X-Git-Url: http://www.privoxy.org/gitweb/?a=blobdiff_plain;f=urlmatch.c;h=f3eaa411b666e41be631c649dd19f8afffcf4e65;hb=4672f9f7b2e6acf8027f4d744b0db3cb2de04aad;hp=1d65c3fee188abff29b77ad7faa241088adb14f8;hpb=b3c3519794426d258aba2ff07313b2f1048189cd;p=privoxy.git diff --git a/urlmatch.c b/urlmatch.c index 1d65c3fe..f3eaa411 100644 --- a/urlmatch.c +++ b/urlmatch.c @@ -1,4 +1,4 @@ -const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.12 2006/07/18 14:48:47 david__schmidt Exp $"; +const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.16 2007/02/13 13:59:24 fabiankeil Exp $"; /********************************************************************* * * File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $ @@ -6,7 +6,7 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.12 2006/07/18 14:48:47 david__s * Purpose : Declares functions to match URLs against URL * patterns. * - * Copyright : Written by and Copyright (C) 2001-2003, 2006 the SourceForge + * Copyright : Written by and Copyright (C) 2001-2003, 2006-2007 the SourceForge * Privoxy team. http://www.privoxy.org/ * * Based on the Internet Junkbuster originally written @@ -33,6 +33,25 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.12 2006/07/18 14:48:47 david__s * * Revisions : * $Log: urlmatch.c,v $ + * 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) @@ -205,7 +224,7 @@ jb_err init_domain_components(struct http_request *http) /* map to lower case */ for (p = http->dbuffer; *p ; p++) { - *p = tolower((int)(unsigned char)*p); + *p = (char)tolower((int)(unsigned char)*p); } /* split the domain name into components */ @@ -222,7 +241,7 @@ jb_err init_domain_components(struct http_request *http) } /* save a copy of the pointers in dvec */ - size = http->dcount * sizeof(*http->dvec); + size = (size_t)http->dcount * sizeof(*http->dvec); http->dvec = (char **)malloc(size); if (NULL == http->dvec) @@ -258,7 +277,7 @@ jb_err init_domain_components(struct http_request *http) *********************************************************************/ jb_err parse_http_url(const char * url, struct http_request *http, - struct client_state *csp) + const struct client_state *csp) { int host_available = 1; /* A proxy can dream. */ @@ -458,7 +477,7 @@ jb_err parse_http_url(const char * url, *********************************************************************/ jb_err parse_http_request(const char *req, struct http_request *http, - struct client_state *csp) + const struct client_state *csp) { char *buf; char *v[10]; @@ -477,7 +496,6 @@ jb_err parse_http_request(const char *req, n = ssplit(buf, " \r\n", v, SZ(v), 1, 1); if (n != 3) { - log_error(LOG_LEVEL_ERROR, "Trouble ssplitting: %s", buf); free(buf); return JB_ERR_PARSE; } @@ -523,6 +541,22 @@ jb_err parse_http_request(const char *req, || (0 == strcmpic(v[0], "unsubscribe")) || (0 == strcmpic(v[0], "notify")) || (0 == strcmpic(v[0], "poll")) + + /* + * Or yet another WebDAV extension, this time for + * Web Distributed Authoring and Versioning (RFC3253) + */ + || (0 == strcmpic(v[0], "version-control")) + || (0 == strcmpic(v[0], "report")) + || (0 == strcmpic(v[0], "checkout")) + || (0 == strcmpic(v[0], "checkin")) + || (0 == strcmpic(v[0], "uncheckout")) + || (0 == strcmpic(v[0], "mkworkspace")) + || (0 == strcmpic(v[0], "update")) + || (0 == strcmpic(v[0], "label")) + || (0 == strcmpic(v[0], "merge")) + || (0 == strcmpic(v[0], "baseline-control")) + || (0 == strcmpic(v[0], "mkactivity")) ) { /* Normal */ @@ -710,6 +744,9 @@ static int domain_match(const struct url_spec *pattern, const struct http_reques jb_err create_url_spec(struct url_spec * url, const char * buf) { char *p; + int errcode; + size_t errlen; + char rebuf[BUFFER_SIZE]; assert(url); assert(buf); @@ -727,6 +764,38 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) return JB_ERR_MEMORY; } + /* Is it tag pattern? */ + if (0 == strncmpic("TAG:", url->spec, 4)) + { + if (NULL == (url->tag_regex = zalloc(sizeof(*url->tag_regex)))) + { + freez(url->spec); + return JB_ERR_MEMORY; + } + + /* buf + 4 to skip "TAG:" */ + errcode = regcomp(url->tag_regex, buf + 4, (REG_EXTENDED|REG_NOSUB|REG_ICASE)); + if (errcode) + { + errlen = regerror(errcode, url->preg, rebuf, sizeof(rebuf)); + if (errlen > (sizeof(rebuf) - 1)) + { + errlen = sizeof(rebuf) - 1; + } + rebuf[errlen] = '\0'; + + log_error(LOG_LEVEL_ERROR, "error compiling %s: %s", url->spec, rebuf); + + freez(url->spec); + regfree(url->tag_regex); + freez(url->tag_regex); + + return JB_ERR_PARSE; + } + return JB_ERR_OK; + } + + /* Only reached for URL patterns */ if ((p = strchr(buf, '/')) != NULL) { if (NULL == (url->path = strdup(p))) @@ -744,9 +813,6 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) } if (url->path) { - int errcode; - char rebuf[BUFFER_SIZE]; - if (NULL == (url->preg = zalloc(sizeof(*url->preg)))) { freez(url->spec); @@ -754,14 +820,13 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) return JB_ERR_MEMORY; } - sprintf(rebuf, "^(%s)", url->path); + snprintf(rebuf, sizeof(rebuf), "^(%s)", url->path); errcode = regcomp(url->preg, rebuf, (REG_EXTENDED|REG_NOSUB|REG_ICASE)); if (errcode) { - size_t errlen = regerror(errcode, - url->preg, rebuf, sizeof(rebuf)); + errlen = regerror(errcode, url->preg, rebuf, sizeof(rebuf)); if (errlen > (sizeof(rebuf) - (size_t)1)) { @@ -825,7 +890,7 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) */ for (p = url->dbuffer; *p ; p++) { - *p = tolower((int)(unsigned char)*p); + *p = (char)tolower((int)(unsigned char)*p); } /* @@ -849,7 +914,7 @@ jb_err create_url_spec(struct url_spec * url, const char * buf) /* * Save a copy of the pointers in dvec */ - size = url->dcount * sizeof(*url->dvec); + size = (size_t)url->dcount * sizeof(*url->dvec); url->dvec = (char **)malloc(size); if (NULL == url->dvec) @@ -903,6 +968,11 @@ void free_url_spec(struct url_spec *url) regfree(url->preg); freez(url->preg); } + if (url->tag_regex) + { + regfree(url->tag_regex); + freez(url->tag_regex); + } } @@ -916,12 +986,18 @@ void free_url_spec(struct url_spec *url) * 1 : pattern = a URL pattern * 2 : url = URL to match * - * Returns : 0 iff the URL matches the pattern, else nonzero. + * Returns : Nonzero if the URL matches the pattern, else 0. * *********************************************************************/ int url_match(const struct url_spec *pattern, const struct http_request *url) { + if (pattern->tag_regex != NULL) + { + /* It's a tag pattern and shouldn't be matched against URLs */ + return 0; + } + return ((pattern->port == 0) || (pattern->port == url->port)) && ((pattern->dbuffer == NULL) || (domain_match(pattern, url) == 0)) && ((pattern->path == NULL) ||