b->action); + result = strsav(result, "{"); + result = strsav(result, s); + result = strsav(result, " }
\n"); + result = strsav(result, b->url->spec); + result = strsav(result, "
\n
\n"); + freez(s); + + merge_current_action(action, b->action); + } + } + } + } + + freez(url->dbuf); + freez(url->dvec); + + freez(host); + freez(path); + + s = current_action_to_text(action); + result = strsav(result, "

\n

Final Results:

\n

{"); + result = strsav(result, s); + result = strsav(result, " }
\n
\n"); + freez(s); + + free_current_action(action); + + result = strsav(result, C_URL_INFO_FOOTER); + return result; + } + else + { + return strdup(C_URL_INFO_FORM); + } +} + + +/********************************************************************* + * + * Function : ijb_send_banner + * + * Description : This "crunch"es "http://i.j.b/ijb-send-banner and + * sends the image. + * + * Parameters : + * 1 : http = http_request request for crunched URL + * 2 : csp = Current client state (buffers, headers, etc...) + * + * Returns : NULL, indicating that it has already sent the data. + * + *********************************************************************/ +char *ijb_send_banner(struct http_request *http, struct client_state *csp) +{ + write_socket(csp->cfd, JBGIF, sizeof(JBGIF)-1); + + return(NULL); +} + #ifdef TRUST_FILES /********************************************************************* * @@ -1419,13 +1703,13 @@ char *ij_untrusted_url(struct http_request *http, struct client_state *csp) p = strsav(p, "

The following referrers are trusted

\n"); - for (tl = trust_list; (t = *tl) ; tl++) + for (tl = csp->config->trust_list; (t = *tl) ; tl++) { sprintf(buf, "%s
\n", t->spec); p = strsav(p, buf); } - if (trust_info->next) + if (csp->config->trust_info->next) { struct list *l; @@ -1439,7 +1723,7 @@ char *ij_untrusted_url(struct http_request *http, struct client_state *csp) p = strsav(p, buf); - for (l = trust_info->next; l ; l = l->next) + for (l = csp->config->trust_info->next; l ; l = l->next) { sprintf(buf, "
  • %s
    \n", @@ -1488,11 +1772,11 @@ char *add_stats(char *s) * Need to alter the stats not to include the fetch of this * page. * - * Can't do following thread safely! doh! - * + * Can't do following thread safely! doh! + * * urls_read--; * urls_rejected--; * This will be incremented subsequently * - */ + */ s = strsav(s,"

    Statistics for this " BANNER ":

    \n");