b26f138699
ci / rust (push) Has been cancelled
Both directions of the audio plane, on CoreAudio's built-in Opus codec
(kAudioFormatOpus — no bundled libopus; OpusCodec.swift, round trip unit-tested):
- Playback: a drain thread pulls nextAudio() packets, decodes, and writes a priming
jitter ring feeding an AVAudioSourceNode (~20 ms prefill, adaptive to the device's
render quantum so large-buffer devices don't oscillate prime/dropout; a high-water
clamp sheds stall backlog so one network hiccup can't permanently lag audio behind
video; underrun re-primes — one dip, not sustained crackle).
- Mic: a second engine taps the input device, resamples to 48 kHz stereo, Opus-encodes
20 ms chunks and sendMic()s them into the host's virtual PipeWire source. Permission
via AVCaptureDevice (NSMicrophoneUsageDescription added to the Xcode target).
- Settings: Speaker + Microphone pickers (CoreAudio HAL enumeration, persisted by
device UID — "System default" leaves the engine unpinned so it follows macOS device
changes) and a "Send microphone" toggle (default on). Applies from the next session.
- Audio starts with streaming, never during the trust prompt (no host sound — and no
mic uplink — before the user trusted the host); teardown stops audio before close().
Adversarial-review fixes baked in: stop() and the dangling mic-permission callback
share one lock+flag protocol (no hot mic with no owner), the connect-success handler
bails when the attempt was abandoned mid-handshake (no session/mic for a dead window),
SessionAudio gets a deinit backstop (a dropped instance can't pin the connection via
its drain thread), and the render scratch buffer is block-owned (was leaked per
session).
Verified live against the box: remote test decodes 100 host Opus packets to PCM and
the host opens its virtual mic on the first uplinked frame ("punktfunk/1 virtual mic
ready"); on-glass session runs with both engines up.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
84 lines
3.7 KiB
Swift
84 lines
3.7 KiB
Swift
// The Opus codec through CoreAudio (kAudioFormatOpus): a real encode → decode round
|
|
// trip. This is the load-bearing assumption of the whole audio feature (no bundled
|
|
// libopus) — if AVAudioConverter can't handle raw Opus packets, fail HERE, not in the
|
|
// app.
|
|
|
|
import AVFoundation
|
|
import XCTest
|
|
|
|
@testable import PunktfunkKit
|
|
|
|
final class OpusCodecTests: XCTestCase {
|
|
/// Encode a 440 Hz stereo tone, decode it back, and require the result to be
|
|
/// recognizably the same signal (Opus is lossy — check correlation, not bytes).
|
|
func testEncodeDecodeRoundTripPreservesTone() throws {
|
|
let encoder = try OpusEncoder()
|
|
let decoder = try OpusDecoder(framesPerPacket: UInt32(OpusEncoder.framesPerPacket))
|
|
let pcmFormat = encoder.pcmFormat
|
|
|
|
let frames = OpusEncoder.framesPerPacket
|
|
var packets: [Data] = []
|
|
var phase: Float = 0
|
|
let step = 2 * Float.pi * 440 / 48_000
|
|
|
|
// 50 packets = 1 s of tone.
|
|
for _ in 0..<50 {
|
|
let buf = AVAudioPCMBuffer(pcmFormat: pcmFormat, frameCapacity: frames)!
|
|
buf.frameLength = frames
|
|
let p = buf.floatChannelData![0] // interleaved: one plane, L R L R …
|
|
for f in 0..<Int(frames) {
|
|
let s = sin(phase) * 0.5
|
|
phase += step
|
|
p[f * 2] = s
|
|
p[f * 2 + 1] = s
|
|
}
|
|
packets.append(contentsOf: try encoder.encode(buf))
|
|
}
|
|
XCTAssertGreaterThanOrEqual(packets.count, 45, "encoder must emit ~one packet per buffer")
|
|
XCTAssertTrue(packets.allSatisfy { !$0.isEmpty })
|
|
|
|
var decoded: [Float] = []
|
|
let out = AVAudioPCMBuffer(pcmFormat: decoder.pcmFormat, frameCapacity: 5760)!
|
|
for packet in packets {
|
|
let n = try decoder.decode(packet, into: out)
|
|
let p = out.floatChannelData![0]
|
|
for f in 0..<Int(n) {
|
|
decoded.append(p[f * 2]) // left channel
|
|
}
|
|
}
|
|
XCTAssertGreaterThan(decoded.count, 40_000, "~1 s of 48 kHz audio back out")
|
|
|
|
// The decoded signal must contain a strong 440 Hz component: correlate against
|
|
// quadrature reference tones (phase-agnostic), skipping the codec warm-up.
|
|
let skip = 4800
|
|
var inPhase: Float = 0
|
|
var quadrature: Float = 0
|
|
var energy: Float = 0
|
|
for (i, s) in decoded[skip...].enumerated() {
|
|
let t = Float(i) * step
|
|
inPhase += s * sin(t)
|
|
quadrature += s * cos(t)
|
|
energy += s * s
|
|
}
|
|
let n = Float(decoded.count - skip)
|
|
let correlation = (inPhase * inPhase + quadrature * quadrature).squareRoot() / n
|
|
let rms = (energy / n).squareRoot()
|
|
XCTAssertGreaterThan(rms, 0.2, "decoded audio is not silence")
|
|
// A clean sine at amplitude a yields correlation a/2 (≈0.25 here); noise ≈ 0.
|
|
XCTAssertGreaterThan(correlation, 0.15, "440 Hz tone must survive the round trip")
|
|
}
|
|
|
|
/// The host's audio plane is 5 ms (240-frame) packets — make sure a 240-frame
|
|
/// decoder accepts packets that small (encoder-side we can't force 5 ms out of
|
|
/// CoreAudio, so this decodes the 20 ms packets with a mismatched nominal fpp,
|
|
/// which the packet descriptions override).
|
|
func testDecoderHandlesDTXAndOversizedPackets() throws {
|
|
let decoder = try OpusDecoder(framesPerPacket: 240)
|
|
let out = AVAudioPCMBuffer(pcmFormat: decoder.pcmFormat, frameCapacity: 5760)!
|
|
XCTAssertEqual(try decoder.decode(Data(), into: out), 0, "DTX decodes to silence/0")
|
|
XCTAssertThrowsError(
|
|
try decoder.decode(Data(repeating: 0, count: 2000), into: out),
|
|
"oversized packet must throw, not crash")
|
|
}
|
|
}
|