* fix(migration): reject the data channel to restart it

Starting on chrome 63, an error occurs when renegotiating
with the new bridge on bridge migration when the SDP sections
do not match, which occurs when removing the data channel
section. Not doing the double renegotiate prevents the data
channel from being reopened. The way around this, while still
avoing the error, is to reject the data channel section instead
of removing it to trigger a new data channel.

* squash: reword comments

* Support layer suspension

Add support for a message which notifies the endpoint whether or not it
is selected (meaning its HD stream is in use).  If it is not
selected and enableLayerSuspension is set to true then it will impose a
bandwidth limit in the SDP to suspend sending the higher layers.

* only add the IS_SELECTED_CHANGED listener in JingleSessionPC if layer
suspension is enabled

this prevents doing a local o/a when we don't need it

When switching bridges, removing the "data" section from the SDP
and doing a double offer-answer results in an error starting on
Chrome 63. So on 63 and up, do a single off-answer without
removing the "data" section.

This PR exposes the functionality that's already built-in the
TraceablePeerConnection that has it gather stats from the wrapped
PeerConnection.

* wip: initial version of the new AnalyticsAdapter.

* ref: Restructures the ICE duration and state change events.

* ref: Restructures the JitsiLocalTrack events.

* ref: Restructures the TTFM events.

* ref: Updates the user feedback event.

* ref: Restructures the _CONNECTION_TIMES_ and TTFM events.

* ref: Restructures the BRIDGE_DOWN and NO_DATA_FROM_SOURCE events.

* ref: Restructures the FOCUS_LEFT event.

* ref: Restructures the DATA_CHANNEL_OPEN event.

* ref: Removes the ICE_FAILED event (it is a duplicate of a state change event).

* ref: Restructures the device list events.

Uses one event per device, since the new format does not allow non-atomic attributes.

* fix: Does not obey "unmute" commands from the focus.

* ref: Restructures the "remotely muted" event.

* ref: Restructures the CONFERENCE_ERROR events.

* ref: Removes the CONNECTION_INTERRUPTED event

We can use ICE_STATE_CHANGED instead.

* ref: Renames isreconnect to isReconnect.

* ref: Removes the CONNECTION_RESTORED event. Use ICE state changes instead.

* ref: Restructures the p2p events.

* ref: Restructures the jingle events.

* ref: Restructures the RTP statistics event.

* ref: Restructures the CONNECTION_FAILED and DISCONNECTED events.

* ref: Restructures the getUserMedia analytics events.

* ref: Cleans up AnalyticsEvents and restructures some of the events.

* fix: Adds error logs to the analytics adapter.

* ref: Refactor Statistics.sendEventToAll

Renames to sendEventAndLog, supports the object-based API, uses the
function where appropriate.

* fix: Addresses PR feedback.

* fix: Addresses Lyubomir's feedback.

* ref: Remove unused functions, adds documentation.

* feat: Adds a Statistics.sendAnalytics shortcut.

* ref: Uses the conference name as the default containerId.

* fix: Adrdesses Lenny's feedback.

* fix: Addresses more feedback.

* fix: Uses 'operational' as the default event type.

* doc: Updates the documentation.

* fix: Fixes adding of permanent properties.

* ref: Uses consistent naming for events' attributes.

Uses "_" as a separator instead of camel case or ".".

* feat: Adds the conference name as a permanent property automatically.

* ref: Don't expose Setting.machineId.

* fix: Adds a "p2p" attribute to jingle events.

* ref: Uses "action" instead of "name".

* ref: Uses underscore in events' attribute names.

* ref: Logs a message to the logger/console

instead of callstats in sendAnalyticsAndLog().

* ref: Simplifies the logic for handling an incoming jingle session-initiate.

* fix: Don't redundantly log cross region

information under a field name called "label".

* cleanup: Simplifies code. Adds the userAgent as a permanent property

for statistics (so that the client doesn't have to).

* ref: Names the parameter which specifies the name of the event "eventName".

* ref: Extracts event names to AnalyticsEvents.

* ref: Exports and imports constants individually.

* fix: Fixes CONNECTION_TIMES event names.

* ref: Arranges constants alphabetically.

* ref: Adds line breaks.

* revert: Reverts be665cbff7.

* ref: Renames "peerjid".

* ref: Refactors the initialization of a peer connection.

* feat: Re-implements the A/B test for the "suspend video" feature.

* squash: Deep copy.

* ref: Renames forceSuspendVideo to abtestSuspendVideo.

Do not log whole objects on Jingle error, as these may cause trouble on
iOS react-native.

This is performed by stripping all traces of H.264 from the local SDP before
passing it to `setLocalDescription`.

ESLint 4.8.0 discovers a lot of error related to formatting. While I
tried to fix as many of them as possible, a portion of them actually go
against our coding style. In such a case, I've disabled the indent rule
which effectively leaves it as it was before ESLint 4.8.0.

The 'setMutedInProgress' flag is unreliable and it can lead to weird
situations when mute operation is in progress, but the removal from
JingleSessionPC is waiting on the queue. In such case LocalSdpMunger
will fake SDP even if the track is in the PeerConnection which may
confuse some parts of the SDP transformation chain.

For example RtxModifier will not attempt to inject Rtx group description
if it sees that the SSRC are already there. But it can happen that even
though the SSRCs are there they do not contain valid track ID, because
the track has changed.

The LocalSdpMunger is supposed to fake the SDP only when the video
MediaStream is not in the PeerConnection. So this commit implements just
that: a way to tell if JitsiLocalTrack's stream is currently in
the PeerConnection (added through TraceablePeerConnection).

Moves the call to 'setLocalDescription' from 'sendSessionInitiate' to
'invite' as it was easy to overlook.

In case when the answer is being set for the first time, full sRD/sLD
cycle is required to have the local description updated and SSRCs
synchronized correctly. Otherwise SSRCs for streams added after invite,
but before the answer was accepted will not be detected. The reason for
that is that renegotiate can not be called when adding tracks and they
will not be reflected in the local SDP.

The 'ondatachannel' even listener must be set as soon as
the TraceablePeerConnection is created and before the offer is accepted.
We've observed situations where the ondatachannel event was missed,
because the listener is bound too late from the JingleSessionPC
'acceptOffer' success callback.

* add support for signaling simulcast for unified plan

1) munge the incoming offer to advertise support for receiving simulcast in unified plan
2) add 3 simulcast encodings via rtp sender
3) inject an ssrc-group line, even when using rids for simulcast (jicofo will rely on this)

* add rid information to the session-accept jingle

* address lenny's feedback

* make firefox simulcast configurable

* fix missing comma

Due to it being ran asyncronously, it's possible a replaceTrack operation is
scheduled while there is a valid PC, but by the time it runs was closed.

Accommodate to this situation by pretending everything is just peachy.

Also add a preferH264 option for P2P.

Some browsers may not support data channels (hi there, Edge!) and sometimes it
may not be desirable for other reasons.

* ref(JSPC): simplify SSRC owner in P2P

There's no need for any extra extensions for SSRCs owner signalling in
P2P, because it's always the remote peer who owns them.

This also fixes a problem where no SSRC owner was added for 'source-add'
in P2P (for JVB conference Jicofo adds that).

* fix(TPC): always advertise 'sendrecv'

Our media direction is only ever updated on the remote side with
the initial offer (or answer). Because of that we want to advertise
'sendrecv' even if we start with no video (or audio) track.

It is OK to adjust this direction in the localDescription getter,
because it's adjusted again in the setter to the correct value based on
local tracks, so the SDP transformation chain still works fine.

This code would crash on react-native if 'sdpMid' is not defined at all.
Still works as expected with an empty string though.

Adds session converted to string to the error object.

Do not log errors for 'item-not-found', after jingle session was
terminated.

When the lastN is set to 0 the P2P session will notify the remote peer
to stop sending video.

Creating SDP instance was unnecessary.

Will actively terminate P2P session by the responder (not moderator) in
order to shutdown P2P in case of eventual initiator's crash. Otherwise
the responder will stay in P2P for too long (until P2P ICE fails).

Prevents from printing Jingle 'session-terminate' error response in case
both responder and initiator terminates their sessions simultaneously
(gracefully). In that case 'item-not-found' error is returned by each
party, because the session is removed immediately from the memory on
termination (see strophe.jingle.js).

If for any reason invite for the JVB JingleSession is delayed and
arrives after the P2P connection has been established then
the media transfer needs to be disabled after the offer is accepted.

Invite must be executed on the queue to avoid strange things happening
on the beginning of the call. For example when the local tracks are
added just after the invite was called.

Move the JingleSessionPC to ACTIVE state, as soon as the first
_renegotiate is executed in PENDING state.

* feat(JSPC): ICE establishment time

Will report total ICE establishment time under
'ice.initiator.establishmentDuration' and
'ice.responder.establishmentDuration' ('p2p.' prefix added for P2P).
It's the amount of time between the time when either checking or
gathering started (whichever starts first) and when ICE entered
'connected' for the first time.

* fix(JSPC): simplify and rename event

* ref: store SSRCs as a number

Converts all the places where SSRCs where stored as string to use
numbers.

* doc(RTPStatsCollector): getNonNegativeStat

Fixes invalid description about returning NaN.

* ref(JitsiConf...EventManager): simplify for..of

* ref(JitsiRemoteTrack): throw TypeError

Will throw a TypeError when 'ssrc' is not a number.

* fix(RTPStatsCollector): invalid reference

* doc(RTPStatsCollector): getNonNegativeStat private

* ref(RTPStatsCollector): simplify for..of

* fix(SSRCs): check for negative value

Will not accept negative SSRCs, since those are supposed to be unsigned.

Will emit analytics events for ICE gathering and ICE checks duration,
separately for initiator/responder and p2p/jvb connections. Initiator
and responder have to be separated, because the flow and the values have
significant differences.

XMPPEvents.CONNECTION_ESTABLISHED is emitted outside of 'is stable'
condition, because for the JVB connection the signalling state is often
not in 'stable' ('have-remote-offer') state when ICE goes to
'connected'.

* fix(JingleSessionPC): do not log whole object
* fix(JitsiConference): fix a crash

The code will crash if there's neither P2P nor JVB session yet.

ICE connection state analytics for the JVB connection should not be
mixed up with the ones for the P2P connection.

* ref(JSPC): rollback doRenegotiate

Modify the code to the old strategy without shared 'doRenegotiate'
method.

* ref(JSPC): add/remove duplication

Removes duplication between add and remove remote stream methods.

* fix(JSPC): remove Timeout

Removes wait timeout for remote stream added/removed. It should not be
necessary given that the task executes on the modification queue and
the initial offer/answer should execute before
'source-add'/'source-remove'. Jingle 'session-invite'/'session-accept'
is sent, before any other notifications.

* feat(JSPC): verify SSRC changes

Will print an error if there was change to local SSRCs where it should
not happen (video mute on browsers where video stream is disposed on
mute).

* fix(JSPC): not always renegotiate

When adding/removing tracks as mute/unmute it only makes sense to
renegotiate if the initial offer/answer cycle has already been executed.

* ref(JSPC): remove duplication

Removes duplication around add/remove as unmute/mute.

* ref(JingleSessionPC): add local tracks with offer/answer

Refactor the current code to add local tracks together with initial
offer/answer to make this atomic/single operation on
the modificationQueue.

This is required to be able to get rid of 'delayedIceCandidates' list
and to execute 'addIceCandidate' task on the queue. If local track
addition is not bundled with initial offer it will often happen that ICE
candidates are queued, before the offer/answer which is queued only once
the local tracks task is done.

* ref(JSPC): use queue for ICE candidates

Refactors the code to get rid of 'delayedIceCandidates' buffer and
use the modification queue to synchronise with the initial offer/answer.

* doc(JingleSessionPC): improve docs

* ref(p2p): use SDP 'inactive' for JVB

This commit gets rid of detach/attach logic and
replaces it with SDP media direction modification.
Now after switching to P2P instead of detaching local
tracks from the JVB peerconnection only the media direction
will be changed to 'inactive'. This will suspend media
transfer on the JVB connection.

It's meant to mitigate Chrome issue where it would randomly
choose to stop sending audio stream, after we modify it's
local SSRC.

* ref(SdpConsistency): cleanup 'recvonly'

Checking on 'recvonly' is no longer reliable way for detecting
whether video media is recvonly, because it can be set to
'inactive' at any point.

Added a check to make sure that the recvonly SSRC is not generated
more than once from '_createOfferOrAnswer'.

* log TPC instance

Logs the TraceablePeerConnection from LocalSdpMunger and
SdpConsistency as part of log messages. Given that there can be
2 TPCs at the same time it was hard to tell for which connection
a log message was printed.

* fix(SdpConsistency): depend on 'recvonly' direction

When createAnswer/createOffer returns SDP it will contain 'recvonly'
direction to reflect current media stream state even though we set
it to 'sendrecv' previously. Using 'hasAnyTracksOfType(VIDEO)' can
not be used to reliably detect 'recvonly' direction when doing video
mute, because muted video track is still in the TPC's map.

* doc(LocalSdpMunger): update description

LocalSdpMunger is currently used only for muted local video tracks.

* fix(P2P): enable P2P on Firefox

After 'detach/attach' is gone it seems that P2P works fine with Firefox.

* ref(TPC): simplify expression

* ref(SdpConsistency): do not pass whole TPC

There's no need to pass whole TPC instance if the only thing needed is
a logging prefix.

* ref(RTC): store remote tracks in peer TPC

In order to implement P2P <-> JVB connection switching we need to
be able to associate remote tracks with the TraceablePeerConnections.

* feat(ChatRoom): multiple presence handlers

Add support for more than 1 presence handler per tag name.

* feat(JitsiLocalTrack): update stored MSID

* ref(stats): add peer connection arg to BYTE_SENT_STATS

Required to store local SSRCs in TraceablePeerConnection.

* ref: change local SSRCs strategy

* fix: generate recvonly SSRC if 0 video tracks

Video SSRC has to be generated for the recvonly stream if there are no
video tracks in the PeerConnection.

* feat: add "attach" and "detach" methods

* feat(jitsi tracks): improve logging

Adds toString methods and improve log messages around local and remote
tracks.

* ref(modify SSRCs): optimisations + fixes

- adds _doRenegotiate to JingleSessionPC that wraps some of
  the duplicated logic
- fixes problems with attach/detach
- renames methods to reflect what that they really do (operate on
  JitsiTrack rather than streams)

* ref(JingleSessionPC): remove duplication

Extracts common code for the 'modificationQueue' execution

* ref(VideoMuteSdpHack): rename, add docs, fix minor

Renames, adds docs and moves 'modified' flag and media direction
modification.

* ref(TPC): add 'isSimulcastOn'

* ref(MungeLocalSdp): move to RTC module

* ref: move "ufrag" events to the RTC module

* ref(JitsiConference): use promises for mute

* feat(XMPPEvents): add CONNECTION_ESTABLISHED

* feat: add peer to peer

* fix(P2P): deal with everyone's a moderator + fixes

* feat(P2P): implement "backToP2PDelay"

* fix(TPC): crash on FF accessing LD/RD

Firefox return null/undefined for localDescription/remoteDescription
objects if they have not been set yet, while Chrome does return empty
object instead. This commit makes the behaviour consistent by making
sure that at least empty object is returned for all browsers.

* fix(TPC): replace isFirefox with feature

* fix(JSPC): fix renegotiate crash on FF

FF does not allow to call 'createAnswer' in 'have-local-offer' state

* fix(JSPC): fix addIceCandidate crash on FF

* doc(JitsiConference): fix outdated comment

To be squashed with "ref(ChatRoom): remove unnecessary JingleSessionPC dependency"

* style(JitsiConference): rename arg to "jingleSession"

* feat(stats): add 'p2p' to 'transport'

The new p2p field will inform whether the transport comes from the peer
to peer type of connection or not.

* doc(TPC): describe local maps

* fix(P2P): multiplex between JVB and P2P ICE status

Will make sure that when in P2P mode the conference will be updated
with the ICE state coming from P2P and when in the JVB mode will get
the JVB one.

* doc(TPC): fixes docs and adds FIXME

* ref: use 'doesVideoMuteByStreamRemove'

* feat(P2P): stop P2P when ICE enters FAILED

The conference will switch back to the JVB connection when P2P
connection breaks (ICE enters failed state).

* feat(P2P): "connectivity-error" for ICE failed

Will use "connectivity-error" reason element name when ending P2P
session due to ICE failure.

* feat(xmpp): make P2P Stun servers configurable

STUN servers used in the P2P connection can be configured through
"p2pStunServers" option.

* ref(JitsiConference): use 'getActivePeerConnection'

* fix(P2P): re-create 'dtmfManager'

* ref(P2P): deal with ICE "completed" state

* ref(RTC): rename "owner" to "ownerEndpointId"

* fix(MungeLocalSdp): fix directions

* ref(ParticipantConnectionStatus): use for..of and () =>

* remove double 'l'

* ref: fix ESLint errors

* fix(MungeLocalSdp): adopt to new SdpTransformerUtil

* ref(MungeLocalSdp): use for .. of

* ref(SdpTransformUtil): remove "forEachSSRCAttr"

* fix(SDPDiffer): fix invalid "arrayEquals" call

* doc(MungeLocalSdp): add fixme

* fix(P2PEnabledConference): JVB tracks not added

* ref(JitsiConference): doc + rename mute methods

* ref(JitsiConference): adjust log level

* fix(JitsiConference): remove invalid eslint comments

Some mistake during rebase merge

* doc(JitsiConference): add FIXME

* ref(JitsiConferenceEventManager): stick to "tpc"

* ref(JitsiLocalTrack): use Set for "peerConnections"

* ref(JitsiLocalTrack): simplify expression

* ref(MungeLocalSdp): style + doc fixes

* ref: rename MungeLocalSdp to LocalSdpMunger

* ref(ParticipantConn..Status): rename method

* ref(SignalingLayerImpl): use Map and =>

* fix(strophe.jingle.js): minor style fixes + rename

* doc(XMPPEvents): typo

* doc(P2PEnabledConference): typo and style

* ref(P2PEnabledConference): rename methods

* ref(P2PEnabledConference): do not use "window"

* fix(P2PEnabledConference): cleanup deferred task

* ref(TPC): make options the last arg

* ref(TPC): use Map

* ref(TPC): syntax and other fixes...

* doc(ChatRoom): remove comment

* ref: remove P2PEnabledConference

* fix: remove JSUtil.js

* ref(LocalSdpMunger): re-use 'RtxModifier'

Reuses RtxModifier for injecting local RTX SSRCs as part of
the LocalSdpMunger logic.

* doc(LocalSdpMunger): remove confusing FIXME

* fix(TPC): setLocalDescription for FF

* fix(LocalSdpMunger): crash on react-native

* fix(JingleSessionPC): no events when ended

The instance once terminated should not emit connection state events.

* fix(P2P): do not start P2P on react-native

* fix: log meaningful error

Prior to this change you would see something like:
JitsiConference <error>: null

* fix(JingleSessionPC): no IQs once ended

* fix(JingleSessionPC): Jingle error logging

* fix: arguments order

* fix: make audio SSRC consistent

Audio SSRC needs to stay consistent between detach and attach operations
in order to avoid source-remove/source-add.

* fix(P2P): disable P2P on FF

There are problems with going back from P2P to JVB in FireFox. Other
participants will not see FF video. Looks like something related to
detach/attach.

* fix(JitsiConference): attach local tracks

Local tracks should be attached back to the JVB connection only
if the P2P was established.

* ref(JitsiConference): PR review fixes

ref(JitsiConference): else if

ref(JitsiConference): use getter

doc(JitsiConference): add comment

style(JitsiConference): remove extra line

log(JitsiConference): misleading msg

ref(JitsiConference): rename method

* ref(RTC): del _iteratePeerConnections

* ref: move getUfrag to SDPUtil

* fix(LocalSdpMunger): docs and if check

* fix(TPC): docs and typo

* ref(JingleSessionPC): PR review fixes

ref(JingleSessionPC): rename 'candidates'

ref(JitsiConference): remove extra check

ref(JitsiConference): rename isP2PEstablished

ref(JitsiConference): rename field (typo)

* doc(JitsiConferenceEventManager): typo

* ref(JitsiLocalTrack): rename var

* ref(JitsiConference): PR review fixes

ref(JitsiConference): rename var

doc(JitsiConference): add comment

doc(JitsiConference): add comment

doc(JitsiConference): fix comment

ref(JitsiConference): rename listener

ref(JitsiConference): rename var

* doc(RTC): remove duplicated arg description

doc(RTC): fill docs

* doc(SignalingLayerImpl): remove fixed FIXME

* ref(strophe.jingle.js): remove comment and break line

* style(TPC): formatting

doc(TPC): add FIXME

ref(TPC): remove unused code

doc(TPC): add docs

* doc(JingleSessionPC): mark "send" methods private

style(JingleSessionPC): extra lines