url.cc

100 病毒源碼,原始碼,無毒 ......

// Larbin
// Sebastien Ailleret
// 15-11-99 -> 29-03-00

/* This class describes an URL */

#include <assert.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <iostream.h>
#include <sys/socket.h>

#include "types.h"
#include "global.h"
#include "xutils/url.h"
#include "xutils/text.h"
#include "xutils/connexion.h"
#include "xutils/debug.h"

/* Constructor : Parses an url */
url::url (char *u, uint depth, char *base) {
  newUrl();
  this->depth = depth;
  host = NULL;
  port = 80;
  file = NULL;
  if (startWithIgnoreCase("http://", u)) {
	// absolute url
	parse (u + 7);
  } else if (base != NULL) {
	if (startWithIgnoreCase("http:", u)) {
	  parseWithBase(u+5, base);
	} else if (isProtocol(u)) {
	  // Unknown protocol (mailto, ftp, news, file, gopher...)
	} else {
	  parseWithBase(u, base);
	}
  }
  delete [] u;
}

/* Constructor : read the url from a file (cf serialize)
 */
url::url (String *line) {
  newUrl();
  int i=0;
  // Read depth
  depth = 0;
  while ((*line)[i] >= '0' && (*line)[i] <= '9') {
	depth = 10*depth + (*line)[i] - '0';
	i++;
  }
  assert((*line)[i] == ' ');
  int deb = ++i;
  // Read host
  while ((*line)[i] != ':' && (*line)[i] != 0) {
	i++;
  }
  assert ((*line)[i] != 0);
  (line->getString())[i] = 0;
  host = newString(line->getString()+deb);
  i++;
  // Read port
  port = 0;
  while ((*line)[i] >= '0' && (*line)[i] <= '9') {
	port = 10*port + (*line)[i] - '0';
	i++;
  }
  // Read file name
  assert((*line)[i] == '/');
  file = newString(line->getString()+i);
  delete line;
}

/* Destructor */
url::~url () {
  delUrl();
  delete [] host;
  delete [] file;
}

/* Is it a valid url ?
 */
int url::isValid () {
  return (host != NULL) && (file != NULL);
}

/* print an URL */
void url::print () {
  cout << "http://" << host << ":" << port << file << "\n";
}

/* return the host */
char *url::getHost () {
  return host;
}

/* return the port */
uint url::getPort () {
  return port;
}

/* return the file */
char *url::getFile () {
  return file;
}

/** Depth in the Site */
uint url::getDepth () {
  return depth;
}

/** Set depth to one if we are at an entry point in the site */
void url::setDepth (char *fromHost) {
  if (strcmp(fromHost, host)) {
	depth = global::depthInSite;
  }
}

/* return the base of the url */
char *url::giveBase () {
  char *tmp;
  int i = strlen(file);
  int j;

  assert (file[0] == '/');
  while (file[i] != '/') {
	i--;
  }
  j = strlen(host);
  tmp = new char[12+i+j];  // strlen(host) + 1 + 9 + (i+1) + 1
                           // (host):(port)(file)
  strcpy (tmp, host);
  tmp[j] = ':';
  sprintf(tmp + j + 1, "%u", port);
  while (tmp[j] != 0) {
	j++;
  }
  tmp[i+j+1] = 0;  // delete file name, just keep the path
  while (i >= 0) {
	tmp [j+i] = file[i];
	i--;
  }
  return tmp;
}

/** return a char * representation of the url
 * give means that you have to delete the string yourself
 */
char *url::giveUrl () {
  char *tmp;
  int i = strlen(file);
  int j = strlen(host);

  tmp = new char[18+i+j];  // 7 + j + 1 + 9 + i + 1
                           // http://(host):(port)(file)
  strcpy(tmp, "http://");
  strcpy (tmp+7, host);
  tmp[j+7] = ':';
  sprintf(tmp + j + 8, "%u", port);
  j += 8;
  while (tmp[j] != 0) {
	j++;
  }
  // Copy file name
  while (i >= 0) {
	tmp [j+i] = file[i];
	i--;
  }
  return tmp;
}

/* return a hashcode for the host of this url */
uint url::hostHashCode () {
  unsigned int h=port;
  unsigned int i;
  for (i=0; i < strlen(host); i++) {
	h = 37*h + host[i];
  }
  return h;
}

/* return a hashcode for this url */
uint url::hashCode () {
  unsigned int h=port;
  unsigned int i;
  for (i=0; i < strlen(host); i++) {
	h = 31*h + host[i];
  }
  for (i=0; i < strlen(file); i++) {
	h = 31*h + file[i];
  }
  return h;
}

/* parses a url : 
 * at the end, arg must not have its initial state, 
 * at least for the real part of the url
 * http:// has allready been suppressed
 */
void url::parse (char *arg) {
  int deb = 0, fin = deb;
  // Find the end of host name (put it into lowerCase)
  while (arg[fin] != '/' && arg[fin] != ':'
		 && arg[fin] != '\n' && arg[fin] != 0) {
	if (arg[fin] >= 'A' && arg[fin] <= 'Z') {
	  arg[fin] = arg[fin] - 'A' + 'a';
	}
	fin++;
  }
  if (arg[fin] == '/') {
	// no port specified, use 80 (default), get host name
	arg[fin] = '\0';
	host = newString(arg + deb);
	arg[fin] = '/';
  } else if (arg[fin] == ':') {
	// read port number
	arg[fin] = '\0';
	host = newString(arg + deb);
	arg[fin] = ':';
	port = 0;
	fin++;
	while (arg[fin] >= '0' && arg[fin] <= '9') {
	  port = port*10 + arg[fin]-'0';
	  fin++;
	}
	if (arg[fin] != '/') {
	  delete [] host;
	  host = NULL;
	  return;
	}
  } else {
	// invalid url
	return;
  }

  // normalize file name
  if (normalize(arg + fin)) {
	// get file name
	file = newString(arg + fin);
  } else {
	  delete [] host;
	  host = NULL;
  }
}

/** parse a file with base
 */
void url::parseWithBase (char *u, char *base) {
  int i = 0;
  // relative url
  parse (base);
  // suppress the #qsdf at the end of the file name
  while (u[i] != 0 && u[i] != '#' && u[i] != '\n') {
	i++;
  }
  u[i] = 0;
  // cat filebase and file
  if (isValid()) {
	if (u[0] == '/') {
	  delete [] file;
	  file = newString(u);
	} else {
	  char *tmp = new char[strlen(file) + strlen(u) + 1];
	  strcpy(tmp, file);
	  strcpy(tmp + strlen(file), u);
	  delete [] file;
	  file = tmp;
	}
	if (!normalize(file)) {
	  delete [] host;
	  host = NULL;
	  delete [] file;
	  file = NULL;
	}
  } else {
	// problem with base tag
  }
}

/** normalize file name
 * @return true if it is ok, false otherwise (cgi-bin)
 */
bool url::normalize (char *file) {
  int i=0;
  while (file[i] != 0 &&  file[i] != '#' && file[i] != '\n') {
	if (file[i] == '/') {
	  if (file[i+1] == '.' && file[i+2] == '/') {
		// suppress /./
		int j=i+3;
		while (file[j] != 0) {
		  file[j-2] = file[j];
		  j++;
		}
		file[j-2] = file[j];  // write the final char (0)
	  } else if (file[i+1] == '.' && file[i+2] == '.' && file[i+3] == '/') {
		// suppress /../
		if (i == 0) {
		  // the file name starts with /../ : error
		  return false;
		} else {
		  int j = i+4, dec;
		  i--;
		  while (file[i] != '/') {
			i--;
		  }
		  dec = i+1-j; // dec < 0
		  while (file[j] != 0) {
			file[j+dec] = file[j];
			j++;
		  }
		  file[j+dec] = file[j];  // write the final char (0)
		}
	  } else {
		// nothing special, go forward
		i++;
	  }
	} else if (file[i] == '?') {
	  // My god : this is one more of those horrible cgi
	  return false;
	} else {
	  // nothing special, go forward
	  i++;
	}
  }
  file[i] = 0;
  return true;
}

/* Does this url starts with a protocol name */
bool url::isProtocol (char *s) {
  uint i = 0;
  while (isalnum(s[i])) {
	i++;
  }
  return s[i] == ':';
}

/* serialize the url */
char *url::serialize (int fds) {
  char *s = new char[30+strlen(host)+strlen(file)];
  sprintf(s, "%u %s:%u%s\n", depth, host, port, file);
  return s;
}