Proposed apigen refactorings
=============================

First of all we would like to have some kind of a persistent storage
for apigen, so we could use it for different purposes (hint! hint! pdb)
than only web pages. This will resolve the issue of having separated
apigen "data" generation and web page generation.

Apigen is very usefull feature, but we don't use it in general. Which
is bad. One of the reasons is above and the other one is that API of
apigen is not that well defined which makes it harder to use. So what
I think would be:

* **py.apigen** tool, which will take tests and initpkg (or whatever
  means of collecting data) and will try to store it somewhere
  (not sure, plain text log as a first step?). Than next step
  would be to have tools for generating webpages out of it
  (py.webapi or so) and other tools which will integrate it to pdb,
  emacs (pick your random IDE here) or whatever.

* Another option is to have py.test generate those data and have another
  tools using it.

* Data storage. Text with a log comes in mind, but it's not very handy.
  Using any sort of SQL doesn't really counts, cause it makes pylib
  less standalone, especially that I wouldn't like to have write all
  those SQL myself, but rather use some kind of sql object relational
  mapper. Another format might be some kind of structured text
  (xml anyone?) or pickled stuff. Pickle has problems on his own,
  so I don't have any best solution at hand.

* Accessing. These are all strings and simple types built on top of it.
  Probably would be good not to store all data in memory, because it might
  be huge in case we would like to have all past informations there.