If the Activity is put into the background before the ReactContext is created we
get an NPE here. While the window might be short, it's thechnically possible to
hit this, as our Crashlytics reports show.

The subsystem is set to the bundle ID and the category to "JitsiMeetSDK".

The call-integration middleware relies on it returning it, as iOS does.

Bring back the workaround introduced in afd2aea7
but removed in 21dcc41d. On conference join,
several other actions have already been fired
that try to set the large video participant
and select the participant on the bridge.
The problem is there is no conference during
these actions so the select participant
never fires. Then subsequent actions do not
fire select participant because the large
video participant has not changed.

This commit changes how the SmallVideo.isVideoPlayable method works.

1st we remove the check on the video stream muted field (materialized with the
!this.videoStream.isMuted() guard). This check is redundant as it is
already materialized in the !this.isVideoMuted check (the isVideoMuted
field is updated with the return value of the videoStream.isMuted()
method).

2nd we return false if we're in audio only mode, because it's
(obviously) undesirable to have a playable video when in audio only
mode.

react-emoji-renderer 1.0.0 removed the
thumbsup and thumbsdown aliases.

We try to load the configuration with every room change, even when there is no
room. There is a bad (corner) case: when we have no config cached (first boot or
wiped app data). In such case the user is trapped in an infinite loop because we
require the config to show the welcome page, oh well.

Pretend we have a configuration by creating the most minimal one to at least get
to the welcome page.

Simplifies the code a bit, and we use no lifecycle methods.

Audio streams are automatically played by WebRTC and this won't change, probably
ever. There is no point in having checks and an Audio component which does
nothing.

Fixes: #312

It's not necessary and makes the build faster.

For some reason ART complains about these methods being overrides of package
private ones from Timber.

In iOS 13 if the call is not unmuted when we report it to the system as started,
an action to unmute it is dispatched automagically. Thanks, Apple.

So, delay synchronizing the muted state until the conference is started (after
the join action). This creates a small window for de-synchronization, but it's
very short and it seems unavoidable.

This change is only applied to operating systems built by the fruit company in
Cupertino.

The currently selected values are a bit above the actual sizes, so if a PR
increases the bundle size enough to trigger the failure, it should bump it.
It better have a good reason for it though!

Build as follows to build (production) bundle size stats:

npx webpack -p --progress --analyze-bundle

Then open the report:

npx webpack-bundle-analyzer build/stats.json build/

The direct import sidesteps many chained-effect imports, halving the bundle
size.

There are just a couple of logs in this feature, and it's a standalone bundle,
which would bloat it due to cascaded dependencis.

There are just a couple of logs in this feature, and it's a standalone bundle,
which would bloat it due to cascaded dependencis.

There are just a couple of logs in this feature, and it's included in bundles
like external_api, which would bloat it due to cascaded dependencis.

This is for other applications to use, and it's currently only used for logging
1 line, so use console.error.

In
b53a034aaf (diff-0339cf92cc68bc5981fe6df601316c1c)
I removed this, because RN has updated the builtin JSC version. On the next
release, however, RN introduced a new JS interpreter (Hermes) so JSC is now a RN
dependency. Thus, add the magic spells to publish the AARs to Maven.