Files
kapture/Sources/Kapture/ResultWindow.swift
T
TZGyn 45e4962ec3 Fix multi-display window detection and click-to-capture; separate Redact tool
Window frames are now converted to AppKit space once at detection time, so
hover highlighting and picking work on every display. A click is only
treated as a drag after 4pt of movement, so clicking a detected window
captures it instead of passing a stray marquee. Redact is now a standalone
tool (Select/Draw/Redact) with its own toolbar hints instead of a toggle
inside the draw bar.

💘 Generated with Crush

Assisted-by: Crush:deepseek-v4-flash-0731
2026-09-09 10:46:32 +08:00

652 lines
25 KiB
Swift

import SwiftUI
import AppKit
import UniformTypeIdentifiers
final class ResultWindow {
static let shared = ResultWindow()
private var windows: [NSWindow] = []
private var nextOrigin = NSPoint(x: 60, y: 60)
private var openCount = 0
@MainActor
func show(image: CGImage) {
let model = CaptureModel(image: image)
let w = NSWindow()
w.contentViewController = NSHostingController(rootView: ResultView(model: model) {
w.close()
})
w.title = "Kapture — Screenshot" + (openCount > 0 ? " \(openCount + 1)" : "")
w.level = .floating
w.styleMask = [.titled, .closable, .resizable]
w.setContentSize(NSSize(width: 694, height: 520))
w.isReleasedWhenClosed = false
w.setFrameOrigin(nextOrigin)
w.makeKeyAndOrderFront(nil)
windows.append(w)
openCount += 1
nextOrigin = NSPoint(x: nextOrigin.x + 28, y: nextOrigin.y - 28)
windowCleanup(for: w)
}
private func windowCleanup(for window: NSWindow) {
NotificationCenter.default.addObserver(
forName: NSWindow.willCloseNotification,
object: window,
queue: .main
) { [weak self] _ in
Task { @MainActor in
guard let self else { return }
self.windows.removeAll { $0 === window }
self.openCount = max(0, self.openCount - 1)
}
}
}
@MainActor
func showOpenPanel() {
let panel = NSOpenPanel()
panel.allowedContentTypes = [.image]
panel.allowsMultipleSelection = false
guard panel.runModal() == .OK, let url = panel.url else { return }
guard let image = NSImage(contentsOf: url),
let cgImage = image.cgImage(forProposedRect: nil, context: nil, hints: nil) else {
self.show(image: Self.failureImage("Could not load the selected image."))
return
}
show(image: cgImage)
}
static func failureImage(_ message: String) -> CGImage {
let size = NSSize(width: 800, height: 200)
guard let rep = NSBitmapImageRep(
bitmapDataPlanes: nil, pixelsWide: Int(size.width), pixelsHigh: Int(size.height),
bitsPerSample: 8, samplesPerPixel: 4, hasAlpha: true, isPlanar: false,
colorSpaceName: .deviceRGB, bytesPerRow: 0, bitsPerPixel: 0
) else { return NSImage(size: size).cgImage(forProposedRect: nil, context: nil, hints: nil)! }
NSGraphicsContext.saveGraphicsState()
NSGraphicsContext.current = NSGraphicsContext(bitmapImageRep: rep)
NSColor.white.setFill()
NSRect(origin: .zero, size: size).fill()
let attrs: [NSAttributedString.Key: Any] = [
.font: NSFont.systemFont(ofSize: 30),
.foregroundColor: NSColor.systemRed,
]
message.draw(at: NSPoint(x: 40, y: 80), withAttributes: attrs)
NSGraphicsContext.restoreGraphicsState()
return rep.cgImage!
}
}
@MainActor
final class CaptureModel: ObservableObject {
let image: CGImage
@Published var mode: CaptureMode = .screenshot
@Published var extractedText: String?
@Published var isOCRRunning = false
@Published var statusMessage: String?
/// Drag selection rect in IMAGE point space (nil = none)
@Published var selection: CGRect?
/// Freehand drawing strokes in IMAGE point space
@Published var strokes: [Stroke] = []
/// Redo stack of removed strokes
@Published var redoStack: [Stroke] = []
/// Whether the pen is active (drag draws instead of selecting)
@Published var tool: Tool = .select
/// Current drawing color
@Published var drawColor: NSColor = .systemRed
/// Stroke thickness in points (image space)
@Published var strokeWidth: CGFloat = 3.0
enum Tool {
case select
case draw
case redact
}
struct Stroke {
let points: [CGPoint]
let width: CGFloat
let color: NSColor
var isRedaction: Bool = false
}
enum CaptureMode {
case screenshot
case text
}
init(image: CGImage) {
self.image = image
}
var hasSelection: Bool { selection != nil && selection!.width >= 2 && selection!.height >= 2 }
var canUndo: Bool { !strokes.isEmpty }
var canRedo: Bool { !redoStack.isEmpty }
func undoStroke() {
guard let last = strokes.popLast() else { return }
redoStack.append(last)
}
func redoStroke() {
guard let last = redoStack.popLast() else { return }
strokes.append(last)
}
func clearAnnotations() {
strokes = []
redoStack = []
}
/// Image with drawn strokes flattened in, for copy/save/export.
var annotatedImage: CGImage {
guard !strokes.isEmpty else { return image }
let size = NSSize(width: image.width, height: image.height)
guard let rep = NSBitmapImageRep(
bitmapDataPlanes: nil, pixelsWide: Int(size.width), pixelsHigh: Int(size.height),
bitsPerSample: 8, samplesPerPixel: 4, hasAlpha: true, isPlanar: false,
colorSpaceName: .deviceRGB, bytesPerRow: 0, bitsPerPixel: 0
) else { return image }
NSGraphicsContext.saveGraphicsState()
NSGraphicsContext.current = NSGraphicsContext(bitmapImageRep: rep)
let ctx = NSGraphicsContext.current!.cgContext
// CGImage draws with a flipped Y in NSGraphicsContext
ctx.draw(image, in: NSRect(origin: .zero, size: size))
// Strokes are stored in TOP-LEFT image coordinates (from the SwiftUI
// canvas), but the CGContext uses a BOTTOM-LEFT origin. Flip Y so the
// strokes land where they were drawn.
ctx.saveGState()
ctx.translateBy(x: 0, y: size.height)
ctx.scaleBy(x: 1, y: -1)
ctx.setLineCap(.round)
ctx.setLineJoin(.round)
for stroke in strokes {
guard stroke.points.count > 1 else { continue }
if stroke.isRedaction {
// Redaction bar: filled black rect covering the stroke bounds,
// padded so it fully covers text.
let xs = stroke.points.map { $0.x }
let ys = stroke.points.map { $0.y }
let bar = NSRect(
x: xs.min()! - 2,
y: ys.min()! - 2,
width: (xs.max()! - xs.min()!) + 4,
height: max(stroke.width, ys.max()! - ys.min()!) + 4
)
NSColor.black.setFill()
NSBezierPath(rect: bar).fill()
} else {
stroke.color.setStroke()
ctx.setLineWidth(stroke.width)
ctx.beginPath()
ctx.move(to: stroke.points[0])
for point in stroke.points.dropFirst() {
ctx.addLine(to: point)
}
ctx.strokePath()
}
}
ctx.restoreGState()
NSGraphicsContext.restoreGraphicsState()
return rep.cgImage ?? image
}
func addStroke(_ points: [CGPoint]) {
guard points.count > 1 else { return }
if tool == .redact {
// Redaction: a filled black bar from start to end, as thick as the
// current stroke width (drawn as a rect for clean edges).
strokes.append(Stroke(points: points, width: max(strokeWidth, 12), color: .black, isRedaction: true))
} else {
strokes.append(Stroke(points: points, width: strokeWidth, color: drawColor))
}
redoStack = []
}
var displayText: String {
if isOCRRunning {
return "Recognizing text…"
}
return extractedText ?? "Select text in the screenshot, then click “Get Text”."
}
func cropImage(to rectInImage: CGRect) -> CGImage? {
return image.cropping(to: rectInImage)
}
func runOCR(over selectionOnly: CGRect? = nil) {
guard !isOCRRunning else { return }
isOCRRunning = true
statusMessage = nil
let targetImage: CGImage
if let sel = selectionOnly {
guard let cropped = image.cropping(to: sel) else {
self.isOCRRunning = false
self.statusMessage = "Selection too small."
return
}
targetImage = cropped
} else {
targetImage = image
}
OCRService.shared.recognize(targetImage) { [weak self] text in
Task { @MainActor in
guard let self else { return }
self.isOCRRunning = false
self.mode = .text
if text.isEmpty {
self.extractedText = "No text found in the selection."
} else {
self.extractedText = text
let pasteboard = NSPasteboard.general
pasteboard.clearContents()
pasteboard.setString(text, forType: .string)
self.statusMessage = "Copied to clipboard."
}
}
}
}
func runOCRSelection() {
guard let sel = selection, hasSelection else { return }
runOCR(over: sel)
}
func copyText() {
guard let text = extractedText else { return }
let pasteboard = NSPasteboard.general
pasteboard.clearContents()
pasteboard.setString(text, forType: .string)
statusMessage = "Copied to clipboard."
}
func copyImage() {
let pasteboard = NSPasteboard.general
pasteboard.clearContents()
pasteboard.writeObjects([NSImage(cgImage: annotatedImage, size: .zero)])
statusMessage = "Image copied to clipboard."
}
func savePNG() {
let panel = NSSavePanel()
panel.allowedContentTypes = [.png]
panel.nameFieldStringValue = "Kapture-\(Self.timestamp()).png"
guard panel.runModal() == .OK, let url = panel.url else { return }
guard let dest = CGImageDestinationCreateWithURL(url as CFURL, UTType.png.identifier as CFString, 1, nil) else {
statusMessage = "Could not create PNG file."
return
}
CGImageDestinationAddImage(dest, annotatedImage, nil)
if CGImageDestinationFinalize(dest) {
statusMessage = "Saved PNG."
} else {
statusMessage = "Could not save PNG."
}
}
private static func timestamp() -> String {
let formatter = DateFormatter()
formatter.dateFormat = "yyyyMMdd-HHmmss"
return formatter.string(from: Date())
}
}
struct ResultView: View {
@ObservedObject var model: CaptureModel
let onClose: () -> Void
var body: some View {
VStack(spacing: 0) {
// Toolbar
HStack(spacing: 10) {
Picker("", selection: $model.mode) {
Text("Screenshot").tag(CaptureModel.CaptureMode.screenshot)
Text("Text").tag(CaptureModel.CaptureMode.text)
}
.pickerStyle(.segmented)
.fixedSize()
Spacer()
if model.hasSelection {
Button {
model.runOCRSelection()
} label: {
Label("OCR Selection", systemImage: "text.magnifyingglass")
}
.buttonStyle(.borderedProminent)
.disabled(model.isOCRRunning)
.help("Recognize text inside the selected region")
}
Button {
model.runOCR()
} label: {
Label("Get All Text", systemImage: "text.viewfinder")
}
.buttonStyle(.bordered)
.disabled(model.isOCRRunning)
.help("Recognize all text in the screenshot")
Divider().frame(height: 18)
Button {
model.tool = model.tool == .draw ? .select : .draw
if model.tool != .select { model.selection = nil }
} label: {
Label("Draw", systemImage: model.tool == .draw ? "pencil.tip.crop.circle.fill" : "pencil.tip.crop.circle")
}
.buttonStyle(.bordered)
.foregroundStyle(model.tool == .draw ? .primary : .secondary)
.help("Draw on the screenshot")
Button {
model.tool = model.tool == .redact ? .select : .redact
if model.tool != .select { model.selection = nil }
} label: {
Label("Redact", systemImage: model.tool == .redact ? "rectangle.fill.on.rectangle.fill" : "rectangle.dashed")
}
.buttonStyle(.bordered)
.foregroundStyle(model.tool == .redact ? .primary : .secondary)
.help("Cover sensitive areas with black bars")
Button {
model.copyImage()
} label: {
Label("Copy", systemImage: "doc.on.doc")
}
.buttonStyle(.bordered)
.help("Copy image to clipboard")
Button {
model.savePNG()
} label: {
Label("Save", systemImage: "square.and.arrow.down")
}
.buttonStyle(.bordered)
.help("Save screenshot as PNG");
Button {
onClose()
} label: {
Image(systemName: "xmark.circle.fill")
.foregroundStyle(.secondary)
}
.buttonStyle(.plain)
.help("Close")
}
.padding(.horizontal, 14)
.padding(.vertical, 10)
Divider()
// Tool toolbar (only when a draw tool is active)
if model.tool != .select {
HStack(spacing: 14) {
Label(model.tool == .redact ? "Redact" : "Draw", systemImage: model.tool == .redact ? "rectangle.fill" : "pencil.tip")
.font(.caption)
.foregroundStyle(.secondary)
Divider().frame(height: 18)
if model.tool == .draw {
HStack(spacing: 6) {
Image(systemName: "circle.fill").font(.system(size: 4))
Image(systemName: "circle.fill").font(.system(size: 7))
Image(systemName: "circle.fill").font(.system(size: 10))
}
.foregroundStyle(.secondary)
Slider(value: $model.strokeWidth, in: 1...12, step: 0.5)
.frame(width: 120)
.help("Stroke thickness")
Divider().frame(height: 18)
ColorPicker("", selection: Binding(
get: { Color(nsColor: model.drawColor) },
set: { model.drawColor = NSColor($0) }
), supportsOpacity: false)
.labelsHidden()
.frame(width: 28)
.help("Drawing color")
} else {
Label("Drag to cover sensitive text", systemImage: "eye.slash")
.font(.caption)
.foregroundStyle(.secondary)
}
Spacer()
Button {
model.undoStroke()
} label: {
Label("Undo", systemImage: "arrow.uturn.backward")
}
.buttonStyle(.bordered)
.controlSize(.small)
.disabled(!model.canUndo)
.keyboardShortcut("z", modifiers: .command)
.help("Undo last stroke (⌘Z)")
Button {
model.redoStroke()
} label: {
Label("Redo", systemImage: "arrow.uturn.forward")
}
.buttonStyle(.bordered)
.controlSize(.small)
.disabled(!model.canRedo)
.keyboardShortcut("z", modifiers: [.command, .shift])
.help("Redo stroke (⌘⇧Z)")
Button {
model.clearAnnotations()
} label: {
Label("Clear", systemImage: "eraser")
}
.buttonStyle(.bordered)
.controlSize(.small)
.disabled(model.strokes.isEmpty)
.help("Remove all drawn annotations")
}
.padding(.horizontal, 14)
.padding(.vertical, 8)
.background(.bar)
Divider()
}
// Content
if model.mode == .screenshot {
ScreenshotPane(model: model)
.padding(12)
} else {
ZStack {
ScrollView {
Text(model.displayText)
.font(.system(.body, design: .monospaced))
.textSelection(.enabled)
.frame(maxWidth: .infinity, alignment: .leading)
.padding(12)
}
}
.frame(maxWidth: .infinity, maxHeight: .infinity)
}
// Status bar
HStack(spacing: 8) {
if model.isOCRRunning {
ProgressView()
.controlSize(.small)
}
Text(model.statusMessage ?? (model.mode == .screenshot
? (model.hasSelection ? "Region selected — click OCR Selection." : "Drag to select a region, or Get All Text.")
: "Selectable text"))
.font(.caption)
.foregroundStyle(.secondary)
.lineLimit(1)
Spacer()
if model.mode == .text, model.extractedText != nil {
Button {
model.copyText()
} label: {
Label("Copy Text", systemImage: "doc.on.doc")
}
.buttonStyle(.bordered)
.controlSize(.small)
}
}
.padding(.horizontal, 14)
.padding(.vertical, 8)
.background(.bar)
}
.frame(minWidth: 520, minHeight: 420)
}
}
struct ScreenshotPane: View {
@ObservedObject var model: CaptureModel
private var imageSize: CGSize {
CGSize(width: model.image.width, height: model.image.height)
}
private func geometry(for geo: GeometryProxy) -> (scale: CGFloat, drawSize: CGSize, origin: CGPoint) {
let size = imageSize
let scale = min(geo.size.width / size.width, geo.size.height / size.height)
let drawSize = CGSize(width: size.width * scale, height: size.height * scale)
let origin = CGPoint(
x: (geo.size.width - drawSize.width) / 2,
y: (geo.size.height - drawSize.height) / 2
)
return (scale, drawSize, origin)
}
private func toImagePoint(_ viewPoint: CGPoint, scale: CGFloat, origin: CGPoint) -> CGPoint {
CGPoint(
x: (viewPoint.x - origin.x) / scale,
y: (viewPoint.y - origin.y) / scale
)
}
private func clampSelection(_ rect: CGRect) -> CGRect {
rect.intersection(CGRect(origin: .zero, size: imageSize))
}
@State private var currentStroke: [CGPoint] = []
var body: some View {
GeometryReader { geo in
let (scale, drawSize, origin) = geometry(for: geo)
ZStack {
Image(nsImage: NSImage(cgImage: model.image, size: .zero))
.resizable()
.interpolation(imageSize.width >= geo.size.width ? .high : .none)
.aspectRatio(contentMode: .fit)
.frame(width: drawSize.width, height: drawSize.height)
.position(x: origin.x + drawSize.width / 2, y: origin.y + drawSize.height / 2)
// Completed strokes
Canvas { context, _ in
for stroke in model.strokes {
guard stroke.points.count > 1 else { continue }
if stroke.isRedaction {
let xs = stroke.points.map { $0.x }
let ys = stroke.points.map { $0.y }
let bar = CGRect(
x: origin.x + (xs.min()! - 2) * scale,
y: origin.y + (ys.min()! - 2) * scale,
width: ((xs.max()! - xs.min()!) + 4) * scale,
height: (max(stroke.width, ys.max()! - ys.min()!) + 4) * scale
)
context.fill(Path(bar), with: .color(.black))
} else {
var path = Path()
path.move(to: CGPoint(x: origin.x + stroke.points[0].x * scale, y: origin.y + stroke.points[0].y * scale))
for point in stroke.points.dropFirst() {
path.addLine(to: CGPoint(x: origin.x + point.x * scale, y: origin.y + point.y * scale))
}
context.stroke(path, with: .color(Color(nsColor: stroke.color)), lineWidth: stroke.width)
}
}
}
.allowsHitTesting(false)
// In-progress stroke
if !currentStroke.isEmpty {
Canvas { context, _ in
var path = Path()
if currentStroke.count > 1 {
path.move(to: CGPoint(x: origin.x + currentStroke[0].x * scale, y: origin.y + currentStroke[0].y * scale))
for point in currentStroke.dropFirst() {
path.addLine(to: CGPoint(x: origin.x + point.x * scale, y: origin.y + point.y * scale))
}
}
context.stroke(path, with: .color(Color(nsColor: model.drawColor)), lineWidth: model.strokeWidth)
}
.allowsHitTesting(false)
}
if model.tool == .select, let sel = model.selection {
let viewRect = CGRect(
x: origin.x + sel.minX * scale,
y: origin.y + sel.minY * scale,
width: sel.width * scale,
height: sel.height * scale
)
Rectangle()
.fill(Color.accentColor.opacity(0.15))
.border(Color.accentColor, width: 1.5)
.frame(width: viewRect.width, height: viewRect.height)
.position(x: viewRect.midX, y: viewRect.midY)
.allowsHitTesting(false)
}
}
.contentShape(Rectangle())
.gesture(
DragGesture(minimumDistance: 0)
.onChanged { value in
if model.tool != .select {
let p = toImagePoint(value.location, scale: scale, origin: origin)
let imgRect = CGRect(origin: .zero, size: imageSize)
if imgRect.contains(p) {
currentStroke.append(p)
}
} else {
let start = toImagePoint(value.startLocation, scale: scale, origin: origin)
let current = toImagePoint(value.location, scale: scale, origin: origin)
let rect = CGRect(
x: min(start.x, current.x),
y: min(start.y, current.y),
width: abs(current.x - start.x),
height: abs(current.y - start.y)
)
model.selection = clampSelection(rect)
}
}
.onEnded { _ in
if model.tool != .select {
if currentStroke.count > 1 {
model.addStroke(currentStroke)
}
currentStroke = []
} else {
if let s = model.selection, (s.width < 2 || s.height < 2) {
model.selection = nil
}
}
}
)
}
}
}