import Vision

func recognizeText(in image: CGImage) async throws -> [String] {
    var request = RecognizeTextRequest()
    request.recognitionLevel = .accurate
    request.recognitionLanguages = [Locale.Language(identifier: "en-US")]

    let observations = try await request.perform(on: image)
    return observations.compactMap { observation in
        observation.topCandidates(1).first?.string
    }
}

import Vision

func recognizeTextLegacy(in image: CGImage) throws -> [String] {
    var recognized: [String] = []
    let request = VNRecognizeTextRequest { request, error in
        guard let observations = request.results as? [VNRecognizedTextObservation] else { return }
        recognized = observations.compactMap { $0.topCandidates(1).first?.string }
    }
    request.recognitionLevel = .accurate

    let handler = VNImageRequestHandler(cgImage: image)
    try handler.perform([request])
    return recognized
}

var request = RecognizeTextRequest()
request.recognitionLevel = .accurate       // .fast for real-time
request.recognitionLanguages = [
    Locale.Language(identifier: "en-US"),
    Locale.Language(identifier: "fr-FR"),
]
request.usesLanguageCorrection = true
request.customWords = ["SwiftUI", "Xcode"] // domain-specific terms

let observations = try await request.perform(on: cgImage)
for observation in observations {
    guard let candidate = observation.topCandidates(1).first else { continue }
    let text = candidate.string
    let confidence = candidate.confidence  // 0.0 ... 1.0
    let bounds = observation.boundingBox   // normalized coordinates
}

let request = VNRecognizeTextRequest()
request.recognitionLevel = .accurate
request.recognitionLanguages = ["en-US", "fr-FR"]
request.usesLanguageCorrection = true

// Modern API
let faceRequest = DetectFaceRectanglesRequest()
let faces = try await faceRequest.perform(on: cgImage)

for face in faces {
    let boundingBox = face.boundingBox   // normalized CGRect
    let roll = face.roll                 // Measurement<UnitAngle>
    let yaw = face.yaw                  // Measurement<UnitAngle>
}

// Landmarks (eyes, nose, mouth contours)
var landmarkRequest = DetectFaceLandmarksRequest()
let landmarkFaces = try await landmarkRequest.perform(on: cgImage)
for face in landmarkFaces {
    let landmarks = face.landmarks
    let leftEye = landmarks?.leftEye?.normalizedPoints
    let nose = landmarks?.nose?.normalizedPoints
}

func convertToUIKit(_ rect: CGRect, imageHeight: CGFloat) -> CGRect {
    CGRect(
        x: rect.origin.x,
        y: imageHeight - rect.origin.y - rect.height,
        width: rect.width,
        height: rect.height
    )
}

var request = DetectBarcodesRequest()
request.symbologies = [.qr, .ean13, .code128, .pdf417]

let barcodes = try await request.perform(on: cgImage)
for barcode in barcodes {
    let payload = barcode.payloadString          // decoded content
    let symbology = barcode.symbology            // .qr, .ean13, etc.
    let bounds = barcode.boundingBox             // normalized rect
}

var request = RecognizeDocumentsRequest()
let documents = try await request.perform(on: cgImage)

for observation in documents {
    let container = observation.document

    // Full text content
    let fullText = container.text

    // Structured access to paragraphs
    for paragraph in container.paragraphs {
        let paragraphText = paragraph.text
    }

    // Tables and lists
    for table in container.tables { /* structured table data */ }
    for list in container.lists { /* structured list data */ }

    // Embedded barcodes detected within the document
    for barcode in container.barcodes { /* barcode data */ }

    // Document title if detected
    if let title = container.title { print(title) }
}

var request = GeneratePersonSegmentationRequest()
request.qualityLevel = .accurate  // .balanced, .fast

let mask = try await request.perform(on: cgImage)
// mask is a PersonSegmentationObservation with a pixelBuffer property
let maskBuffer = mask.pixelBuffer
// Apply mask using Core Image: CIFilter.blendWithMask()

let request = VNGeneratePersonSegmentationRequest()
request.qualityLevel = .accurate  // .balanced, .fast
request.outputPixelFormat = kCVPixelFormatType_OneComponent8

let handler = VNImageRequestHandler(cgImage: cgImage)
try handler.perform([request])

guard let mask = request.results?.first?.pixelBuffer else { return }
// Apply mask using Core Image: CIFilter.blendWithMask()

// Modern API (iOS 18+)
let request = GeneratePersonInstanceMaskRequest()
let observation = try await request.perform(on: cgImage)
let indices = observation.allInstances

for index in indices {
    let mask = try observation.generateMask(forInstances: IndexSet(integer: index))
    // mask is a CVPixelBuffer with only this person visible
}

// Legacy API (iOS 17+)
let request = VNGeneratePersonInstanceMaskRequest()
let handler = VNImageRequestHandler(cgImage: cgImage)
try handler.perform([request])

guard let result = request.results?.first else { return }
let indices = result.allInstances
for index in indices {
    let instanceMask = try result.generateMaskedImage(
        ofInstances: IndexSet(integer: index),
        from: handler,
        croppedToInstancesExtent: false
    )
}

// Initialize with a detected object's bounding box
let initialObservation = DetectedObjectObservation(boundingBox: detectedRect)
var request = TrackObjectRequest(observation: initialObservation)
request.trackingLevel = .accurate

// For each video frame:
let results = try await request.perform(on: pixelBuffer)
if let tracked = results.first {
    let updatedBounds = tracked.boundingBox
    let confidence = tracked.confidence
}

let trackRequest = VNTrackObjectRequest(detectedObjectObservation: initialObservation)
trackRequest.trackingLevel = .accurate

let sequenceHandler = VNSequenceRequestHandler()
// For each frame:
try sequenceHandler.perform([trackRequest], on: pixelBuffer)
if let result = trackRequest.results?.first {
    let updatedBounds = result.boundingBox
    trackRequest.inputObservation = result
}

// Modern API (iOS 18+)
let model = try MLModel(contentsOf: modelURL)
let request = CoreMLRequest(model: .init(model))
let results = try await request.perform(on: cgImage)

// Classification model
if let classification = results.first as? ClassificationObservation {
    let label = classification.identifier
    let confidence = classification.confidence
}

// Legacy API
let vnModel = try VNCoreMLModel(for: model)
let request = VNCoreMLRequest(model: vnModel) { request, error in
    guard let results = request.results as? [VNClassificationObservation] else { return }
    let topResult = results.first
}
let handler = VNImageRequestHandler(cgImage: cgImage)
try handler.perform([request])

import VisionKit

// Check availability (requires A12+ chip and camera)
guard DataScannerViewController.isSupported,
      DataScannerViewController.isAvailable else { return }

let scanner = DataScannerViewController(
    recognizedDataTypes: [
        .text(languages: ["en"]),
        .barcode(symbologies: [.qr, .ean13])
    ],
    qualityLevel: .balanced,
    recognizesMultipleItems: true,
    isHighFrameRateTrackingEnabled: true,
    isHighlightingEnabled: true
)
scanner.delegate = self
present(scanner, animated: true) {
    try? scanner.startScanning()
}