X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=urlmatch.c;h=a8f887b7dfa26d0b7911e766ddc8b8eb2d33d11b;hp=4ba17cf10cbd72c8b737d6a8dfa2b11ae7cb6ea5;hb=a3ee8549f25573ab20c3cde9dd52bbb3205cebfc;hpb=8fe6bb275095d03b4dc1c68edf2dd72babf56428 diff --git a/urlmatch.c b/urlmatch.c index 4ba17cf1..a8f887b7 100644 --- a/urlmatch.c +++ b/urlmatch.c @@ -1,4 +1,4 @@ -const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.42 2008/05/04 13:24:16 fabiankeil Exp $"; +const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.58 2009/06/03 16:44:41 fabiankeil Exp $"; /********************************************************************* * * File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $ @@ -6,8 +6,8 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.42 2008/05/04 13:24:16 fabianke * Purpose : Declares functions to match URLs against URL * patterns. * - * Copyright : Written by and Copyright (C) 2001-2003, 2006-2008 the SourceForge - * Privoxy team. http://www.privoxy.org/ + * Copyright : Written by and Copyright (C) 2001-2009 + * the Privoxy team. http://www.privoxy.org/ * * Based on the Internet Junkbuster originally written * by and Copyright (C) 1997 Anonymous Coders and @@ -31,211 +31,8 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.42 2008/05/04 13:24:16 fabianke * or write to the Free Software Foundation, Inc., 59 * Temple Place - Suite 330, Boston, MA 02111-1307, USA. * - * Revisions : - * $Log: urlmatch.c,v $ - * Revision 1.42 2008/05/04 13:24:16 fabiankeil - * If the method isn't CONNECT, reject URLs without protocol. - * - * Revision 1.41 2008/05/02 09:51:34 fabiankeil - * In parse_http_url(), don't muck around with values - * that are none of its business: require an initialized - * http structure and never unset http->ssl. - * - * Revision 1.40 2008/04/23 16:12:28 fabiankeil - * Free with freez(). - * - * Revision 1.39 2008/04/22 16:27:42 fabiankeil - * In parse_http_request(), remove a pointless - * temporary variable and free the buffer earlier. - * - * Revision 1.38 2008/04/18 05:17:18 fabiankeil - * Mark simplematch()'s parameters as immutable. - * - * Revision 1.37 2008/04/17 14:53:29 fabiankeil - * Move simplematch() into urlmatch.c as it's only - * used to match (old-school) domain patterns. - * - * Revision 1.36 2008/04/14 18:19:48 fabiankeil - * Remove now-pointless cast in create_url_spec(). - * - * Revision 1.35 2008/04/14 18:11:21 fabiankeil - * The compiler might not notice it, but the buffer passed to - * create_url_spec() is modified later on and thus shouldn't - * be declared immutable. - * - * Revision 1.34 2008/04/13 13:32:07 fabiankeil - * Factor URL pattern compilation out of create_url_spec(). - * - * Revision 1.33 2008/04/12 14:03:13 fabiankeil - * Remove an obvious comment and improve another one. - * - * Revision 1.32 2008/04/12 12:38:06 fabiankeil - * Factor out duplicated code to compile host, path and tag patterns. - * - * Revision 1.31 2008/04/10 14:41:04 fabiankeil - * Ditch url_spec's path member now that it's no longer used. - * - * Revision 1.30 2008/04/10 04:24:24 fabiankeil - * Stop duplicating the plain text representation of the path regex - * (and keeping the copy around). Once the regex is compiled it's no - * longer useful. - * - * Revision 1.29 2008/04/10 04:17:56 fabiankeil - * In url_match(), check the right member for NULL when determining - * whether there's a path regex to execute. Looking for a plain-text - * representation works as well, but it looks "interesting" and that - * member will be removed soonish anyway. - * - * Revision 1.28 2008/04/08 16:07:39 fabiankeil - * Make it harder to mistake url_match()'s - * second parameter for an url_spec. - * - * Revision 1.27 2008/04/08 15:44:33 fabiankeil - * Save a bit of memory (and a few cpu cycles) by not bothering to - * compile slash-only path regexes that don't affect the result. - * - * Revision 1.26 2008/04/07 16:57:18 fabiankeil - * - Use free_url_spec() more consistently. - * - Let it reset url->dcount just in case. - * - * Revision 1.25 2008/04/06 15:18:38 fabiankeil - * Oh well, rename the --enable-pcre-host-patterns option to - * --enable-extended-host-patterns as it's not really PCRE syntax. - * - * Revision 1.24 2008/04/06 14:54:26 fabiankeil - * Use PCRE syntax in host patterns when configured - * with --enable-pcre-host-patterns. - * - * Revision 1.23 2008/04/05 12:19:20 fabiankeil - * Factor compile_host_pattern() out of create_url_spec(). - * - * Revision 1.22 2008/03/30 15:02:32 fabiankeil - * SZitify unknown_method(). - * - * Revision 1.21 2007/12/24 16:34:23 fabiankeil - * Band-aid (and micro-optimization) that makes it less likely to run out of - * stack space with overly-complex path patterns. Probably masks the problem - * reported by Lee in #1856679. Hohoho. - * - * Revision 1.20 2007/09/02 15:31:20 fabiankeil - * Move match_portlist() from filter.c to urlmatch.c. - * It's used for url matching, not for filtering. - * - * Revision 1.19 2007/09/02 13:42:11 fabiankeil - * - Allow port lists in url patterns. - * - Ditch unused url_spec member pathlen. - * - * Revision 1.18 2007/07/30 16:42:21 fabiankeil - * Move the method check into unknown_method() - * and loop through the known methods instead - * of using a screen-long OR chain. - * - * Revision 1.17 2007/04/15 16:39:21 fabiankeil - * Introduce tags as alternative way to specify which - * actions apply to a request. At the moment tags can be - * created based on client and server headers. - * - * Revision 1.16 2007/02/13 13:59:24 fabiankeil - * Remove redundant log message. - * - * Revision 1.15 2007/01/28 16:11:23 fabiankeil - * Accept WebDAV methods for subversion - * in parse_http_request(). Closes FR 1581425. - * - * Revision 1.14 2007/01/06 14:23:56 fabiankeil - * Fix gcc43 warnings. Mark *csp as immutable - * for parse_http_url() and url_match(). - * Replace a sprintf call with snprintf. - * - * Revision 1.13 2006/12/06 19:50:54 fabiankeil - * parse_http_url() now handles intercepted - * HTTP request lines as well. Moved parts - * of parse_http_url()'s code into - * init_domain_components() so that it can - * be reused in chat(). - * - * Revision 1.12 2006/07/18 14:48:47 david__schmidt - * Reorganizing the repository: swapping out what was HEAD (the old 3.1 branch) - * with what was really the latest development (the v_3_0_branch branch) - * - * Revision 1.10.2.7 2003/05/17 15:57:24 oes - * - parse_http_url now checks memory allocation failure for - * duplication of "*" URL and rejects "*something" URLs - * Closes bug #736344 - * - Added a comment to what might look like a bug in - * create_url_spec (see !bug #736931) - * - Comment cosmetics - * - * Revision 1.10.2.6 2003/05/07 12:39:48 oes - * Fix typo: Default port for https URLs is 443, not 143. - * Thanks to Scott Tregear for spotting this one. - * - * Revision 1.10.2.5 2003/02/28 13:09:29 oes - * Fixed a rare double free condition as per Bug #694713 - * - * Revision 1.10.2.4 2003/02/28 12:57:44 oes - * Moved freeing of http request structure to its owner - * as per Dan Price's observations in Bug #694713 - * - * Revision 1.10.2.3 2002/11/12 16:50:40 oes - * Fixed memory leak in parse_http_request() reported by Oliver Stoeneberg. Fixes bug #637073 - * - * Revision 1.10.2.2 2002/09/25 14:53:15 oes - * Added basic support for OPTIONS and TRACE HTTP methods: - * parse_http_url now recognizes the "*" URI as well as - * the OPTIONS and TRACE method keywords. - * - * Revision 1.10.2.1 2002/06/06 19:06:44 jongfoster - * Adding support for proprietary Microsoft WebDAV extensions - * - * Revision 1.10 2002/05/12 21:40:37 jongfoster - * - Removing some unused code - * - * Revision 1.9 2002/04/04 00:36:36 gliptak - * always use pcre for matching - * - * Revision 1.8 2002/04/03 23:32:47 jongfoster - * Fixing memory leak on error - * - * Revision 1.7 2002/03/26 22:29:55 swa - * we have a new homepage! - * - * Revision 1.6 2002/03/24 13:25:43 swa - * name change related issues - * - * Revision 1.5 2002/03/13 00:27:05 jongfoster - * Killing warnings - * - * Revision 1.4 2002/03/07 03:46:17 oes - * Fixed compiler warnings - * - * Revision 1.3 2002/03/03 14:51:11 oes - * Fixed CLF logging: Added ocmd member for client's request to struct http_request - * - * Revision 1.2 2002/01/21 00:14:09 jongfoster - * Correcting comment style - * Fixing an uninitialized memory bug in create_url_spec() - * - * Revision 1.1 2002/01/17 20:53:46 jongfoster - * Moving all our URL and URL pattern parsing code to the same file - it - * was scattered around in filters.c, loaders.c and parsers.c. - * - * Providing a single, simple url_match(pattern,url) function - rather than - * the 3-line match routine which was repeated all over the place. - * - * Renaming free_url to free_url_spec, since it frees a struct url_spec. - * - * Providing parse_http_url() so that URLs can be parsed without faking a - * HTTP request line for parse_http_request() or repeating the parsing - * code (both of which were techniques that were actually in use). - * - * Standardizing that struct http_request is used to represent a URL, and - * struct url_spec is used to represent a URL pattern. (Before, URLs were - * represented as seperate variables and a partially-filled-in url_spec). - * - * *********************************************************************/ - + #include "config.h" @@ -261,7 +58,13 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.42 2008/05/04 13:24:16 fabianke const char urlmatch_h_rcs[] = URLMATCH_H_VERSION; -enum regex_anchoring {NO_ANCHORING, LEFT_ANCHORED, RIGHT_ANCHORED}; +enum regex_anchoring +{ + NO_ANCHORING, + LEFT_ANCHORED, + RIGHT_ANCHORED, + RIGHT_ANCHORED_HOST +}; static jb_err compile_host_pattern(struct url_spec *url, const char *host_pattern); /********************************************************************* @@ -289,12 +92,15 @@ void free_http_request(struct http_request *http) freez(http->path); freez(http->ver); freez(http->host_ip_addr_str); +#ifndef FEATURE_EXTENDED_HOST_PATTERNS freez(http->dbuffer); freez(http->dvec); http->dcount = 0; +#endif } +#ifndef FEATURE_EXTENDED_HOST_PATTERNS /********************************************************************* * * Function : init_domain_components @@ -358,6 +164,7 @@ jb_err init_domain_components(struct http_request *http) return JB_ERR_OK; } +#endif /* ndef FEATURE_EXTENDED_HOST_PATTERNS */ /********************************************************************* @@ -371,6 +178,8 @@ jb_err init_domain_components(struct http_request *http) * 1 : url = URL (or is it URI?) to break down * 2 : http = pointer to the http structure to hold elements. * Must be initialized with valid values (like NULLs). + * 3 : require_protocol = Whether or not URLs without + * protocol are acceptable. * * Returns : JB_ERR_OK on success * JB_ERR_MEMORY on out of memory @@ -378,7 +187,7 @@ jb_err init_domain_components(struct http_request *http) * or >100 domains deep. * *********************************************************************/ -jb_err parse_http_url(const char * url, struct http_request *http) +jb_err parse_http_url(const char *url, struct http_request *http, int require_protocol) { int host_available = 1; /* A proxy can dream. */ @@ -448,7 +257,7 @@ jb_err parse_http_url(const char * url, struct http_request *http) http->host = NULL; host_available = 0; } - else if (!http->ssl) + else if (require_protocol) { freez(buf); return JB_ERR_PARSE; @@ -521,8 +330,40 @@ jb_err parse_http_url(const char * url, struct http_request *http) host = buf; } + /* Move after hostname before port number */ + if (*host == '[') + { + /* Numeric IPv6 address delimited by brackets */ + host++; + port = strchr(host, ']'); + + if (port == NULL) + { + /* Missing closing bracket */ + freez(buf); + return JB_ERR_PARSE; + } + + *port++ = '\0'; + + if (*port == '\0') + { + port = NULL; + } + else if (*port != ':') + { + /* Garbage after closing bracket */ + freez(buf); + return JB_ERR_PARSE; + } + } + else + { + /* Plain non-escaped hostname */ + port = strchr(host, ':'); + } + /* check if url contains port */ - port = strchr(host, ':'); if (port != NULL) { /* Contains port */ @@ -546,10 +387,12 @@ jb_err parse_http_url(const char * url, struct http_request *http) } } - /* - * Split domain name so we can compare it against wildcards - */ +#ifdef FEATURE_EXTENDED_HOST_PATTERNS + return JB_ERR_OK; +#else + /* Split domain name so we can compare it against wildcards */ return init_domain_components(http); +#endif /* def FEATURE_EXTENDED_HOST_PATTERNS */ } @@ -618,7 +461,6 @@ static int unknown_method(const char *method) * Parameters : * 1 : req = HTTP request line to break down * 2 : http = pointer to the http structure to hold elements - * 3 : csp = Current client state (buffers, headers, etc...) * * Returns : JB_ERR_OK on success * JB_ERR_MEMORY on out of memory @@ -626,9 +468,7 @@ static int unknown_method(const char *method) * or >100 domains deep. * *********************************************************************/ -jb_err parse_http_request(const char *req, - struct http_request *http, - const struct client_state *csp) +jb_err parse_http_request(const char *req, struct http_request *http) { char *buf; char *v[10]; /* XXX: Why 10? We should only need three. */ @@ -666,9 +506,17 @@ jb_err parse_http_request(const char *req, return JB_ERR_PARSE; } + if (strcmpic(v[2], "HTTP/1.1") && strcmpic(v[2], "HTTP/1.0")) + { + log_error(LOG_LEVEL_ERROR, "The only supported HTTP " + "versions are 1.0 and 1.1. This rules out: %s", v[2]); + freez(buf); + return JB_ERR_PARSE; + } + http->ssl = !strcmpic(v[0], "CONNECT"); - err = parse_http_url(v[1], http); + err = parse_http_url(v[1], http, !http->ssl); if (err) { freez(buf); @@ -704,9 +552,10 @@ jb_err parse_http_request(const char *req, * * Parameters : * 1 : pattern = The pattern to compile. - * 2 : anchoring = How the regex should be anchored. - * Can be either one of NO_ANCHORING, - * LEFT_ANCHORED or RIGHT_ANCHORED. + * 2 : anchoring = How the regex should be modified + * before compilation. Can be either + * one of NO_ANCHORING, LEFT_ANCHORED, + * RIGHT_ANCHORED or RIGHT_ANCHORED_HOST. * 3 : url = In case of failures, the spec member is * logged and the structure freed. * 4 : regex = Where the compiled regex should be stored. @@ -721,7 +570,7 @@ static jb_err compile_pattern(const char *pattern, enum regex_anchoring anchorin { int errcode; char rebuf[BUFFER_SIZE]; - const char *fmt; + const char *fmt = NULL; assert(pattern); assert(strlen(pattern) < sizeof(rebuf) - 2); @@ -740,6 +589,9 @@ static jb_err compile_pattern(const char *pattern, enum regex_anchoring anchorin case RIGHT_ANCHORED: fmt = "%s$"; break; + case RIGHT_ANCHORED_HOST: + fmt = "%s\\.?$"; + break; case LEFT_ANCHORED: fmt = "^%s"; break; @@ -820,7 +672,33 @@ static jb_err compile_url_pattern(struct url_spec *url, char *buf) *p = '\0'; } - p = strchr(buf, ':'); + /* + * IPv6 numeric hostnames can contain colons, thus we need + * to delimit the hostname before the real port separator. + * As brackets are already used in the hostname pattern, + * we use angle brackets ('<', '>') instead. + */ + if ((buf[0] == '<') && (NULL != (p = strchr(buf + 1, '>')))) + { + *p++ = '\0'; + buf++; + + if (*p == '\0') + { + /* IPv6 address without port number */ + p = NULL; + } + else if (*p != ':') + { + /* Garbage after address delimiter */ + return JB_ERR_PARSE; + } + } + else + { + p = strchr(buf, ':'); + } + if (NULL != p) { *p++ = '\0'; @@ -863,7 +741,7 @@ static jb_err compile_url_pattern(struct url_spec *url, char *buf) *********************************************************************/ static jb_err compile_host_pattern(struct url_spec *url, const char *host_pattern) { - return compile_pattern(host_pattern, RIGHT_ANCHORED, url, &url->host_regex); + return compile_pattern(host_pattern, RIGHT_ANCHORED_HOST, url, &url->host_regex); } #else @@ -1249,7 +1127,7 @@ jb_err create_url_spec(struct url_spec *url, char *buf) return JB_ERR_MEMORY; } - /* Is it tag pattern? */ + /* Is it a tag pattern? */ if (0 == strncmpic("TAG:", url->spec, 4)) { /* The pattern starts with the first character after "TAG:" */ @@ -1257,7 +1135,7 @@ jb_err create_url_spec(struct url_spec *url, char *buf) return compile_pattern(tag_pattern, NO_ANCHORING, url, &url->tag_regex); } - /* If it isn't a tag pattern it must be a URL pattern. */ + /* If it isn't a tag pattern it must be an URL pattern. */ return compile_url_pattern(url, buf); } @@ -1305,6 +1183,70 @@ void free_url_spec(struct url_spec *url) } +/********************************************************************* + * + * Function : port_matches + * + * Description : Compares a port against a port list. + * + * Parameters : + * 1 : port = The port to check. + * 2 : port_list = The list of port to compare with. + * + * Returns : TRUE for yes, FALSE otherwise. + * + *********************************************************************/ +static int port_matches(const int port, const char *port_list) +{ + return ((NULL == port_list) || match_portlist(port_list, port)); +} + + +/********************************************************************* + * + * Function : host_matches + * + * Description : Compares a host against a host pattern. + * + * Parameters : + * 1 : url = The URL to match + * 2 : pattern = The URL pattern + * + * Returns : TRUE for yes, FALSE otherwise. + * + *********************************************************************/ +static int host_matches(const struct http_request *http, + const struct url_spec *pattern) +{ +#ifdef FEATURE_EXTENDED_HOST_PATTERNS + return ((NULL == pattern->host_regex) + || (0 == regexec(pattern->host_regex, http->host, 0, NULL, 0))); +#else + return ((NULL == pattern->dbuffer) || (0 == domain_match(pattern, http))); +#endif +} + + +/********************************************************************* + * + * Function : path_matches + * + * Description : Compares a path against a path pattern. + * + * Parameters : + * 1 : path = The path to match + * 2 : pattern = The URL pattern + * + * Returns : TRUE for yes, FALSE otherwise. + * + *********************************************************************/ +static int path_matches(const char *path, const struct url_spec *pattern) +{ + return ((NULL == pattern->preg) + || (0 == regexec(pattern->preg, path, 0, NULL, 0))); +} + + /********************************************************************* * * Function : url_match @@ -1321,22 +1263,14 @@ void free_url_spec(struct url_spec *url) int url_match(const struct url_spec *pattern, const struct http_request *http) { - /* XXX: these should probably be functions. */ -#define PORT_MATCHES ((NULL == pattern->port_list) || match_portlist(pattern->port_list, http->port)) -#ifdef FEATURE_EXTENDED_HOST_PATTERNS -#define DOMAIN_MATCHES ((NULL == pattern->host_regex) || (0 == regexec(pattern->host_regex, http->host, 0, NULL, 0))) -#else -#define DOMAIN_MATCHES ((NULL == pattern->dbuffer) || (0 == domain_match(pattern, http))) -#endif -#define PATH_MATCHES ((NULL == pattern->preg) || (0 == regexec(pattern->preg, http->path, 0, NULL, 0))) - if (pattern->tag_regex != NULL) { /* It's a tag pattern and shouldn't be matched against URLs */ return 0; } - return (PORT_MATCHES && DOMAIN_MATCHES && PATH_MATCHES); + return (port_matches(http->port, pattern->port_list) + && host_matches(http, pattern) && path_matches(http->path, pattern)); } @@ -1360,7 +1294,7 @@ int match_portlist(const char *portlist, int port) { char *min, *max, *next, *portlist_copy; - min = next = portlist_copy = strdup(portlist); + min = portlist_copy = strdup(portlist); /* * Zero-terminate first item and remember offset for next @@ -1373,7 +1307,7 @@ int match_portlist(const char *portlist, int port) /* * Loop through all items, checking for match */ - while(min) + while (NULL != min) { if (NULL == (max = strchr(min, (int) '-'))) { @@ -1421,6 +1355,59 @@ int match_portlist(const char *portlist, int port) } +/********************************************************************* + * + * Function : parse_forwarder_address + * + * Description : Parse out the host and port from a forwarder address. + * + * Parameters : + * 1 : address = The forwarder address to parse. + * 2 : hostname = Used to return the hostname. NULL on error. + * 3 : port = Used to return the port. Untouched if no port + * is specified. + * + * Returns : JB_ERR_OK on success + * JB_ERR_MEMORY on out of memory + * JB_ERR_PARSE on malformed address. + * + *********************************************************************/ +jb_err parse_forwarder_address(char *address, char **hostname, int *port) +{ + char *p = address; + + if ((*address == '[') && (NULL == strchr(address, ']'))) + { + /* XXX: Should do some more validity checks here. */ + return JB_ERR_PARSE; + } + + *hostname = strdup(address); + if (NULL == *hostname) + { + return JB_ERR_MEMORY; + } + + if ((**hostname == '[') && (NULL != (p = strchr(*hostname, ']')))) + { + *p++ = '\0'; + memmove(*hostname, (*hostname + 1), (size_t)(p - *hostname)); + if (*p == ':') + { + *port = (int)strtol(++p, NULL, 0); + } + } + else if (NULL != (p = strchr(*hostname, ':'))) + { + *p++ = '\0'; + *port = (int)strtol(p, NULL, 0); + } + + return JB_ERR_OK; + +} + + /* Local Variables: tab-width: 3