1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
|
/**
* URL Processing
*
* Copyright (C) 2000-2007 by
* Jeffrey Fulmer - <jeff@joedog.org>, et al.
* This file is distributed as part of Siege
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*
*/
#include <stdio.h>
#include <stdlib.h>
#include <setup.h>
#include <load.h>
#include <joedog/joedog.h>
#include <joedog/boolean.h>
/*HARDCODED ALERT*/
#define PLENGTH 84 /* length of the *prot[] array */
/**
* ALERT: using hardcoded array lengths below,
* if you change this array, then redefine PLENGTH
*
* Currently http(prot[25]) and https(prot[26]) are
* the only supported protocols. But all w3c supported
* protocols are listed for URL evaluation.
*/
static const char *prot[] = {
"about:", "addrbook:", "acap:", "afp:",
"afs:", "callto:", "chttp:", "cid:",
"clsid:", "data:", "date:", "DAV:",
"dns:", "eid:", "fax:", "file:",
"finger:", "freenet:", "ftp:", "gopher:",
"gsm:", "h323:", "h324:", "hdl:",
"hnews:", "http:", "https:", "iioploc:",
"ilu:", "imap:", "IOR:", "irc:",
"isbn:", "java:", "JavaRMI:", "javascript:",
"jdbc:", "ldap:", "lid:", "lifn:",
"livescript:", "lrq:", "mailto:", "mailserver:",
"md5:", "mid:", "mocha:", "modem:",
"news:", "nfs:", "nntp:", "opaquelocktoken:"
"path:", "phone:", "pop:", "pop3:",
"printer:", "prospero:", "res:", "rtsp:",
"rvp:", "rwhois:", "rx:", "sdp:",
"sip:", "shttp:", "snews:", "STANF:",
"t120:", "tel:", "telephone:", "telnet:",
"tip:", "tn3270:", "tv:", "uuid:",
"urn:", "vemmi:", "videotex:", "view:",
"wais:", "whois++:", "whodp:", "z39.50r:",
"z39.50s:"
};
/**
* int value of the length of the protocol
* string passed to the function.
*/
int
protocol_length(char *url)
{
int x;
/**
* hardcoded protocol length!! see explanation above...
*/
for(x = 0; x < PLENGTH; x ++){
if(strncasecmp( url, prot[x], strlen( prot[x] )) == 0){
return strlen(prot[x]);
}
}
return 0;
}
/**
* boolean, returns true if the protocol is
* supported by siege, false if it is not.
*/
BOOLEAN
is_supported(char* url)
{
if( strncasecmp( url, prot[25], strlen( prot[25] )) == 0 )
return TRUE;
#ifdef HAVE_SSL
if( strncasecmp( url, prot[26], strlen( prot[26] )) == 0 )
return TRUE;
#endif /* HAVE_SSL */
return FALSE;
}
/**
* get_protocol
* returns protocol char*
*/
PROTOCOL
get_protocol(const char *url)
{
if(strncasecmp(url, prot[25], strlen(prot[25])) == 0)
return HTTP;
if(strncasecmp(url, prot[26], strlen(prot[26])) == 0)
#ifdef HAVE_SSL
return HTTPS;
#else
return HTTP;
#endif /* HAVE_SSL */
else
return UNSUPPORTED;
}
/**
* get_default_port
*/
int
get_default_port(PROTOCOL p)
{
if(p == HTTP)
return 80;
if(p == HTTPS)
#ifdef HAVE_SSL
return 443;
#else
return 80;
#endif /* HAVE_SSL */
else
return 80;
}
/**
* insert_childid
* replaces all '+' characters in POST
* data with numbers derived from the process id.
* return void
*/
void
insert_childid(URL *U, int mypid)
{
int i,j;
char *c, *f, *l;
char pidbuf[6];
sprintf( pidbuf, "%5.5d", mypid );
for( i=0; i<5; i++ ){
if( U->posttemp ){
f = strchr(U->posttemp, '+');
l = strrchr(U->posttemp, '+');
/* Start at last occurrence of '+' and move to first */
for (j=sizeof(pidbuf)-1, c=l; c >= f; j--, c--){
if (*c == '+'){
*c = pidbuf[j-1];
}
if (j == 0){
j=sizeof(pidbuf)-1; /* Start over */
}
}
/* Now that we're done, copy the new template to data */
strcpy(U->postdata, U->posttemp);
}
}
}
char *
url_encode(char *str)
{
int size = 0;
char *ch, *bk;
char *p, *buf;
static char unsafe[] = "<>{}#%|\"\\^~[]`@:\033";
static char char2hex[16] = "0123456789ABCDEF";
bk = ch = str;
do{
if( strchr( unsafe, *ch ))
size += 2;
ch++; size ++;
} while( *ch );
buf = (char*)malloc( size +1 );
p = buf;
ch = bk;
do{
if( strchr( unsafe, *ch )){
const char c = *ch;
*p++ = '%';
*p++ = char2hex[(c >> 4) & 0xf];
*p++ = char2hex[c & 0xf];
}
else{
*p++ = *ch;
}
ch ++;
} while( *ch );
*p = '\0';
return(buf);
}
/**
* build_from_template
* builds POST data replacing all '*'
* characters with random numbers
* returns void
*/
void
build_from_template(URL *U, int rand)
{
char *s=U->posttemp;
char *t=U->postdata;
int i,j,f,l;
char buf[9];
sprintf(buf, "%8.8d", rand);
f = strchr(s, '*') -s;
l = strrchr(s, '*') -s;
/* Start at last occurrence of '+' and move to first */
for (j=sizeof(buf)-1, i=l; i >= f; j--, i--){
if (s[i] == '*'){
t[i] = buf[j-1];
} else {
t[i] = s[i];
}
if (j == 0){
j=sizeof(buf)-1; /* Start over */
}
}
}
/**
* process_post_data
* populates URL->postdata with POST information
*/
void
process_post_data(URL *U, char *datap)
{
for( ; isspace((unsigned int)*datap); datap++ ){
/* Advance past white space */
}
if(*datap == '<'){
datap++;
load_file(U, datap);
return;
} else {
U->postdata = xstrdup(datap);
U->postlen = strlen(U->postdata);
U->conttype = xstrdup("application/x-www-form-urlencoded");
return;
}
return;
}
URL *
build_url(char *url, int defaultport, int id)
{
URL *U; /* defined in setup.h */
int mark[4] = {0,0,0,0}; /* placement counters. */
char *post_cmd=NULL; /* POST directive for server */
char *tmp;
U = xcalloc(sizeof(URL), 1);
U->urlid = id;
post_cmd = strstr(url, " POST");
if( post_cmd != NULL ){
/* How do we deal with handling the multi-headed url_t arrays */
U->calltype = URL_POST;
*post_cmd = 0;
post_cmd += 5;
process_post_data(U, post_cmd);
} else {
U->calltype = URL_GET;
U->postdata = NULL;
U->posttemp = NULL;
U->postlen = 0;
}
if((mark[0] = protocol_length(url)) > 0 && is_supported(url) == TRUE){
mark[0] += 2;
} else if((mark[0] = protocol_length(url)) > 0 && is_supported(url) == FALSE){
U->protocol = UNSUPPORTED;
mark[0] += 2;
joe_warning("unsupported protocol");
return NULL;
} else {
/* we are dealing with who knows what */
tmp = (char*)strstr( url, "://" );
if(tmp != NULL){
mark[0] = (strlen(url) - (strlen(tmp) - 3));
} else {
mark[0] = 0; /* no specified protocol, assuming http: */
}
}
mark[1] = mark[0];
while(url[mark[1]] && url[mark[1]] != ':' && url[mark[1]] != '/') mark[1]++;
if(url[mark[1]] == ':'){
mark[3] = mark[1];
while(url[mark[1]] && url[mark[1]] != '/'){
mark[1]++;
}
} else {
mark[3] = mark[1];
}
if(url[mark[1]] == '/'){
mark[2] = mark[1];
} else {
mark[2] = strlen(url);
}
/* here we piece it all together */
if( mark[0] == 0 ){
U->protocol = HTTP;
} else {
U->protocol = get_protocol(url);
}
if(mark[0] != mark[3]){
U->hostname = (char*)(substring(url, mark[0], (mark[3] - mark[0])));
} else {
joe_warning( "malformed URL: %s", url );
return NULL;
}
if(mark[3] == mark[1]){
if(defaultport < 0)
U->port = get_default_port(U->protocol);
else
U->port = defaultport;
} else {
char *portstr = substring(url, mark[3]+1, (mark[2]-(mark[3]+1)));
if(portstr != NULL){
U->port = atoi(portstr);
} else {
U->port = 80;
}
xfree(portstr);
}
tmp = substring(url, mark[2], strlen(url));
if(tmp == NULL){
U->pathname = (char *)xstrdup("/");
} else {
U->pathname = (char *)xstrdup(tmp);
}
U->pathname = (strlen(U->pathname)==0)?strcpy(U->pathname, "/"):U->pathname;
trim(U->pathname);
snprintf(
U->url, MAX_URL, "%s%s:%d%s",
(U->protocol==HTTP)?"http://":"https://", U->hostname, U->port, U->pathname
);
xfree(url);
xfree(tmp);
return(U);
}
URL *
add_redirect(char *url, int port, int id)
{
char *tmp;
/**
* freed in build_url()
*/
tmp = xstrdup(url);
return build_url(tmp, port, id);
}
/**
* add_url
* parses char * then populates and
* returns a URL with appropriate data.
*/
URL *
add_url(char *url, int id)
{
char *tmp;
/**
* check string integrity so we
* can inform the user rather then
* simply abort with an archaic msg.
*/
if(!url){
joe_warning("INVALID URL: <%s>", url);
display_help();
}
/**
* freed in build_url()
*/
tmp = (char*)xstrdup(url);
return build_url(tmp, -1, id);
}
|