X-Git-Url: http://www.privoxy.org/gitweb/?a=blobdiff_plain;f=urlmatch.c;h=3a9c865784a75f3eed315be14e35dcbd887a6237;hb=1e51d8b2242eca8fc0657cf0c51330207d60771b;hp=6cb6013f3371e9ff1ad5aa67d7976ced67b9387d;hpb=0428133610c525457cb16f7ac6a54203a2743d6c;p=privoxy.git diff --git a/urlmatch.c b/urlmatch.c index 6cb6013f..3a9c8657 100644 --- a/urlmatch.c +++ b/urlmatch.c @@ -1,4 +1,4 @@ -const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.61 2011/05/22 10:25:26 fabiankeil Exp $"; +const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.69 2012/03/09 16:24:36 fabiankeil Exp $"; /********************************************************************* * * File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $ @@ -6,7 +6,7 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.61 2011/05/22 10:25:26 fabianke * Purpose : Declares functions to match URLs against URL * patterns. * - * Copyright : Written by and Copyright (C) 2001-2009 + * Copyright : Written by and Copyright (C) 2001-2011 * the Privoxy team. http://www.privoxy.org/ * * Based on the Internet Junkbuster originally written @@ -135,7 +135,7 @@ jb_err init_domain_components(struct http_request *http) /* map to lower case */ for (p = http->dbuffer; *p ; p++) { - *p = (char)tolower((int)(unsigned char)*p); + *p = (char)privoxy_tolower(*p); } /* split the domain name into components */ @@ -167,6 +167,53 @@ jb_err init_domain_components(struct http_request *http) #endif /* ndef FEATURE_EXTENDED_HOST_PATTERNS */ +/********************************************************************* + * + * Function : url_requires_percent_encoding + * + * Description : Checks if an URL contains invalid characters + * according to RFC 3986 that should be percent-encoded. + * Does not verify whether or not the passed string + * actually is a valid URL. + * + * Parameters : + * 1 : url = URL to check + * + * Returns : True in case of valid URLs, false otherwise + * + *********************************************************************/ +int url_requires_percent_encoding(const char *url) +{ + static const char allowed_characters[128] = { + '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', + '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', + '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', + '\0', '\0', '\0', '!', '\0', '#', '$', '%', '&', '\'', + '(', ')', '*', '+', ',', '-', '.', '/', '0', '1', + '2', '3', '4', '5', '6', '7', '8', '9', ':', ';', + '\0', '=', '\0', '?', '@', 'A', 'B', 'C', 'D', 'E', + 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', + 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', + 'Z', '[', '\0', ']', '\0', '_', '\0', 'a', 'b', 'c', + 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', + 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', + 'x', 'y', 'z', '\0', '\0', '\0', '~', '\0' + }; + + while (*url != '\0') + { + const unsigned int i = (unsigned char)*url++; + if (i >= sizeof(allowed_characters) || '\0' == allowed_characters[i]) + { + return TRUE; + } + } + + return FALSE; + +} + + /********************************************************************* * * Function : parse_http_url @@ -206,8 +253,8 @@ jb_err parse_http_url(const char *url, struct http_request *http, int require_pr */ if (*http->url == '*') { - if ( NULL == (http->path = strdup("*")) - || NULL == (http->hostport = strdup("")) ) + if (NULL == (http->path = strdup("*")) + || NULL == (http->hostport = strdup(""))) { return JB_ERR_MEMORY; } @@ -290,8 +337,8 @@ jb_err parse_http_url(const char *url, struct http_request *http, int require_pr freez(buf); - if ( (http->path == NULL) - || (http->hostport == NULL)) + if ((http->path == NULL) + || (http->hostport == NULL)) { return JB_ERR_MEMORY; } @@ -411,7 +458,7 @@ jb_err parse_http_url(const char *url, struct http_request *http, int require_pr *********************************************************************/ static int unknown_method(const char *method) { - static const char *known_http_methods[] = { + static const char * const known_http_methods[] = { /* Basic HTTP request type */ "GET", "HEAD", "POST", "PUT", "DELETE", "OPTIONS", "TRACE", "CONNECT", /* webDAV extensions (RFC2518) */ @@ -534,7 +581,7 @@ jb_err parse_http_request(const char *req, struct http_request *http) if ( (http->cmd == NULL) || (http->gpc == NULL) - || (http->ver == NULL) ) + || (http->ver == NULL)) { return JB_ERR_MEMORY; } @@ -728,7 +775,7 @@ static jb_err compile_url_pattern(struct url_spec *url, char *buf) * * Function : compile_host_pattern * - * Description : Parses and compiles a host pattern.. + * Description : Parses and compiles a host pattern. * * Parameters : * 1 : url = Target url_spec to be filled in. @@ -794,7 +841,7 @@ static jb_err compile_host_pattern(struct url_spec *url, const char *host_patter */ for (p = url->dbuffer; *p ; p++) { - *p = (char)tolower((int)(unsigned char)*p); + *p = (char)privoxy_tolower(*p); } /* @@ -924,9 +971,9 @@ static int simplematch(const char *pattern, const char *text) /* * Char match, or char range match? */ - if ( (*pat == *txt) - || (*pat == '?') - || ((*pat == ']') && (charmap[*txt / 8] & (1 << (*txt % 8)))) ) + if ((*pat == *txt) + || (*pat == '?') + || ((*pat == ']') && (charmap[*txt / 8] & (1 << (*txt % 8))))) { /* * Success: Go ahead @@ -962,7 +1009,7 @@ static int simplematch(const char *pattern, const char *text) } /* Cut off extra '*'s */ - if(*pat == '*') pat++; + if (*pat == '*') pat++; /* If this is the pattern's end, fine! */ return(*pat); @@ -1327,7 +1374,7 @@ int match_portlist(const char *portlist, int port) * or, if max was omitted, between min and 65K */ *max++ = '\0'; - if(port >= atoi(min) && port <= (atoi(max) ? atoi(max) : 65535)) + if (port >= atoi(min) && port <= (atoi(max) ? atoi(max) : 65535)) { freez(portlist_copy); return(1);