This gets around the issue of a cdn page being opened.

Recent changes in lib-jitsi-meet probably led to (1) our
RTCPeerConnection customizations on react-native not being used which is
a problem because we need them for at least NAT64 on iOS in order to
pass the review in Apple's App Store and (2) unexpected exceptions
inside react-native-webrtc.

The Promise-based WebRTC API should be merged from react-native-webrtc's
upstream but I don't want to do it right now because last time we got
multiple bugs in addition.

Destroy local tracks and also destroy large video so the
user does not wonder why camera (and mic) are still enabled
even though hangup has been pressed.

config: Whitelists the desktopSharingFrameRate config key.

feat(ss_framerate): Add config option for min/max frame rate.

This only works automatically on Android >= 8. On other platforms / versions, it
relies on the SDK user on implementing a "reduced UI" mode and reacting to the
"request PIP" delegate method.

Implement external API notification about screen sharing status

- Move the existing components for the static dial in page into
  a separate folder for easier reuse.
- Reuse those components for displaying dial-on numbers on the
  mobile page for unsupported browsers.
- Modify those components to support having tel protocol
  links on the dial-in numbers.
- Have DialInSummary, formerly DialInInfoPage, respect a
  passed in className prop for easier styling differences.

* feat(welcome): new design

* squash: update strings

* squash: copy/paste error?

* squash: remove welcome page disabling checks

* squash: change strings again

* squash: background var

* squash: title and desc css as variables

* ref(invite): remove InviteDialog

InviteDialog functionality has been moved into InfoDialog.
The InviteButton has been temporarily hacked to show one
of its dropdown options instead as the button. Future
work will bring in a redesigned InviteModal that the button
will open.

* squash: filter invalid options and map valid options

* squash: update strings

On Android we go into "immersive mode" when in a conference, this is our way of
being full-creen. There are occasions, however, in which Android takes us out of
immerfive mode without us (the application / SDK) knowing: when a child activity
is started, a modal window shown, etc.

In order to be resilient to any possible change in the immersive mode, register
a listener which will be called when Android changes it, so we can re-eavluate
if we need it and thus re-enable it.

* feat(info): new dialog design

- Add display of a dial in number.
- Add a static page to show a full list of dial in numbers.
- Add password management.
- Invite modal will be changed soon to remove password and
  dial-in.

* squash: add classes for torture tests

* squash: class for local lock for torture tests

* squash: more classes for torture tests

* squash: more classes, work around linter

* squash: remove unused string?

* squash: work around linter and avoid react warnings

* squash: pixel push, add bold

* squash: font size bump

* squash: NumbersTable -> NumbersList

* squash: document response from fetching numbers

* squash: showEdit -> editEnabled, pixel push padding for alignment

* squash: pin -> conferenceID

* squash: prepare to receive defaultCountry from api

Flow caught an incorrect function call.

When in PiP mode the LargeView will not be large enough to hold the avatar (for
those interested in the details, our avatar's size is 200, and in PiP mode the
app is resized to about 150).

In order to solve it, this PR refactors how the avatar style is passed along,
reducing it to a single "size" prop. With this only prop, the Avatar compononent
will compute the width, height and borderRadius, plus deal with some Android
shenanigans.

In addition, the LargeView component now uses DimensionsDetector to check its
own size and adjust the size prop passed to the Avatar component as needed.

* ref(large-video): reactify background

This is pre-requisite work for disabling the background on
certain browsers, namely Firefox. By moving the component
to react, and in general encapsulating background logic,
selectively disabling the background will be easier.

The component was left for LargeVideo to update so it can
continue to coordinate update timing with the actual large
video display. If the background were moved completely into
react and redux with LargeVideo, then background updates would
occur before large video updates causing visual jank.

* fix(large-video): do not show background for Firefox and temasys

Firefox has performance issues with adding filter effects on
animated elements. On temasys, the background videos weren't
really displaying anyway.

* some props refactoring

Instead of passing in classes to LargeVideoBackground, rely on
explicit props. At some point LargeVideo will have to be reactified
and the relationsihp between it and LargeVideoBackground might
change, so for now make use of props to be explicit about
how LargeVideoBackground can be modified.

Also, set the jitsiTrack to display on LargeVideoBackground to
null if the background is not displayed. This was an existing
optimization, although previously done with pausing and playing.

* squash: use newly exposed RTCBrowserType

* squash: rebase and use new lib browser util

* squash: move hiding logic all into LargeVideo

* squash: remove hiding of background on stream change. hopefully doesnt break anything

Passing around of the component was used when there were two
independent Notification components. Now that there is only
one Notification component, it is not necessary to pass
around the component.

Ga tweaks