X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=urlmatch.c;h=84eb90a8e7760c0f4509251cd6013c975b0d9322;hp=28dd245efbd53b48539ee677f565b612736e78d9;hb=7537bf8433682b12ccf1099e1e30c978f4bd52a2;hpb=1251e702bce39f773f2213aa419d0254cb0a4a2e diff --git a/urlmatch.c b/urlmatch.c index 28dd245e..84eb90a8 100644 --- a/urlmatch.c +++ b/urlmatch.c @@ -1,13 +1,13 @@ -const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.3 2002/03/03 14:51:11 oes Exp $"; +const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.10.2.7 2003/05/17 15:57:24 oes Exp $"; /********************************************************************* * - * File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $ + * File : $Source: /cvsroot/ijbswa/current/Attic/urlmatch.c,v $ * * Purpose : Declares functions to match URLs against URL * patterns. * * Copyright : Written by and Copyright (C) 2001 the SourceForge - * IJBSWA team. http://ijbswa.sourceforge.net + * Privoxy team. http://www.privoxy.org/ * * Based on the Internet Junkbuster originally written * by and Copyright (C) 1997 Anonymous Coders and @@ -33,6 +33,57 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.3 2002/03/03 14:51:11 oes Exp $ * * Revisions : * $Log: urlmatch.c,v $ + * 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 * @@ -85,19 +136,6 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.3 2002/03/03 14:51:11 oes Exp $ const char urlmatch_h_rcs[] = URLMATCH_H_VERSION; -/* Fix a problem with Solaris. There should be no effect on other - * platforms. - * Solaris's isspace() is a macro which uses it's argument directly - * as an array index. Therefore we need to make sure that high-bit - * characters generate +ve values, and ideally we also want to make - * the argument match the declared parameter type of "int". - * - * Why did they write a character function that can't take a simple - * "char" argument? Doh! - */ -#define ijb_isupper(__X) isupper((int)(unsigned char)(__X)) -#define ijb_tolower(__X) tolower((int)(unsigned char)(__X)) - /********************************************************************* * @@ -147,8 +185,8 @@ void free_http_request(struct http_request *http) * * Returns : JB_ERR_OK on success * JB_ERR_MEMORY on out of memory - * JB_ERR_CGI_PARAMS on malformed command/URL - * or >100 domains deep. + * JB_ERR_PARSE on malformed command/URL + * or >100 domains deep. * *********************************************************************/ jb_err parse_http_url(const char * url, @@ -171,6 +209,24 @@ jb_err parse_http_url(const char * url, } + /* + * Check for * URI. If found, we're done. + */ + if (*http->url == '*') + { + if ( NULL == (http->path = strdup("*")) + || NULL == (http->hostport = strdup("")) ) + { + return JB_ERR_MEMORY; + } + if (http->url[1] != '\0') + { + return JB_ERR_PARSE; + } + return JB_ERR_OK; + } + + /* * Split URL into protocol,hostport,path. */ @@ -227,13 +283,11 @@ jb_err parse_http_url(const char * url, http->hostport = strdup(url_noproto); } - free(buf); + freez(buf); if ( (http->path == NULL) || (http->hostport == NULL)) { - free(buf); - free_http_request(http); return JB_ERR_MEMORY; } } @@ -250,7 +304,6 @@ jb_err parse_http_url(const char * url, buf = strdup(http->hostport); if (buf == NULL) { - free_http_request(http); return JB_ERR_MEMORY; } @@ -279,7 +332,7 @@ jb_err parse_http_url(const char * url, else { /* No port specified. */ - http->port = (http->ssl ? 143 : 80); + http->port = (http->ssl ? 443 : 80); } http->host = strdup(host); @@ -288,15 +341,14 @@ jb_err parse_http_url(const char * url, if (http->host == NULL) { - free_http_request(http); return JB_ERR_MEMORY; } } - /* * Split domain name so we can compare it against wildcards */ + { char *vec[BUFFER_SIZE]; size_t size; @@ -305,7 +357,6 @@ jb_err parse_http_url(const char * url, http->dbuffer = strdup(http->host); if (NULL == http->dbuffer) { - free_http_request(http); return JB_ERR_MEMORY; } @@ -324,7 +375,6 @@ jb_err parse_http_url(const char * url, * Error: More than SZ(vec) components in domain * or: no components in domain */ - free_http_request(http); return JB_ERR_PARSE; } @@ -334,15 +384,14 @@ jb_err parse_http_url(const char * url, http->dvec = (char **)malloc(size); if (NULL == http->dvec) { - free_http_request(http); return JB_ERR_MEMORY; } memcpy(http->dvec, vec, size); } - return JB_ERR_OK; + } @@ -401,6 +450,8 @@ jb_err parse_http_request(const char *req, || (0 == strcmpic(v[0], "post")) || (0 == strcmpic(v[0], "put")) || (0 == strcmpic(v[0], "delete")) + || (0 == strcmpic(v[0], "options")) + || (0 == strcmpic(v[0], "trace")) /* or a webDAV extension (RFC2518) */ || (0 == strcmpic(v[0], "propfind")) @@ -410,6 +461,24 @@ jb_err parse_http_request(const char *req, || (0 == strcmpic(v[0], "mkcol")) || (0 == strcmpic(v[0], "lock")) || (0 == strcmpic(v[0], "unlock")) + + /* Or a Microsoft webDAV extension for Exchange 2000. See: */ + /* http://lists.w3.org/Archives/Public/w3c-dist-auth/2002JanMar/0001.html */ + /* http://msdn.microsoft.com/library/en-us/wss/wss/_webdav_methods.asp */ + || (0 == strcmpic(v[0], "bcopy")) + || (0 == strcmpic(v[0], "bmove")) + || (0 == strcmpic(v[0], "bdelete")) + || (0 == strcmpic(v[0], "bpropfind")) + || (0 == strcmpic(v[0], "bproppatch")) + + /* Or another Microsoft webDAV extension for Exchange 2000. See: */ + /* http://systems.cs.colorado.edu/grunwald/MobileComputing/Papers/draft-cohen-gena-p-base-00.txt */ + /* http://lists.w3.org/Archives/Public/w3c-dist-auth/2002JanMar/0001.html */ + /* http://msdn.microsoft.com/library/en-us/wss/wss/_webdav_methods.asp */ + || (0 == strcmpic(v[0], "subscribe")) + || (0 == strcmpic(v[0], "unsubscribe")) + || (0 == strcmpic(v[0], "notify")) + || (0 == strcmpic(v[0], "poll")) ) { /* Normal */ @@ -442,11 +511,12 @@ jb_err parse_http_request(const char *req, || (http->ver == NULL) ) { free(buf); - free_http_request(http); return JB_ERR_MEMORY; } + free(buf); return JB_ERR_OK; + } @@ -574,7 +644,7 @@ static int domain_match(const struct url_spec *pattern, const struct http_reques * Function : create_url_spec * * Description : Creates a "url_spec" structure from a string. - * When finished, free with unload_url(). + * When finished, free with free_url_spec(). * * Parameters : * 1 : url = Target url_spec to be filled in. Will be @@ -599,16 +669,20 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) assert(url); assert(buf); - /* Zero memory */ + /* + * Zero memory + */ memset(url, '\0', sizeof(*url)); - /* save a copy of the orignal specification */ + /* + * Save a copy of the orignal specification + */ if ((url->spec = strdup(buf)) == NULL) { return JB_ERR_MEMORY; } - if ((p = strchr(buf, '/'))) + if ((p = strchr(buf, '/')) != NULL) { if (NULL == (url->path = strdup(p))) { @@ -623,7 +697,6 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) url->path = NULL; url->pathlen = 0; } -#ifdef REGEX if (url->path) { int errcode; @@ -656,12 +729,12 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) freez(url->spec); freez(url->path); + regfree(url->preg); freez(url->preg); return JB_ERR_PARSE; } } -#endif if ((p = strchr(buf, ':')) == NULL) { url->port = 0; @@ -677,7 +750,9 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) char *v[150]; size_t size; - /* Parse domain part */ + /* + * Parse domain part + */ if (buf[strlen(buf) - 1] == '.') { url->unanchored |= ANCHOR_RIGHT; @@ -687,35 +762,38 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) url->unanchored |= ANCHOR_LEFT; } - /* split domain into components */ - + /* + * Split domain into components + */ url->dbuffer = strdup(buf); if (NULL == url->dbuffer) { freez(url->spec); freez(url->path); -#ifdef REGEX + regfree(url->preg); freez(url->preg); -#endif /* def REGEX */ return JB_ERR_MEMORY; } - /* map to lower case */ + /* + * Map to lower case + */ for (p = url->dbuffer; *p ; p++) { *p = tolower((int)(unsigned char)*p); } - /* split the domain name into components */ + /* + * Split the domain name into components + */ url->dcount = ssplit(url->dbuffer, ".", v, SZ(v), 1, 1); if (url->dcount < 0) { freez(url->spec); freez(url->path); -#ifdef REGEX + regfree(url->preg); freez(url->preg); -#endif /* def REGEX */ freez(url->dbuffer); url->dcount = 0; return JB_ERR_MEMORY; @@ -723,7 +801,9 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) else if (url->dcount != 0) { - /* save a copy of the pointers in dvec */ + /* + * Save a copy of the pointers in dvec + */ size = url->dcount * sizeof(*url->dvec); url->dvec = (char **)malloc(size); @@ -731,9 +811,8 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) { freez(url->spec); freez(url->path); -#ifdef REGEX + regfree(url->preg); freez(url->preg); -#endif /* def REGEX */ freez(url->dbuffer); url->dcount = 0; return JB_ERR_MEMORY; @@ -741,6 +820,11 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) memcpy(url->dvec, v, size); } + /* + * else dcount == 0 in which case we needn't do anything, + * since dvec will never be accessed and the pattern will + * match all domains. + */ } return JB_ERR_OK; @@ -769,14 +853,11 @@ void free_url_spec(struct url_spec *url) freez(url->dbuffer); freez(url->dvec); freez(url->path); -#ifdef REGEX if (url->preg) { regfree(url->preg); freez(url->preg); } -#endif - } @@ -799,11 +880,7 @@ int url_match(const struct url_spec *pattern, return ((pattern->port == 0) || (pattern->port == url->port)) && ((pattern->dbuffer == NULL) || (domain_match(pattern, url) == 0)) && ((pattern->path == NULL) || -#ifdef REGEX (regexec(pattern->preg, url->path, 0, NULL, 0) == 0) -#else - (strncmp(pattern->path, url->path, pattern->pathlen) == 0) -#endif ); }