Use a dimensions detecting root component. The Dimensions module does not
measure the app's view size, but the Window, which may not be the same, for
example on iOS when PiP is used.

Also refactor the aspect ratio wrap component since it can be taken directly
from the store.

Last, remove the use of DimensionsDetector on LargeVideo and TileView since they
occupy the full-screen anyway.

Fixes PiP mode on iOS.

🔥🔥🔥

* feat(tile-view): initial implementation for mobile

- Create a tile view component for displaying thumbnails in a
  two-dimensional grid.
- Update the existing TileViewButton so it shows a label in the
  overflow menu.
- Modify conference so it can display TileView while hiding
  Filmstrip.
- Modify Thumbnail so its width/height can be set and to prevent
  pinning while in tile view mode.

* use style array for thumbnail styles

* change ternary to math.min for expressiveness

* use dimensiondetector

* pass explicit disableTint prop

* use makeAspectRatioAware instead of aspectRatio prop

* update docs

* fix docs again (fix laziest copy/paste job I've ever done)

* large-video: rename onPress prop to onClick

* change forEach to for...of

* use truthy check fallthrough logic instead of explicit if

* put tile view button second to last in menu

* move spacer to a constant

* the magical incantation to make flow shut up

Since the main conference container is no longer "clickable" there must
be a way for clicking on the "large video". A clickable TestHint nested
in ParticipantView makes it easier for dealing with the fact that the
click handler is not always on the same component (required for the
pinch and zoom feature to work correctly).

TouchableWithoutFeedback and TouchableHighlight interfere with the
implementation of 'pinch to zoom' to come. We prepare for it by driving
the onClick/onPress handler(s) out of Conference, through LargeVideo and
ParticipantView into Video itself where the bulk of 'pinch to zoom' will
be implemented.

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.

The video will switch to the avatar and be tinted with gray. On the large view,
a text message indicating the user has connectivity issues will be shown.

Prepare for React 16.

The files styles.js are used (pretty much) on React Native only and each
of them exports 1 name. Export it as default to cut down on source code.

We've had Filmstrip & LargeVideo React Components on mobile/React Native
from the start. We didn't have them on Web (because the rewrite in React
is not complete yet). However, that led to differences in the React
Component Conference on Web and mobile. In an effort to get closer to
merging the React Component Conference on Web and mobile, introduce the
React Components Filmstrip & LargeVideo on Web even if a minimal
render-only form at this time.

Until we make a decision on access modifier hints and adopt a respective
coding style, consistency is king.

As an intermediate step on the path to merging jitsi-meet and
jitsi-meet-react, import the whole source code of jitsi-meet-react as it
stands at
2f23d98424
i.e. the lastest master at the time of this import. No modifications are
applied to the imported source code in order to preserve a complete
snapshot of it in the repository of jitsi-meet and, thus, facilitate
comparison later on. Consequently, the source code of jitsi-meet and/or
jitsi-meet-react may not work. For example, jitsi-meet's jshint may be
unable to parse jitsi-meet-react's source code.