对url格式化

/* normalize a file name : also called by robots.txt parser
 * return true if it is ok, false otherwise (cgi-bin)
 */
bool fileNormalize (char *file) {
  int i=0;
  while (file[i] != 0 && file[i] != '#') {
	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] = 0;
      } else if (file[i+1] == '/') {
        // replace // by /
        int j=i+2;
        while (file[j] != 0) {
          file[j-1] = file[j];
		  j++;
        }
        file[j-1] = 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] = 0;
		}
	  } else if (file[i+1] == '.' && file[i+2] == 0) {
		// suppress /.
        file[i+1] = 0;
        return true;
	  } else if (file[i+1] == '.' && file[i+2] == '.' && file[i+3] == 0) {
		// suppress /..
		if (i == 0) {
          // the file name starts with /.. : error
		  return false;
		} else {
		  i--;
		  while (file[i] != '/') {
			i--;
		  }
          file[i+1] = 0;
          return true;
		}
	  } else { // nothing special, go forward
		i++;
	  }
	} else if (file[i] == '%') {
      int v1 = int_of_hexa(file[i+1]);
      int v2 = int_of_hexa(file[i+2]);
      if (v1 < 0 || v2 < 0) return false;
      char c = 16 * v1 + v2;
      if (isgraph(c)) {
        file[i] = c;
        int j = i+3;
        while (file[j] != 0) {
          file[j-2] = file[j];
          j++;
        }
        file[j-2] = 0;
        i++;s
      } else if (c == ' ' || c == '/') { // keep it with the % notation
        i += 3;
      } else { // bad url
        return false;
      }
    } else { // nothing special, go forward
	  i++;
	}
  }
  file[i] = 0;
  return true;
}