X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=urlmatch.c;h=86d211be5081b55068717f99cd3afcdb255bf4de;hp=6e84bc3c1b79ec85c736ed3e727ea7dfe4ace883;hb=03a212cd9ff953a50904e7a970748b5661840426;hpb=1d2a21ed0350fd3cad3b8e08f9c72fd3404d5c3b diff --git a/urlmatch.c b/urlmatch.c index 6e84bc3c..86d211be 100644 --- a/urlmatch.c +++ b/urlmatch.c @@ -1,4 +1,4 @@ -const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.34 2008/04/13 13:32:07 fabiankeil Exp $"; +const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.44 2008/05/04 16:18:32 fabiankeil Exp $"; /********************************************************************* * * File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $ @@ -33,6 +33,43 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.34 2008/04/13 13:32:07 fabianke * * Revisions : * $Log: urlmatch.c,v $ + * Revision 1.44 2008/05/04 16:18:32 fabiankeil + * Provide parse_http_url() with a third parameter to specify + * whether or not URLs without protocol are acceptable. + * + * Revision 1.43 2008/05/04 13:30:55 fabiankeil + * Streamline parse_http_url()'s prototype. + * + * 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(). * @@ -340,10 +377,9 @@ jb_err init_domain_components(struct http_request *http) * Parameters : * 1 : url = URL (or is it URI?) to break down * 2 : http = pointer to the http structure to hold elements. - * Will be zeroed before use. Note that this - * function sets the http->gpc and http->ver - * members to NULL. - * 3 : csp = Current client state (buffers, headers, etc...) + * 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 @@ -351,18 +387,10 @@ 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, - const struct client_state *csp) +jb_err parse_http_url(const char *url, struct http_request *http, int require_protocol) { int host_available = 1; /* A proxy can dream. */ - /* - * Zero out the results structure - */ - memset(http, '\0', sizeof(*http)); - - /* * Save our initial URL */ @@ -410,10 +438,12 @@ jb_err parse_http_url(const char * url, if (strncmpic(url_noproto, "http://", 7) == 0) { url_noproto += 7; - http->ssl = 0; } else if (strncmpic(url_noproto, "https://", 8) == 0) { + /* + * Should only happen when called from cgi_show_url_info(). + */ url_noproto += 8; http->ssl = 1; } @@ -424,13 +454,13 @@ jb_err parse_http_url(const char * url, * Most likely because the client's request * was intercepted and redirected into Privoxy. */ - http->ssl = 0; http->host = NULL; host_available = 0; } - else + else if (require_protocol) { - http->ssl = 0; + freez(buf); + return JB_ERR_PARSE; } url_path = strchr(url_noproto, '/'); @@ -517,7 +547,7 @@ jb_err parse_http_url(const char * url, http->host = strdup(host); - free(buf); + freez(buf); if (http->host == NULL) { @@ -613,7 +643,6 @@ jb_err parse_http_request(const char *req, char *v[10]; /* XXX: Why 10? We should only need three. */ int n; jb_err err; - int is_connect = 0; memset(http, '\0', sizeof(*http)); @@ -626,7 +655,7 @@ jb_err parse_http_request(const char *req, n = ssplit(buf, " \r\n", v, SZ(v), 1, 1); if (n != 3) { - free(buf); + freez(buf); return JB_ERR_PARSE; } @@ -642,39 +671,35 @@ jb_err parse_http_request(const char *req, if (unknown_method(v[0])) { log_error(LOG_LEVEL_ERROR, "Unknown HTTP method detected: %s", v[0]); - free(buf); + freez(buf); return JB_ERR_PARSE; } - if (strcmpic(v[0], "CONNECT") == 0) - { - is_connect = 1; - } + http->ssl = !strcmpic(v[0], "CONNECT"); - err = parse_http_url(v[1], http, csp); + err = parse_http_url(v[1], http, !http->ssl); if (err) { - free(buf); + freez(buf); return err; } /* * Copy the details into the structure */ - http->ssl = is_connect; http->cmd = strdup(req); http->gpc = strdup(v[0]); http->ver = strdup(v[2]); + freez(buf); + if ( (http->cmd == NULL) || (http->gpc == NULL) || (http->ver == NULL) ) { - free(buf); return JB_ERR_MEMORY; } - free(buf); return JB_ERR_OK; } @@ -705,7 +730,7 @@ 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); @@ -938,6 +963,144 @@ static jb_err compile_host_pattern(struct url_spec *url, const char *host_patter } +/********************************************************************* + * + * Function : simplematch + * + * Description : String matching, with a (greedy) '*' wildcard that + * stands for zero or more arbitrary characters and + * character classes in [], which take both enumerations + * and ranges. + * + * Parameters : + * 1 : pattern = pattern for matching + * 2 : text = text to be matched + * + * Returns : 0 if match, else nonzero + * + *********************************************************************/ +static int simplematch(const char *pattern, const char *text) +{ + const unsigned char *pat = (const unsigned char *)pattern; + const unsigned char *txt = (const unsigned char *)text; + const unsigned char *fallback = pat; + int wildcard = 0; + + unsigned char lastchar = 'a'; + unsigned i; + unsigned char charmap[32]; + + while (*txt) + { + + /* EOF pattern but !EOF text? */ + if (*pat == '\0') + { + if (wildcard) + { + pat = fallback; + } + else + { + return 1; + } + } + + /* '*' in the pattern? */ + if (*pat == '*') + { + + /* The pattern ends afterwards? Speed up the return. */ + if (*++pat == '\0') + { + return 0; + } + + /* Else, set wildcard mode and remember position after '*' */ + wildcard = 1; + fallback = pat; + } + + /* Character range specification? */ + if (*pat == '[') + { + memset(charmap, '\0', sizeof(charmap)); + + while (*++pat != ']') + { + if (!*pat) + { + return 1; + } + else if (*pat == '-') + { + if ((*++pat == ']') || *pat == '\0') + { + return(1); + } + for (i = lastchar; i <= *pat; i++) + { + charmap[i / 8] |= (unsigned char)(1 << (i % 8)); + } + } + else + { + charmap[*pat / 8] |= (unsigned char)(1 << (*pat % 8)); + lastchar = *pat; + } + } + } /* -END- if Character range specification */ + + + /* + * Char match, or char range match? + */ + if ( (*pat == *txt) + || (*pat == '?') + || ((*pat == ']') && (charmap[*txt / 8] & (1 << (*txt % 8)))) ) + { + /* + * Sucess: Go ahead + */ + pat++; + } + else if (!wildcard) + { + /* + * No match && no wildcard: No luck + */ + return 1; + } + else if (pat != fallback) + { + /* + * Increment text pointer if in char range matching + */ + if (*pat == ']') + { + txt++; + } + /* + * Wildcard mode && nonmatch beyond fallback: Rewind pattern + */ + pat = fallback; + /* + * Restart matching from current text pointer + */ + continue; + } + txt++; + } + + /* Cut off extra '*'s */ + if(*pat == '*') pat++; + + /* If this is the pattern's end, fine! */ + return(*pat); + +} + + /********************************************************************* * * Function : simple_domaincmp @@ -1104,7 +1267,7 @@ jb_err create_url_spec(struct url_spec *url, char *buf) } /* If it isn't a tag pattern it must be a URL pattern. */ - return compile_url_pattern(url, (char *)buf); + return compile_url_pattern(url, buf); } @@ -1228,7 +1391,7 @@ int match_portlist(const char *portlist, int port) */ if (port == atoi(min)) { - free(portlist_copy); + freez(portlist_copy); return(1); } } @@ -1241,7 +1404,7 @@ int match_portlist(const char *portlist, int port) *max++ = '\0'; if(port >= atoi(min) && port <= (atoi(max) ? atoi(max) : 65535)) { - free(portlist_copy); + freez(portlist_copy); return(1); } @@ -1261,7 +1424,7 @@ int match_portlist(const char *portlist, int port) } } - free(portlist_copy); + freez(portlist_copy); return 0; }