...so that the text is more readable in the presenter mode. Chrome by
default uses 'detail' for screen sharing. I went with the 'text' here,
because the docs[1] say "may take advantage of encoder tools that
optimize for text rendering." - whether that's good specifically for
the presenter mode I don't know. It looked good for me when tested
on Chrome.

https://www.w3.org/TR/mst-content-hint/

* Update JitsiStreamPresenterEffect.js
Create/terminate the Web Worker on effect start/stop so that we don't leak them.

On electron 7 drawing on hidden canvas will trigger a memory leak.
Not appending the canvas for the DOM seems to solve the problem.

- Adds the ability to share video as a "PiP" when screenshare is in progress.
- Add a method for creating a local presenter track.
- Make sure isLocalVideoTrackMuted returns the correct mute state when only screenshare is present.
- Make sure we get the updated window size of the window being shared before painting it on the canvas.
- Make sure we check if the shared window has been resized