spike: expose libdatachannel media packetizer chain via Track

Track.setPacketizer(kind, ssrc, pt, clockRate, ...) builds the same
media-handler chain node-datachannel does for @dank074:
  RtpPacketizer (Opus | H264 | H265 | AV1) → RtcpSrReporter →
  RtcpNackResponder → PacingHandler(25Mbps, 1ms) for video
Track.sendFrame(encodedFrame) packetizes into RTP; addTimestamp(delta)
advances the RTP timestamp (node-datachannel contract).

Verified test-packetizer.js: two peers connected over tracks, real opus
frames + AnnexB H264 (SPS/PPS/IDR) flow through the chain without crash.
This removes the need for a JS RTP packetizer entirely — libdatachannel
0.24 has the full media stack built in.
This commit is contained in:
asepharyana
2026-08-11 14:57:04 +07:00
parent 4f06c30c05
commit a1a6d8b418
2 changed files with 156 additions and 2 deletions
@@ -130,7 +130,9 @@ class TrackWrap : public Napi::ObjectWrap<TrackWrap> {
InstanceMethod("send", &TrackWrap::Send),
InstanceMethod("isOpen", &TrackWrap::IsOpen),
InstanceMethod("close", &TrackWrap::Close),
InstanceMethod("onStateChange", &TrackWrap::OnStateChange),
InstanceMethod("setPacketizer", &TrackWrap::SetPacketizer),
InstanceMethod("sendFrame", &TrackWrap::SendFrame),
InstanceMethod("addTimestamp", &TrackWrap::AddTimestamp),
});
trackConstructor = Napi::Persistent(func);
return func;
@@ -151,6 +153,7 @@ class TrackWrap : public Napi::ObjectWrap<TrackWrap> {
private:
static FunctionReference trackConstructor;
std::shared_ptr<rtc::Track> track_;
std::shared_ptr<rtc::RtpPacketizationConfig> rtpConfig_;
void Send(const Napi::CallbackInfo& info) {
Buffer<uint8_t> buf = info[0].As<Buffer<uint8_t>>();
@@ -164,6 +167,78 @@ class TrackWrap : public Napi::ObjectWrap<TrackWrap> {
}
}
// setPacketizer(kind, ssrc, payloadType, clockRate, playoutDelayId,
// playoutDelayMin, playoutDelayMax)
// kind: "audio" | "h264" | "h265" | "av1"
// Builds the media-handler chain (packetizer → RTCP SR → NACK → pacing for
// video) exactly like @dank074's WebRtcWrapper does via node-datachannel.
void SetPacketizer(const Napi::CallbackInfo& info) {
Napi::Env env = info.Env();
if (!track_) throw Error::New(env, "track closed");
std::string kind = info[0].As<String>().Utf8Value();
uint32_t ssrc = info[1].As<Number>().Uint32Value();
uint8_t pt = (uint8_t)info[2].As<Number>().Uint32Value();
uint32_t clockRate = info[3].As<Number>().Uint32Value();
uint8_t playoutDelayId = (uint8_t)info[4].As<Number>().Uint32Value();
uint16_t playoutDelayMin = (uint16_t)info[5].As<Number>().Uint32Value();
uint16_t playoutDelayMax = (uint16_t)info[6].As<Number>().Uint32Value();
try {
auto cfg = std::make_shared<rtc::RtpPacketizationConfig>(
ssrc, "", pt, clockRate);
cfg->playoutDelayId = playoutDelayId;
cfg->playoutDelayMin = playoutDelayMin;
cfg->playoutDelayMax = playoutDelayMax;
std::shared_ptr<rtc::MediaHandler> handler;
if (kind == "audio") {
handler = std::make_shared<rtc::OpusRtpPacketizer>(cfg);
} else if (kind == "h264") {
handler = std::make_shared<rtc::H264RtpPacketizer>(
rtc::NalUnit::Separator::StartSequence, cfg);
} else if (kind == "h265") {
handler = std::make_shared<rtc::H265RtpPacketizer>(
rtc::NalUnit::Separator::StartSequence, cfg);
} else if (kind == "av1") {
handler = std::make_shared<rtc::AV1RtpPacketizer>(
rtc::AV1RtpPacketizer::Packetization::Obu, cfg);
} else {
throw std::runtime_error("unknown packetizer kind: " + kind);
}
handler->addToChain(std::make_shared<rtc::RtcpSrReporter>(cfg));
handler->addToChain(std::make_shared<rtc::RtcpNackResponder>());
if (kind != "audio") {
handler->addToChain(std::make_shared<rtc::PacingHandler>(
25.0 * 1000 * 1000, std::chrono::milliseconds(1)));
}
track_->setMediaHandler(handler);
rtpConfig_ = cfg;
} catch (const std::exception& e) {
fprintf(stderr, "[binding] setPacketizer THREW: %s\n", e.what());
throw Error::New(env, e.what());
}
}
// sendFrame(buffer) — sends an ENCODED frame (AnnexB H264 / raw opus /
// OBU AV1). The media-handler chain packetizes it into RTP.
void SendFrame(const Napi::CallbackInfo& info) {
Buffer<uint8_t> buf = info[0].As<Buffer<uint8_t>>();
if (!track_) return;
rtc::binary data(buf.Length());
for (size_t i = 0; i < buf.Length(); i++) data[i] = (std::byte)buf[i];
try {
track_->send(data);
} catch (const std::exception& e) {
fprintf(stderr, "[binding] track.sendFrame THREW: %s\n", e.what());
}
}
// addTimestamp(delta) — advances the packetizer RTP timestamp by delta
// (clock-rate units). Called by JS after each frame, matching the
// node-datachannel contract (WebRtcWrapper does the same increment).
void AddTimestamp(const Napi::CallbackInfo& info) {
uint32_t delta = info[0].As<Number>().Uint32Value();
if (rtpConfig_) rtpConfig_->timestamp += delta;
}
Napi::Value IsOpen(const Napi::CallbackInfo& info) {
bool open = track_ && track_->isOpen();
return Boolean::New(info.Env(), open);
@@ -178,7 +253,6 @@ class TrackWrap : public Napi::ObjectWrap<TrackWrap> {
(void)info;
}
};
class PeerConnectionWrap : public Napi::ObjectWrap<PeerConnectionWrap> {
public:
static Function Init(Napi::Env env) {
@@ -0,0 +1,80 @@
// Verify setPacketizer + sendFrame: two peers connect, audio+video tracks
// packetize real encoded frames (opus + AnnexB H264), RTP flows without crash.
"use strict";
const { PeerConnection } = require("./build/Release/datachannel_min.node");
function sleep(ms) { return new Promise((r) => setTimeout(r, ms)); }
async function main() {
const pcA = new PeerConnection({ iceServers: [] });
const pcB = new PeerConnection({ iceServers: [] });
const aAudio = pcA.addTrack("0", "audio");
const aVideo = pcA.addTrack("1", "video");
pcB.addTrack("0", "audio");
pcB.addTrack("1", "video");
let states = { a: "", b: "" };
pcA.onStateChange((s) => (states.a = s));
pcB.onStateChange((s) => (states.b = s));
// A: offer (createDataChannel not needed — tracks trigger negotiation)
const offer = await pcA.createOffer();
pcB.setRemoteDescription(offer, "offer");
const answer = await pcB.createAnswer(offer);
pcA.setRemoteDescription(answer, "answer");
// Wait for connected
for (let i = 0; i < 50; i++) {
if (states.a === "connected" && states.b === "connected") break;
await sleep(100);
}
console.log("[pkt] states:", states.a, states.b);
if (states.a !== "connected" || states.b !== "connected") {
console.log("PKT TEST FAILED: not connected");
process.exit(1);
}
// Setup packetizers on A (sender)
aAudio.setPacketizer("audio", 1234, 120, 48000, 5, 0, 1);
aVideo.setPacketizer("h264", 5678, 101, 90000, 5, 0, 10);
// Fake opus frame (20ms @48kHz stereo — payload can be any bytes)
const opusFrame = Buffer.alloc(160);
for (let i = 0; i < 160; i++) opusFrame[i] = i & 0xff;
// Fake AnnexB H264 frame: SPS + PPS + IDR slice
const sps = Buffer.from([0x00, 0x00, 0x00, 0x01, 0x67, 0x42, 0xc0, 0x1e, 0xd9, 0x01, 0x40, 0x7e]);
const pps = Buffer.from([0x00, 0x00, 0x00, 0x01, 0x68, 0xce, 0x3c, 0x80]);
const idr = Buffer.from([0x00, 0x00, 0x00, 0x01, 0x65, 0x88, 0x84, 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07]);
const h264Frame = Buffer.concat([sps, pps, idr]);
// Send 10 audio frames (20ms each) + 3 video frames (33ms each)
for (let i = 0; i < 10; i++) {
aAudio.sendFrame(opusFrame);
aAudio.addTimestamp(960); // 20ms @ 48kHz
}
for (let i = 0; i < 3; i++) {
aVideo.sendFrame(h264Frame);
aVideo.addTimestamp(3000); // 33ms @ 90kHz
}
await sleep(500);
console.log("[pkt] after send: states:", states.a, states.b);
console.log("[pkt] audio track open:", aAudio.isOpen(), "| video track open:", aVideo.isOpen());
const ok = states.a === "connected" && aAudio.isOpen() && aVideo.isOpen();
console.log(ok ? "PKT TEST PASSED" : "PKT TEST FAILED");
pcA.close();
pcB.close();
process.exit(ok ? 0 : 1);
}
main().catch((e) => {
console.error("[pkt] FAILED:", e.message);
process.exit(1);
});
setTimeout(() => {
console.error("[pkt] TIMEOUT");
process.exit(1);
}, 25000);