Grant Gilliam
c347acbd97
Front-loads the remaining visual adapters per the Signal→Meet→Zoom priority. All three reuse GridCallAnalyzer's coloured-border (saturated) detection path and share the new bottom-left name anchor: - GridCallAnalyzer: generalise nameAtBottom:Bool into a NameAnchor enum (.bottomCenter for Signal's centered footer, .bottomLeft for Meet/Zoom/Teams where the name hugs the tile's bottom-left corner, .center for completeness). tileRect estimates the tile up-and-right of a bottom-left name. - MeetAdapter (Google-blue ring, browser-hosted), ZoomAdapter (green/yellow border), TeamsAdapter (violet ring): coloured-border on, white-border off, bottom-left names. Geometry constants are first-pass pending real fixtures. - AdapterRegistry.adapter(for:) maps CallDetector.DetectedApp → AppAdapter so VisualObserver can be constructed when live visual capture is wired in; unmapped apps degrade to audio-only. Synthetic 4-tile tests: Meet picks each blue-bordered speaker with no adjacent-tile bleed, Zoom picks the green-bordered speaker, and Signal's white-only detector correctly ignores a coloured border. 18/18 XCTest pass.
39 lines
1.6 KiB
Swift
39 lines
1.6 KiB
Swift
import Foundation
|
|
import CoreVideo
|
|
|
|
/// Signal Desktop adapter. Signal shows avatars/initials with a coloured ring
|
|
/// around the active speaker; names may also be available via the Electron
|
|
/// Accessibility tree (preferred over OCR when we enable it). Geometry/threshold
|
|
/// here are first-pass and will be calibrated against real Signal screenshots.
|
|
struct SignalAdapter: AppAdapter {
|
|
static let bundleIDs = ["org.whispersystems.signal-desktop"]
|
|
let adapterVersion = "signal-0.1.0"
|
|
let preferredFPS = 3
|
|
|
|
private let analyzer: GridCallAnalyzer
|
|
|
|
init() {
|
|
var config = GridCallAnalyzer.Config()
|
|
// Signal's speaking cue is a 3px WHITE rounded border (not coloured); the
|
|
// name is a bottom footer, so the tile extends up from it. Geometry tuned
|
|
// with real fixtures. (Gotchas, per Signal source: NO border in 1:1 calls —
|
|
// fall back to mic-VAD/audio pill — and in Speaker view the large tile is
|
|
// the speaker; both handled at a higher level later.)
|
|
config.nameAnchor = .bottomCenter
|
|
config.detectWhiteBorder = true
|
|
config.detectColoredBorder = false
|
|
config.tileExpandX = 2.4
|
|
config.tileExpandY = 4.8
|
|
self.analyzer = GridCallAnalyzer(config: config)
|
|
}
|
|
|
|
func analyze(frame: CVPixelBuffer, at t: TimeInterval) -> [SpeakerObservation] {
|
|
analyzer.analyze(pixelBuffer: frame, at: t)
|
|
}
|
|
|
|
// Exposed for fixture/synthetic tests.
|
|
func analyze(cgImage: CGImage, at t: TimeInterval) -> [SpeakerObservation] {
|
|
analyzer.analyze(cgImage: cgImage, at: t)
|
|
}
|
|
}
|