Files
kapture/Sources/Kapture/CaptureController.swift
T
TZGyn 7633e81c52 Capture picked windows natively with real rounded corners
Window picks now capture via ScreenCaptureKit's desktopIndependentWindow
filter, so the image carries the app's actual rounded-corner alpha
instead of a fixed 10pt mask that let the desktop show through on apps
with larger radii. Falls back to crop+mask when the window is not in the
shareable content.

💘 Generated with Crush

Assisted-by: Crush:deepseek-v4-flash-0731
2026-09-09 14:10:03 +08:00

495 lines
22 KiB
Swift

import AppKit
import CoreGraphics
import ScreenCaptureKit
import ApplicationServices
final class CaptureController: NSObject {
static let shared = CaptureController()
private var overlays: [OverlayWindow] = []
private(set) var isSelecting = false
private var previousApp: NSRunningApplication?
private var overlayIDs: [Int] = []
// Selection state (driven by the event tap; AppKit global coordinates)
private var marqueeStart: NSPoint?
private(set) var marqueeRect: NSRect?
private(set) var hoverWindow: (id: CGWindowID, frame: NSRect)?
var hoverFrame: NSRect? { hoverWindow?.frame }
private var trackedWindows: [(id: CGWindowID, frame: NSRect)] = []
private var lastWindowScan = Date.distantPast
private var eventTap: CFMachPort?
/// Session event log for debugging (dumped via Copy Diagnostics).
/// Also appended to /tmp/kapture-debug.log so it survives relaunches.
static var sessionLog: [String] = []
static func log(_ line: String) {
let stamped = String(format: "%@ %@", DateFormatter.localizedString(from: Date(), dateStyle: .none, timeStyle: .medium), line)
sessionLog.append(stamped)
if sessionLog.count > 200 { sessionLog.removeFirst() }
NSLog("[Kapture] \(line)")
let path = "/tmp/kapture-debug.log"
if let handle = FileHandle(forWritingAtPath: path) {
handle.seekToEndOfFile()
handle.write((stamped + "\n").data(using: .utf8)!)
handle.closeFile()
} else {
FileManager.default.createFile(atPath: path, contents: (stamped + "\n").data(using: .utf8))
}
}
/// Diagnostic snapshot for "Copy Diagnostics" menu item.
func diagnostics() -> String {
var lines: [String] = []
lines.append("Kapture diagnostics — version \(Bundle.main.infoDictionary?["CFBundleShortVersionString"] ?? "?")")
lines.append("accessibility=\(AXIsProcessTrusted()) eventTap=\(eventTap != nil)")
lines.append("--- session log (newest last) ---")
lines.append(contentsOf: Self.sessionLog)
lines.append("--- screens ---")
for (i, s) in NSScreen.screens.enumerated() {
let scale = s.backingScaleFactor
let cgID = (s.deviceDescription[NSDeviceDescriptionKey("NSScreenNumber")] as? NSNumber)?.uint32Value ?? 0
lines.append("screen[\(i)]: frame=\(s.frame) scale=\(scale) backingSize=\(s.frame.width*scale)x\(s.frame.height*scale) cgID=\(cgID)")
}
if #available(macOS 14.0, *) {
Task {
if let content = try? await SCShareableContent.current {
for (i, d) in content.displays.enumerated() {
lines.append("SCDisplay[\(i)]: frame=\(d.frame) width=\(d.width)x\(d.height) id=\(d.displayID)")
}
} else {
lines.append("SCShareableContent: unavailable (no Screen Recording permission?)")
}
let text = lines.joined(separator: "\n")
let pb = NSPasteboard.general
pb.clearContents()
pb.setString(text, forType: .string)
}
} else {
let text = lines.joined(separator: "\n")
let pb = NSPasteboard.general
pb.clearContents()
pb.setString(text, forType: .string)
}
return lines.joined(separator: "\n")
}
// MARK: - Session lifecycle
func begin() {
guard !isSelecting else { return }
guard PermissionManager.isGranted else {
PermissionManager.request()
return
}
isSelecting = true
previousApp = NSWorkspace.shared.frontmostApplication
// Activation is async on macOS 26; wait a tick so the app is active
// before the overlays appear (otherwise clicks pass through).
NSApp.activate(ignoringOtherApps: true)
CaptureController.log("begin: activate issued, active=\(NSApp.isActive)")
DispatchQueue.main.asyncAfter(deadline: .now() + 0.05) { [weak self] in
guard let self, self.isSelecting else { return }
CaptureController.log("begin: active=\(NSApp.isActive) — showing overlays")
self.overlays = NSScreen.screens.map { screen in
let panel = OverlayWindow(screen: screen, controller: self)
(panel.contentView as? OverlayView)?.controller = self
return panel
}
self.overlays.forEach { $0.makeKeyAndOrderFront(nil) }
self.overlayIDs = self.overlays.map { $0.windowNumber }
CaptureController.log("begin: \(self.overlays.count) overlays, ids=\(self.overlayIDs), active=\(NSApp.isActive)")
self.installEventTap()
}
}
/// A window was picked from hover — capture it directly (real rounded
/// corners come from the window's own alpha).
private func finishWindowPick(_ windowID: CGWindowID, _ rect: NSRect) {
let ids = overlayIDs
hideOverlays()
isSelecting = false
restorePreviousApp()
DispatchQueue.main.async { [self] in
capture(rect, excludingWindowIDs: ids, windowID: windowID)
}
}
private func finishSelection(_ rect: NSRect) {
let ids = overlayIDs
hideOverlays()
guard rect.width >= 2, rect.height >= 2 else {
cancelSelection()
return
}
DispatchQueue.main.async { [self] in
capture(rect, excludingWindowIDs: ids)
}
}
private func cancelSelection() {
hideOverlays()
isSelecting = false
restorePreviousApp()
}
private func hideOverlays() {
removeEventTap()
overlays.forEach { $0.orderOut(nil) }
overlays = []
marqueeRect = nil
hoverWindow = nil
marqueeStart = nil
}
private func restorePreviousApp() {
previousApp?.activate(options: [.activateIgnoringOtherApps])
previousApp = nil
}
private func renderOverlays() {
for overlay in overlays {
(overlay.contentView as? OverlayView)?.needsDisplay = true
}
}
// MARK: - Event tap
private func installEventTap() {
guard eventTap == nil else { return }
guard AXIsProcessTrusted() else {
CaptureController.log("tap: accessibility not granted — falling back to panel events")
PermissionManager.requestAccessibility()
return
}
let mask: CGEventMask = (1 << CGEventType.mouseMoved.rawValue)
| (1 << CGEventType.leftMouseDown.rawValue)
| (1 << CGEventType.leftMouseDragged.rawValue)
| (1 << CGEventType.leftMouseUp.rawValue)
| (1 << CGEventType.keyDown.rawValue)
guard let tap = CGEvent.tapCreate(
tap: .cghidEventTap,
place: .headInsertEventTap,
options: .defaultTap,
eventsOfInterest: CGEventMask(mask),
callback: Self.tapCallback,
userInfo: Unmanaged.passUnretained(self).toOpaque()
) else {
CaptureController.log("tap: creation FAILED — falling back to panel events")
return
}
eventTap = tap
if let source = CFMachPortCreateRunLoopSource(nil, tap, 0) {
CFRunLoopAddSource(CFRunLoopGetMain(), source, .commonModes)
}
CGEvent.tapEnable(tap: tap, enable: true)
CaptureController.log("tap: installed")
}
private func removeEventTap() {
guard let tap = eventTap else { return }
CGEvent.tapEnable(tap: tap, enable: false)
if let source = CFMachPortCreateRunLoopSource(nil, tap, 0) {
CFRunLoopRemoveSource(CFRunLoopGetMain(), source, .commonModes)
}
CFMachPortInvalidate(tap)
eventTap = nil
CaptureController.log("tap: removed")
}
private static let tapCallback: CGEventTapCallBack = { _, type, event, refcon in
guard let refcon else { return Unmanaged.passUnretained(event) }
let controller = Unmanaged<CaptureController>.fromOpaque(refcon).takeUnretainedValue()
if let result = controller.handleTap(type, event) {
return Unmanaged.passUnretained(result)
}
return nil
}
/// Convert a CG global point (top-left origin) to AppKit global.
private func cgPointToAppKit(_ p: NSPoint) -> NSPoint {
guard let mainScreen = NSScreen.screens.first else { return p }
return NSPoint(x: p.x, y: mainScreen.frame.height - p.y)
}
/// Scan on-screen windows (AppKit global frames), front to back.
private func refreshTrackedWindows() {
guard let list = CGWindowListCopyWindowInfo(
[ .optionOnScreenOnly, .excludeDesktopElements ], kCGNullWindowID
) as? [[String: Any]] else { trackedWindows = []; return }
let ownIDs = Set(overlayIDs)
var found: [(id: CGWindowID, frame: NSRect)] = []
for info in list {
guard let cid = info[kCGWindowNumber as String] as? CGWindowID,
let bounds = info[kCGWindowBounds as String] as? [String: CGFloat],
let layer = info[kCGWindowLayer as String] as? Int,
layer == 0
else { continue }
if ownIDs.contains(Int(cid)) { continue }
let cgRect = NSRect(
x: bounds["X"] ?? 0,
y: bounds["Y"] ?? 0,
width: bounds["Width"] ?? 0,
height: bounds["Height"] ?? 0
)
guard cgRect.width >= 80, cgRect.height >= 60 else { continue }
let rect = Self.cgToAppKit(rect: cgRect)
found.append((cid, rect))
}
trackedWindows = found
}
/// Convert a CGWindowList (top-left origin) frame into AppKit screen
/// coordinates (bottom-left origin).
private static func cgToAppKit(rect: NSRect) -> NSRect {
guard let mainScreen = NSScreen.screens.first else { return rect }
let y = mainScreen.frame.height - rect.origin.y - rect.height
return NSRect(x: rect.origin.x, y: y, width: rect.width, height: rect.height)
}
private func topmostWindowContaining(_ appKitPoint: NSPoint) -> (id: CGWindowID, frame: NSRect)? {
for entry in trackedWindows {
if entry.frame.contains(appKitPoint) {
return entry
}
}
return nil
}
/// Returns the event to pass through, or nil to consume it.
func handleTap(_ type: CGEventType, _ event: CGEvent) -> CGEvent? {
guard isSelecting else { return event }
switch type {
case .tapDisabledByUserInput, .tapDisabledByTimeout:
// A timed-out tap must be re-enabled; guard against a torn-down tap.
if let tap = eventTap {
CGEvent.tapEnable(tap: tap, enable: true)
CaptureController.log("tap: re-enabled after \(type)")
}
return event
case .keyDown:
if event.getIntegerValueField(.keyboardEventKeycode) == 53 {
CaptureController.log("tap: Esc — cancel")
cancelSelection()
return nil
}
return event
case .mouseMoved, .leftMouseDragged:
// Throttle window scans while moving
if Date().timeIntervalSince(lastWindowScan) > 0.15 {
lastWindowScan = Date()
refreshTrackedWindows()
}
let appKitPoint = cgPointToAppKit(NSPoint(x: event.location.x, y: event.location.y))
if type == .mouseMoved {
let window = topmostWindowContaining(appKitPoint)
if window?.frame != hoverFrame {
hoverWindow = window
renderOverlays()
}
return event
}
// Drag: grow the marquee
guard let start = marqueeStart else { return nil }
let rect = NSRect(
x: min(start.x, appKitPoint.x),
y: min(start.y, appKitPoint.y),
width: abs(appKitPoint.x - start.x),
height: abs(appKitPoint.y - start.y)
)
marqueeRect = rect
hoverWindow = nil
renderOverlays()
return nil
case .leftMouseDown:
marqueeStart = cgPointToAppKit(NSPoint(x: event.location.x, y: event.location.y))
marqueeRect = nil
CaptureController.log("tap: mouseDown at \(marqueeStart.map { "\($0)" } ?? "?")")
return nil
case .leftMouseUp:
defer { marqueeStart = nil; marqueeRect = nil }
let appKitPoint = cgPointToAppKit(NSPoint(x: event.location.x, y: event.location.y))
let dragDistance = marqueeStart.map { hypot($0.x - appKitPoint.x, $0.y - appKitPoint.y) } ?? 0
if let rect = marqueeRect, dragDistance >= 4, rect.width >= 2, rect.height >= 2 {
CaptureController.log("tap: marquee complete \(rect)")
finishSelection(rect)
} else if let hover = hoverWindow {
CaptureController.log("tap: window pick id=\(hover.id) \(hover.frame)")
finishWindowPick(hover.id, hover.frame)
} else {
CaptureController.log("tap: click with no hover/marquee — cancel")
cancelSelection()
}
return nil
default:
return event
}
}
// MARK: - Capture
private func capture(_ rect: NSRect, excludingWindowIDs ids: [Int], roundedCorners: Bool = false, windowID: CGWindowID? = nil) {
ScreenCapture.shared.capture(rect, excludingWindowIDs: ids, roundedCorners: roundedCorners, windowID: windowID) { [weak self] image in
DispatchQueue.main.async {
self?.isSelecting = false
self?.restorePreviousApp()
Task { @MainActor in
guard let image else {
ResultWindow.shared.show(image: ResultWindow.failureImage("Capture failed. Check Screen Recording permission."))
return
}
CaptureController.log("capture done: \(image.width)x\(image.height) — showing result window")
ResultWindow.shared.show(image: image)
}
}
}
}
}
final class ScreenCapture {
static let shared = ScreenCapture()
private init() {}
@available(macOS 14.0, *)
private func crop(_ image: CGImage, to cgRect: CGRect, display: SCDisplay, roundedCorners: Bool = false) -> CGImage? {
// cgRect is in SCDisplay space (bottom-left origin, Y flipped vs AppKit).
// The captured image has a TOP-LEFT origin. So within the display,
// we must flip Y: pixelY = displayHeight - (cgY - displayMinY) - cgHeight.
let scaleX = CGFloat(image.width) / display.frame.width
let scaleY = CGFloat(image.height) / display.frame.height
guard scaleX > 0, scaleY > 0 else { return nil }
let localMinX = cgRect.minX - display.frame.minX
let localMaxY = cgRect.maxY - display.frame.minY
let flippedY = display.frame.height - localMaxY
let pxRect = CGRect(
x: localMinX * scaleX,
y: flippedY * scaleY,
width: cgRect.width * scaleX,
height: cgRect.height * scaleY
)
// Guard against negative offsets when the selection reaches beyond the
// display's frame (e.g. secondary monitor coordinate quirks).
let safeRect = pxRect.intersection(CGRect(x: 0, y: 0, width: CGFloat(image.width), height: CGFloat(image.height)))
guard safeRect.width >= 1, safeRect.height >= 1 else { return nil }
// Use a pixel-exact subimage crop instead of redrawing through a
// CGContext, which resamples and loses quality on retina captures.
let rounded = safeRect.integral
guard rounded.width >= 1, rounded.height >= 1 else { return nil }
guard var result = image.cropping(to: rounded) else { return nil }
// Apply a rounded-corner alpha mask for window captures, matching
// macOS window chrome (≈10pt radius, scaled to image pixels).
if roundedCorners {
let radius = 10 * scaleX
let maskRect = CGRect(x: 0, y: 0, width: result.width, height: result.height)
guard let maskCtx = CGContext(
data: nil, width: result.width, height: result.height,
bitsPerComponent: 8, bytesPerRow: 0,
space: CGColorSpaceCreateDeviceRGB(),
bitmapInfo: CGImageAlphaInfo.premultipliedLast.rawValue
) else { return result }
maskCtx.setFillColor(CGColor(gray: 1, alpha: 1))
maskCtx.fill(maskRect)
maskCtx.setBlendMode(.clear)
maskCtx.setFillColor(CGColor(gray: 0, alpha: 1))
maskCtx.addPath(CGPath(roundedRect: maskRect, cornerWidth: radius, cornerHeight: radius, transform: nil))
maskCtx.fillPath()
maskCtx.setBlendMode(.normal)
if let mask = maskCtx.makeImage(),
let masked = result.masking(mask) {
result = masked
}
}
return result
}
@available(macOS 14.0, *)
private func displayContaining(_ rect: NSRect, in content: SCShareableContent) -> SCDisplay? {
let mid = NSPoint(x: rect.midX, y: rect.midY)
guard let screen = NSScreen.screens.first(where: { $0.frame.contains(mid) }) ?? NSScreen.screens.first else {
return nil
}
let cgID = (screen.deviceDescription[NSDeviceDescriptionKey("NSScreenNumber")] as? NSNumber)?.uint32Value ?? 0
return content.displays.first(where: { $0.displayID == cgID }) ?? content.displays.first
}
func capture(_ rect: NSRect, excludingWindowIDs excludedIDs: [Int], roundedCorners: Bool = false, windowID: CGWindowID? = nil, completion: @escaping (CGImage?) -> Void) {
if #available(macOS 14.0, *) {
Task {
guard let content = try? await SCShareableContent.current,
let display = displayContaining(rect, in: content) else {
completion(nil)
return
}
let excludedSet = Set(excludedIDs.map { CGWindowID($0) })
let excluded = content.windows.filter { excludedSet.contains($0.windowID) }
let filter = SCContentFilter(display: display, excludingWindows: excluded)
let config = SCStreamConfiguration()
// SCDisplay.width/height are in POINTS; SCStreamConfiguration
// width/height are output PIXELS. Multiply by the backing scale
// of the screen containing the selection so retina displays are
// captured at full resolution and 1x displays stay 1x.
guard let screen = NSScreen.screens.first(where: { $0.frame.contains(NSPoint(x: rect.midX, y: rect.midY)) }) else {
completion(nil)
return
}
let backingScale = screen.backingScaleFactor
config.width = Int(CGFloat(display.width) * backingScale)
config.height = Int(CGFloat(display.height) * backingScale)
config.showsCursor = false
// ScreenCaptureKit uses a different origin than AppKit for
// screens stacked around the main display: per-display,
// SCDisplay y = appKitY - NSScreen.maxY + SCDisplay.maxY.
let scRect = CGRect(
x: rect.minX,
y: rect.minY - screen.frame.maxY + display.frame.maxY,
width: rect.width,
height: rect.height
)
// Window pick: capture the window DIRECTLY — the image comes
// with the app's real rounded-corner alpha (no mask guessing).
if let windowID,
let scWindow = content.windows.first(where: { $0.windowID == windowID }) {
var windowConfig = SCStreamConfiguration()
windowConfig.width = Int(scWindow.frame.width * backingScale)
windowConfig.height = Int(scWindow.frame.height * backingScale)
windowConfig.showsCursor = false
if let windowImage = try? await SCScreenshotManager.captureImage(
contentFilter: SCContentFilter(desktopIndependentWindow: scWindow),
configuration: windowConfig
) {
CaptureController.log("capture: WINDOW id=\(windowID) image=\(windowImage.width)x\(windowImage.height) (native alpha corners)")
completion(windowImage)
return
}
CaptureController.log("capture: window filter failed for id=\(windowID) — falling back to crop+mask")
}
guard let image = try? await SCScreenshotManager.captureImage(contentFilter: filter, configuration: config) else {
completion(nil)
return
}
CaptureController.log("capture: rect=\(rect) screen=\(screen.frame) display=\(display.frame) backing=\(backingScale) image=\(image.width)x\(image.height) scRect=\(scRect)")
completion(self.crop(image, to: scRect, display: display, roundedCorners: roundedCorners))
}
} else {
guard let primary = NSScreen.screens.first(where: { $0.frame.origin == .zero }) ?? NSScreen.screens.first else {
completion(nil)
return
}
let cgRect = CGRect(
x: rect.minX,
y: primary.frame.height - rect.maxY,
width: rect.width,
height: rect.height
)
completion(CGWindowListCreateImage(cgRect, .optionOnScreenOnly, kCGNullWindowID, [.bestResolution, .boundsIgnoreFraming]))
}
}
}