import Foundation
import CoreVideo

/// Zoom adapter (native app: us.zoom.xos).
///
/// Zoom's active-speaker cue is a **coloured border** around the speaking tile —
/// by default a green/yellow outline (configurable in Zoom settings). The
/// participant **name sits in the tile's bottom-LEFT corner**, so the tile is
/// estimated extending up and to the right of the name.
///
/// Gotchas to calibrate against real fixtures later:
/// - **Speaker view** shows one big tile; the active speaker fills it (no useful
///   per-tile border) — handle by attributing speech to the large tile.
/// - The self-view tile and screen-share change the layout.
///
/// Detection *logic* is validated on synthetic frames; geometry constants are a
/// first pass pending real Zoom screenshots.
struct ZoomAdapter: AppAdapter {
    static let bundleIDs = ["us.zoom.xos"]
    let adapterVersion = "zoom-0.1.0"
    let preferredFPS = 3

    private let analyzer: GridCallAnalyzer

    init() {
        var config = GridCallAnalyzer.Config()
        config.nameAnchor = .bottomLeft
        config.detectColoredBorder = true     // green/yellow speaking border (vivid)
        config.detectWhiteBorder = false
        // Zoom's frame is vivid (green #2d8c3c ≈ 0.68, yellow ≈ 0.96); the green→
        // yellow hue band spans ~45–140°. Keep a generous-but-not-trivial threshold;
        // require all-four-sides distribution (handled upstream) to reject bright video.
        config.colorSaturation = 0.45
        config.colorHueRange = 40...150
        config.tileExpandX = 3.0
        config.tileExpandY = 5.0
        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)
    }
}