Make sure participants in the redux store have updated names.
This will be needed for showing avatars with user initials.

* ref(avatars): remove Avatar.js

- Rely on redux getting updated with new participant state
and any calls to getAvatarURL passing in the redux
participant state. This way the state within Avatar.js can
be removed.
- Clean up methods on UI.js. Because all state is in the
store, separate methods for updating the avatar aren't as
necessary. Instead centralize accessing of the avatar for
components outside of redux and centralize the call to
update avatars for non-react components.
- Controversial: cache a participant's avatarURL on the
participant state. Currently the participant's avatarURL
that is generated without jwt (which sets the avatarURL directly)
is not cached. Without cache, there can be many redundant
calls to APP.API.notifyAvatarChanged.

* Leverage middleware timing to diff avatars

One alternative implementation is to leverage middleware's
ability to intercept updates before and after redux has
upated and then compare avatarURLs.

* kill UI.getAvatarUrl

* profile button sets its own avatar url (solves update timing)

* remove calls to updating avatar outside of middleware

* update UI.js doc

* remove left over logic from initial implementation

* try to move local user fallback into selector func

* default to id 'local' in selector

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.

It's designed to cover a container and give it a "tint" by using a color and
opacity.

They will be stored in redux and the PageReloadOverlay will be displayed.

Note that this commit also introduces a subtle (and yet important!) change:
the location URL is now always set, regardless of the configuration loading or
not. This is needed in order for the retry logic to pick it up.

It's not supposed to go on top of everything, like an error would. It's tied to
a conference, so render it outside of the OverlayContainer.

* Removes unused config logic.

* Whitelists config options that can be overridden using the URL.

* Recorder login with credentials, not supported by externalconnect.

Jibri uses xmpp credentials to login, which is not supported by externalconnect, so we want to skip it till that is supported.

* Whitelist only config.js

* Extracts whitelisting in separate function.

* ref(analytics): centralize all event names

* squash: fix typo and alpha ordering

* squash: rename file to AnalyticsEvents to parallel lib-jitsi-meet

The goal is to reduce usage on atlassian/aui. New components
have been created to display the settings panel. Language
selection will reach into i18n for state whereas moderator
options will keep state in redux.

Properly handle errors while connecting or joining a conference. Prior to this
patch, only errors on established conferences / connections were saved to the
redux store.

75bf7638b3 introduced this regression, state must
be assigned as an object, even though one would think it's automagically
initialized to an object. Oh well!

Adds more accessibility labels required for mobile automated testing.

These modification are not necessarily directly related to the
containing PR, I merely saw them while reviewing the containing PR.

Do the selection in mapStateToProps so the container itself doesn't need to
receive all the props that each overlay needs.

Each overlay is responsible for fetching their own props and for providing a
"needsDisplay" static method wich will be called with the full redux state and
should return true if the overlay needs displaying.

Also eliminate duplicated state keeping: the connection and conference error
states can be fetched from their respective base features.

Initializing UI features, like keyboard shortcuts, by chaining
onto APP.conference.init is not safe because init can fail,
skipping the initializing of UI features. This can happen when
the room is locked and then a failure event is dispatched into
middleware. I couldn't find a place to properly chain onto
in the APP.conference.init promise chain, primarily due
to the flow continued within middleware, so instead I
leveraged an existing listener for CONFERENCE_JOINED.

* Adds initial documentation for sipgw jibri.

Also explains enabling the people search service and the request/response that are made around sipgw jibri service.

* Fixes add people dialog to invite users and rooms.

No invitation is sent when there is nobody to invite.

* Reuse some recording strings, by using arguments.

* Make sure web also dispatches CONFERENCE_WILL_JOIN.

* Introduces new feature videosipgw.

* Fixes lint errors.

* Renames methods to use people, chatRooms and videoRooms.

* Updates to latest lib-jitsi-meet (dc3397b18b).

* fix(notifications): throttle and batch join notifications

Instead of directly calling to show a join notification,
go through a specific method. This method will queue
names for display while a throttled function pulls
the names and shows a notification.

* squash: remove unused translation key

* squash: use default display name

* squash: move into participant actions

Refs: https://github.com/jitsi/lib-jitsi-meet/pull/648

It's possible for a track to be disposed but still on the redux store, before
the reducer removed it.

Prepares for the latest eslint & flow-related npm packages which cause
these errors.

Rearrange the ToolbarButtons in the secondary Toolbar in order to mostly
group the media-related ones such as the AudioRouteButton, the
switchCamera button, and the audio-only mode button.

Due to the difference in nature, the iOS and Android implementations are
completely different:

iOS: MPVolumeView is used, which allows us to place a button which will launch a
native route picker provided by iOS itself. This view is different depending on
the iOS version, with the iOS 11 version being more complete.

Android: A completely custom component is used, which displays a bottom sheet
with the device categories, not devices individually. This is akin to the sheet
in the builtin dialer.

It emulates Android's BottomSheet in pure JavaScript. It's implemented as
another Dialog, so it can be used instead of one.

The implementation only supports text options with an associated icon, and an
optional 'selected' marker.

We're already using the notion of _WILL_ in redux action types and
there's currently no compelling reason to introduce _BEGIN_ as well.

While reviewing "[PREVIEW|RN]: Handle getUserMedia in progress" I
discovered JSDoc comments which could be improved. They are not
necessarily 100% related to the PR.

This commit adds extra actions/Redux state to be able to deal with
the GUM operation being in progress. There will be early local track
stub in the Redux state for any a local track for which GUM has been
called, but not completed yet.

Local track is considered valid only after TRACK_ADDED event when it
will have JitsiLocalTrack instance set.

That standalone ButtonGroup package has been deprecated.
The deprecation warning says to use the ButtonGroup component
from the Button package.

* feat(audio-only): be able to lock a browser into capturing audio only

* squash: try to make string more clear about audio only support

* squash: final strings

* fix(remote-mute): Moves remote participant mute to react

* fix(translation): Removes unused strings

* [squash] Addressing comments

Now that we no longer hide the filmstrip it is fine to return null
instead of trying to hide with some tricks.

Adds the ability to detect app area's aspect ratio on react-native
through the features/base/aspect-ratio.

Makes conference, filmstrip and toolbox react to the aspect ratio
changes and display filmstrip on the shorter side of the screen.