function url_decode(str){
var hex = /^[0-9a-fA-F]{2}/;
var out='';
var arr = str.split('%');
if(arr.length<2) return str;
for(var i=0;i<arr.length;i++)
{
  /*look for hex values */
  if(hex.exec(arr[i])) {
    out += String.fromCharCode(parseInt(arr[i].substring(0,2),16))+arr[i].substring(2,arr[i].length);
  } else { if(i==0) out+=arr[i]; else out+='%'+arr[i];
  }
}
return utf8to16(out);
}

function utf16to8(str) {
    var out, i, len, c;

    out = "";
    len = str.length;
    for(i = 0; i < len; i++) {
	c = str.charCodeAt(i);
	if ((c >= 0x0001) && (c <= 0x007F)) {
	    out += str.charAt(i);
	} else if (c > 0x07FF) {
	    out += String.fromCharCode(0xE0 | ((c >> 12) & 0x0F));
	    out += String.fromCharCode(0x80 | ((c >>  6) & 0x3F));
	    out += String.fromCharCode(0x80 | ((c >>  0) & 0x3F));
	} else {
	    out += String.fromCharCode(0xC0 | ((c >>  6) & 0x1F));
	    out += String.fromCharCode(0x80 | ((c >>  0) & 0x3F));
	}
    }
    return out;
}

function utf8to16(str) {
    var out, i, len, c;
    var char2, char3;

    out = "";
    len = str.length;
    i = 0;
    while(i < len) {
	c = str.charCodeAt(i++);
	switch(c >> 4)
	{
	  case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
	    // 0xxxxxxx
	    out += str.charAt(i-1);
	    break;
	  case 12: case 13:
	    // 110x xxxx   10xx xxxx
	    char2 = str.charCodeAt(i++);
	    out += String.fromCharCode(((c & 0x1F) << 6) | (char2 & 0x3F));
	    break;
	  case 14:
	    // 1110 xxxx  10xx xxxx  10xx xxxx
	    char2 = str.charCodeAt(i++);
	    char3 = str.charCodeAt(i++);
	    out += String.fromCharCode(((c & 0x0F) << 12) |
					   ((char2 & 0x3F) << 6) |
					   ((char3 & 0x3F) << 0));
	    break;
	}
    }
    return out;
}

function trace(url){
var tracker = _gat._getTracker("UA-XXXXXXX-X");
tracker._trackPageview(url);
}

Now every time I need to track something I call this function with a custom build URL.

A lot of people out there use services like delicious where you tag you favorite sites and make this available to other users. Now I started to grab that data and began to build a massive tag cloud. After some time the site collected hundreds of thousands of links with their corresponding tags. So now you can start on the site and search for tags which interests you. These search tags will then be correlated against the cloud database and you get the most active links for your tags. So here is an example.
Let’s say you are interested in a tomcat tutorial.
tags:

tutorial, tomcat

results:

howtoforge.com
howtogeek.com
java.sun.com

Of course those results will be a link to the concrete tutorial (not just the entry page).
So far to the official part. For me this is more of a fun project. I prefer to start with some random tag and then wander around. It’s more like browsing, cause you start at points that you don’t already know. You have the chance to break out of your existing network of most used sites and see something new.

So have fun with it.

www.cloudtheweb.com

PS: For the implementation part – if you have any questions, just ask. I’m planning to explain some details about how it works on some later posts.

First download the GLUEscript source from sourceforge.
A second tool you will need to get this running is premake. This is also a sourceforge project (you can use the binary version of it right away).
After downloading, I copied the premake binary into the glue/src folder.

So now we can start with fetching the dependencies which debian can fulfill.

sudo apt-get install libnspr4-0d libnspr4-0d-dbg libnspr4-dev libcurl4-openssl-dev libwxgtk2.8-dev libssl-dev libiodbc2-dev libmysql++-dev

In addition to that I needed a library called poco version 1.3.5 (all repositories I found just provided versions up to 1.3.3 -> those don’t work). So get the source from http://pocoproject.org/download/ (the complete version). Compiling that should make no trouble cause all the dependencies are already installed.

/tmp$ cd poco-1.3.5-all/
/tmp/poco-1.3.5-all$ ./configure
Configured for Linux
/tmp/poco-1.3.5-all$ make
/tmp/poco-1.3.5-all$ sudo make install

Now let’s get back to configuring GLUEscript. All configuration is done via lua script which will than be consumed by premake. The config file I needed to edit was the premake.lua file:

-- Check NSPR
if ( string.len(nspr_dir) == 0 ) then
  print("Using the NSPR library which is part of GLUEscript")
  dopackage("nspr") -- build our own NSPR
  nspr_dir = "../nspr/include"
  nspr_lib = "nspr"
  nspr_lib_dir = project.libdir
else
  print("You are using your own NSPR library: ")
  nspr_dir = "/usr/include/nspr"
  print("nspr include: " .. nspr_dir)
  print("nspr lib: " .. nspr_lib_dir .. "/" .. nspr_lib)
end

I copied the whole paragraph to just make it easier to find the position. Important is the added row in the else part.

nspr_dir = “/usr/include/nspr”

This is needed because debian has a different file structure for header files than the script expects it.

After that we are done with configuring. To actually start the build process you have to run premake first.

./premake gnu
make

The output will be generated to the following directory:

glue/bin/Debug

So far the makefile does not a an installation part. So if you want to install this you have to do it by yourself.

PS: This only works for the 0.0.1 version. So far I didn’t get any more recent svn version running.