// LEADTOOLS: Four namespaces, four packages, six steps before recognition
using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath)); // Step 1: two files on disk
var codecs = new RasterCodecs();                              // Step 2: codec layer
var engine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD); // Step 3: engine factory
engine.Startup(codecs, null, null, runtimePath);              // Step 4: blocking startup
// ... still need to create document, add page, call Recognize(), extract text

// LEADTOOLS: Four namespaces, four packages, six steps before recognition
using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath)); // Step 1: two files on disk
var codecs = new RasterCodecs();                              // Step 2: codec layer
var engine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD); // Step 3: engine factory
engine.Startup(codecs, null, null, runtimePath);              // Step 4: blocking startup
// ... still need to create document, add page, call Recognize(), extract text

// IronOCR: One namespace, one package, one line
using IronOcr;

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
var text = new IronTesseract().Read("document.jpg").Text;

// IronOCR: One namespace, one package, one line
using IronOcr;

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
var text = new IronTesseract().Read("document.jpg").Text;

dotnet remove package Leadtools
dotnet remove package Leadtools.Ocr
dotnet remove package Leadtools.Codecs
dotnet remove package Leadtools.Forms.DocumentWriters
dotnet remove package Leadtools.Pdf

dotnet remove package Leadtools
dotnet remove package Leadtools.Ocr
dotnet remove package Leadtools.Codecs
dotnet remove package Leadtools.Forms.DocumentWriters
dotnet remove package Leadtools.Pdf

// Before (LEADTOOLS)
using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

// After (IronOCR)
using IronOcr;

// Before (LEADTOOLS)
using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

// After (IronOCR)
using IronOcr;

// Single line replaces the entire file-based license setup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Production pattern: pull from environment variable or secrets manager
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

// Single line replaces the entire file-based license setup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Production pattern: pull from environment variable or secrets manager
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

// Service class required purely to manage engine lifecycle
public class LeadtoolsOcrService : IDisposable
{
    private IOcrEngine _engine;
    private RasterCodecs _codecs;
    private readonly string _runtimePath;

    public LeadtoolsOcrService(string licPath, string keyPath, string runtimePath)
    {
        _runtimePath = runtimePath;

        // License setup — two files, both must be present
        RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath));

        // Codec layer — required before engine creation
        _codecs = new RasterCodecs();

        // Engine factory — engine type determines capability and cost
        _engine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD);

        // Blocking startup — loads runtime into memory (500–2000ms)
        _engine.Startup(_codecs, null, null, _runtimePath);
    }

    public bool IsReady => _engine?.IsStarted ?? false;

    public string Process(string imagePath)
    {
        if (!IsReady)
            throw new InvalidOperationException("Engine not started");

        using var image = _codecs.Load(imagePath);
        using var doc = _engine.DocumentManager.CreateDocument();
        var page = doc.Pages.AddPage(image, null);
        page.Recognize(null);
        return page.GetText(-1);
    }

    public void Dispose()
    {
        // Order is mandatory: Shutdown before Dispose
        if (_engine?.IsStarted == true)
            _engine.Shutdown();

        _engine?.Dispose();
        _codecs?.Dispose();
    }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

// Service class required purely to manage engine lifecycle
public class LeadtoolsOcrService : IDisposable
{
    private IOcrEngine _engine;
    private RasterCodecs _codecs;
    private readonly string _runtimePath;

    public LeadtoolsOcrService(string licPath, string keyPath, string runtimePath)
    {
        _runtimePath = runtimePath;

        // License setup — two files, both must be present
        RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath));

        // Codec layer — required before engine creation
        _codecs = new RasterCodecs();

        // Engine factory — engine type determines capability and cost
        _engine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD);

        // Blocking startup — loads runtime into memory (500–2000ms)
        _engine.Startup(_codecs, null, null, _runtimePath);
    }

    public bool IsReady => _engine?.IsStarted ?? false;

    public string Process(string imagePath)
    {
        if (!IsReady)
            throw new InvalidOperationException("Engine not started");

        using var image = _codecs.Load(imagePath);
        using var doc = _engine.DocumentManager.CreateDocument();
        var page = doc.Pages.AddPage(image, null);
        page.Recognize(null);
        return page.GetText(-1);
    }

    public void Dispose()
    {
        // Order is mandatory: Shutdown before Dispose
        if (_engine?.IsStarted == true)
            _engine.Shutdown();

        _engine?.Dispose();
        _codecs?.Dispose();
    }
}

using IronOcr;

// No lifecycle management needed — the service class becomes trivial
public class OcrService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    // Always ready — no IsStarted check needed
    public string Process(string imagePath) => _ocr.Read(imagePath).Text;

    // No Dispose() needed for the engine
    // No Startup(), no Shutdown(), no codec layer
}

using IronOcr;

// No lifecycle management needed — the service class becomes trivial
public class OcrService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    // Always ready — no IsStarted check needed
    public string Process(string imagePath) => _ocr.Read(imagePath).Text;

    // No Dispose() needed for the engine
    // No Startup(), no Shutdown(), no codec layer
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsTiffBatchService
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public List<string> ProcessMultiFrameTiff(string tiffPath)
    {
        var pageTexts = new List<string>();

        // Must query page count before iterating
        var info = _codecs.GetInformation(tiffPath, true);
        int frameCount = info.TotalPages;

        using var document = _engine.DocumentManager.CreateDocument();

        for (int frameNum = 1; frameNum <= frameCount; frameNum++)
        {
            // Load one frame at a time — must specify firstPage/lastPage
            using var frameImage = _codecs.Load(
                tiffPath,
                0,                            // bitsPerPixel
                CodecsLoadByteOrder.BgrOrGray,
                frameNum,                     // firstPage
                frameNum);                    // lastPage

            var page = document.Pages.AddPage(frameImage, null);
            page.Recognize(null);
            pageTexts.Add(page.GetText(-1));

            // GC pressure accumulates if disposal is missed on any frame
        }

        return pageTexts;
    }

    public Dictionary<string, List<string>> ProcessTiffDirectory(string directoryPath)
    {
        var results = new Dictionary<string, List<string>>();

        foreach (var tiffFile in Directory.GetFiles(directoryPath, "*.tiff"))
        {
            results[tiffFile] = ProcessMultiFrameTiff(tiffFile);

            // Manual GC between files to prevent memory growth
            GC.Collect();
            GC.WaitForPendingFinalizers();
        }

        return results;
    }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsTiffBatchService
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public List<string> ProcessMultiFrameTiff(string tiffPath)
    {
        var pageTexts = new List<string>();

        // Must query page count before iterating
        var info = _codecs.GetInformation(tiffPath, true);
        int frameCount = info.TotalPages;

        using var document = _engine.DocumentManager.CreateDocument();

        for (int frameNum = 1; frameNum <= frameCount; frameNum++)
        {
            // Load one frame at a time — must specify firstPage/lastPage
            using var frameImage = _codecs.Load(
                tiffPath,
                0,                            // bitsPerPixel
                CodecsLoadByteOrder.BgrOrGray,
                frameNum,                     // firstPage
                frameNum);                    // lastPage

            var page = document.Pages.AddPage(frameImage, null);
            page.Recognize(null);
            pageTexts.Add(page.GetText(-1));

            // GC pressure accumulates if disposal is missed on any frame
        }

        return pageTexts;
    }

    public Dictionary<string, List<string>> ProcessTiffDirectory(string directoryPath)
    {
        var results = new Dictionary<string, List<string>>();

        foreach (var tiffFile in Directory.GetFiles(directoryPath, "*.tiff"))
        {
            results[tiffFile] = ProcessMultiFrameTiff(tiffFile);

            // Manual GC between files to prevent memory growth
            GC.Collect();
            GC.WaitForPendingFinalizers();
        }

        return results;
    }
}

using IronOcr;

public class TiffBatchService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public List<string> ProcessMultiFrameTiff(string tiffPath)
    {
        using var input = new OcrInput();
        input.LoadImageFrames(tiffPath);  // All frames loaded automatically

        var result = _ocr.Read(input);

        // Per-frame text available through result.Pages
        return result.Pages.Select(p => p.Text).ToList();
    }

    public Dictionary<string, List<string>> ProcessTiffDirectory(string directoryPath)
    {
        var results = new Dictionary<string, List<string>>();

        foreach (var tiffFile in Directory.GetFiles(directoryPath, "*.tiff"))
        {
            results[tiffFile] = ProcessMultiFrameTiff(tiffFile);
        }

        return results;
    }

    // Parallel processing across files — thread-safe out of the box
    public Dictionary<string, List<string>> ProcessTiffDirectoryParallel(string directoryPath)
    {
        var concurrentResults = new System.Collections.Concurrent.ConcurrentDictionary<string, List<string>>();
        var tiffFiles = Directory.GetFiles(directoryPath, "*.tiff");

        Parallel.ForEach(tiffFiles, tiffFile =>
        {
            using var input = new OcrInput();
            input.LoadImageFrames(tiffFile);
            var result = new IronTesseract().Read(input);
            concurrentResults[tiffFile] = result.Pages.Select(p => p.Text).ToList();
        });

        return new Dictionary<string, List<string>>(concurrentResults);
    }
}

using IronOcr;

public class TiffBatchService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public List<string> ProcessMultiFrameTiff(string tiffPath)
    {
        using var input = new OcrInput();
        input.LoadImageFrames(tiffPath);  // All frames loaded automatically

        var result = _ocr.Read(input);

        // Per-frame text available through result.Pages
        return result.Pages.Select(p => p.Text).ToList();
    }

    public Dictionary<string, List<string>> ProcessTiffDirectory(string directoryPath)
    {
        var results = new Dictionary<string, List<string>>();

        foreach (var tiffFile in Directory.GetFiles(directoryPath, "*.tiff"))
        {
            results[tiffFile] = ProcessMultiFrameTiff(tiffFile);
        }

        return results;
    }

    // Parallel processing across files — thread-safe out of the box
    public Dictionary<string, List<string>> ProcessTiffDirectoryParallel(string directoryPath)
    {
        var concurrentResults = new System.Collections.Concurrent.ConcurrentDictionary<string, List<string>>();
        var tiffFiles = Directory.GetFiles(directoryPath, "*.tiff");

        Parallel.ForEach(tiffFiles, tiffFile =>
        {
            using var input = new OcrInput();
            input.LoadImageFrames(tiffFile);
            var result = new IronTesseract().Read(input);
            concurrentResults[tiffFile] = result.Pages.Select(p => p.Text).ToList();
        });

        return new Dictionary<string, List<string>>(concurrentResults);
    }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

public class LeadtoolsDocumentWriterService
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public void CreateSearchablePdfFromImages(string[] imagePaths, string outputPath)
    {
        using var document = _engine.DocumentManager.CreateDocument();

        foreach (var imagePath in imagePaths)
        {
            using var image = _codecs.Load(imagePath);
            var page = document.Pages.AddPage(image, null);
            page.Recognize(null);
        }

        // DocumentWriter configuration — four properties to set before save
        var pdfOptions = new PdfDocumentOptions
        {
            DocumentType = PdfDocumentType.Pdf,
            ImageOverText = true,     // Image layer visible, text layer searchable
            Linearized = false,
            Title = "Searchable Output"
        };

        // Apply options to the engine's writer instance
        _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);

        // Save with format enum — the format must match the options set above
        document.Save(outputPath, DocumentFormat.Pdf, null);
    }

    public void CreateSearchablePdfFromPdf(string inputPdfPath, string outputPath)
    {
        var pdfInfo = _codecs.GetInformation(inputPdfPath, true);
        using var document = _engine.DocumentManager.CreateDocument();

        for (int i = 1; i <= pdfInfo.TotalPages; i++)
        {
            using var pageImage = _codecs.Load(inputPdfPath, 0,
                CodecsLoadByteOrder.BgrOrGray, i, i);

            var page = document.Pages.AddPage(pageImage, null);
            page.Recognize(null);
        }

        var pdfOptions = new PdfDocumentOptions
        {
            DocumentType = PdfDocumentType.Pdf,
            ImageOverText = true,
            Title = Path.GetFileNameWithoutExtension(inputPdfPath)
        };

        _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);
        document.Save(outputPath, DocumentFormat.Pdf, null);
    }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

public class LeadtoolsDocumentWriterService
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public void CreateSearchablePdfFromImages(string[] imagePaths, string outputPath)
    {
        using var document = _engine.DocumentManager.CreateDocument();

        foreach (var imagePath in imagePaths)
        {
            using var image = _codecs.Load(imagePath);
            var page = document.Pages.AddPage(image, null);
            page.Recognize(null);
        }

        // DocumentWriter configuration — four properties to set before save
        var pdfOptions = new PdfDocumentOptions
        {
            DocumentType = PdfDocumentType.Pdf,
            ImageOverText = true,     // Image layer visible, text layer searchable
            Linearized = false,
            Title = "Searchable Output"
        };

        // Apply options to the engine's writer instance
        _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);

        // Save with format enum — the format must match the options set above
        document.Save(outputPath, DocumentFormat.Pdf, null);
    }

    public void CreateSearchablePdfFromPdf(string inputPdfPath, string outputPath)
    {
        var pdfInfo = _codecs.GetInformation(inputPdfPath, true);
        using var document = _engine.DocumentManager.CreateDocument();

        for (int i = 1; i <= pdfInfo.TotalPages; i++)
        {
            using var pageImage = _codecs.Load(inputPdfPath, 0,
                CodecsLoadByteOrder.BgrOrGray, i, i);

            var page = document.Pages.AddPage(pageImage, null);
            page.Recognize(null);
        }

        var pdfOptions = new PdfDocumentOptions
        {
            DocumentType = PdfDocumentType.Pdf,
            ImageOverText = true,
            Title = Path.GetFileNameWithoutExtension(inputPdfPath)
        };

        _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);
        document.Save(outputPath, DocumentFormat.Pdf, null);
    }
}

using IronOcr;

public class SearchablePdfService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public void CreateSearchablePdfFromImages(string[] imagePaths, string outputPath)
    {
        using var input = new OcrInput();
        foreach (var imagePath in imagePaths)
            input.LoadImage(imagePath);

        var result = _ocr.Read(input);
        result.SaveAsSearchablePdf(outputPath);  // DocumentWriter pipeline: gone
    }

    public void CreateSearchablePdfFromPdf(string inputPdfPath, string outputPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);

        var result = _ocr.Read(input);
        result.SaveAsSearchablePdf(outputPath);
    }

    // Get bytes directly — useful for streaming responses in ASP.NET
    public byte[] CreateSearchablePdfBytes(string inputPdfPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);
        return _ocr.Read(input).SaveAsSearchablePdfBytes();
    }
}

using IronOcr;

public class SearchablePdfService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public void CreateSearchablePdfFromImages(string[] imagePaths, string outputPath)
    {
        using var input = new OcrInput();
        foreach (var imagePath in imagePaths)
            input.LoadImage(imagePath);

        var result = _ocr.Read(input);
        result.SaveAsSearchablePdf(outputPath);  // DocumentWriter pipeline: gone
    }

    public void CreateSearchablePdfFromPdf(string inputPdfPath, string outputPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);

        var result = _ocr.Read(input);
        result.SaveAsSearchablePdf(outputPath);
    }

    // Get bytes directly — useful for streaming responses in ASP.NET
    public byte[] CreateSearchablePdfBytes(string inputPdfPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);
        return _ocr.Read(input).SaveAsSearchablePdfBytes();
    }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsFormFieldExtractor
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    // Invoice field extraction using named zones
    public InvoiceFields ExtractInvoiceFields(string invoicePath)
    {
        using var image = _codecs.Load(invoicePath);
        using var document = _engine.DocumentManager.CreateDocument();
        var page = document.Pages.AddPage(image, null);

        // Must clear auto-detected zones before adding custom ones
        page.Zones.Clear();

        // Zone definitions — index order matters for extraction
        var zoneDefinitions = new[]
        {
            new { Name = "InvoiceNumber", X = 450, Y = 80,  W = 200, H = 30 },
            new { Name = "InvoiceDate",   X = 450, Y = 115, W = 200, H = 30 },
            new { Name = "VendorName",    X = 50,  Y = 150, W = 300, H = 40 },
            new { Name = "TotalAmount",   X = 450, Y = 600, W = 200, H = 30 }
        };

        foreach (var def in zoneDefinitions)
        {
            var zone = new OcrZone
            {
                Bounds = new LeadRect(def.X, def.Y, def.W, def.H),
                ZoneType = OcrZoneType.Text,
                CharacterFilters = OcrZoneCharacterFilters.None,
                RecognitionModule = OcrZoneRecognitionModule.Auto
            };
            page.Zones.Add(zone);
        }

        page.Recognize(null);

        // Extract by index — must match insertion order exactly
        return new InvoiceFields
        {
            InvoiceNumber = page.Zones[0].Text?.Trim(),
            InvoiceDate   = page.Zones[1].Text?.Trim(),
            VendorName    = page.Zones[2].Text?.Trim(),
            TotalAmount   = page.Zones[3].Text?.Trim()
        };
    }
}

public class InvoiceFields
{
    public string InvoiceNumber { get; set; }
    public string InvoiceDate   { get; set; }
    public string VendorName    { get; set; }
    public string TotalAmount   { get; set; }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsFormFieldExtractor
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    // Invoice field extraction using named zones
    public InvoiceFields ExtractInvoiceFields(string invoicePath)
    {
        using var image = _codecs.Load(invoicePath);
        using var document = _engine.DocumentManager.CreateDocument();
        var page = document.Pages.AddPage(image, null);

        // Must clear auto-detected zones before adding custom ones
        page.Zones.Clear();

        // Zone definitions — index order matters for extraction
        var zoneDefinitions = new[]
        {
            new { Name = "InvoiceNumber", X = 450, Y = 80,  W = 200, H = 30 },
            new { Name = "InvoiceDate",   X = 450, Y = 115, W = 200, H = 30 },
            new { Name = "VendorName",    X = 50,  Y = 150, W = 300, H = 40 },
            new { Name = "TotalAmount",   X = 450, Y = 600, W = 200, H = 30 }
        };

        foreach (var def in zoneDefinitions)
        {
            var zone = new OcrZone
            {
                Bounds = new LeadRect(def.X, def.Y, def.W, def.H),
                ZoneType = OcrZoneType.Text,
                CharacterFilters = OcrZoneCharacterFilters.None,
                RecognitionModule = OcrZoneRecognitionModule.Auto
            };
            page.Zones.Add(zone);
        }

        page.Recognize(null);

        // Extract by index — must match insertion order exactly
        return new InvoiceFields
        {
            InvoiceNumber = page.Zones[0].Text?.Trim(),
            InvoiceDate   = page.Zones[1].Text?.Trim(),
            VendorName    = page.Zones[2].Text?.Trim(),
            TotalAmount   = page.Zones[3].Text?.Trim()
        };
    }
}

public class InvoiceFields
{
    public string InvoiceNumber { get; set; }
    public string InvoiceDate   { get; set; }
    public string VendorName    { get; set; }
    public string TotalAmount   { get; set; }
}

using IronOcr;

public class FormFieldExtractor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    // Each field gets its own CropRectangle-scoped Read() call
    // No zone index management, no zone ordering dependency
    public InvoiceFields ExtractInvoiceFields(string invoicePath)
    {
        return new InvoiceFields
        {
            InvoiceNumber = ReadRegion(invoicePath, 450, 80,  200, 30),
            InvoiceDate   = ReadRegion(invoicePath, 450, 115, 200, 30),
            VendorName    = ReadRegion(invoicePath, 50,  150, 300, 40),
            TotalAmount   = ReadRegion(invoicePath, 450, 600, 200, 30)
        };
    }

    private string ReadRegion(string imagePath, int x, int y, int width, int height)
    {
        using var input = new OcrInput();
        input.LoadImage(imagePath, new CropRectangle(x, y, width, height));
        return _ocr.Read(input).Text.Trim();
    }

    // Batch: extract the same field from many invoices in parallel
    public Dictionary<string, string> ExtractInvoiceNumbersBatch(string[] invoicePaths)
    {
        var results = new System.Collections.Concurrent.ConcurrentDictionary<string, string>();

        Parallel.ForEach(invoicePaths, invoicePath =>
        {
            using var input = new OcrInput();
            input.LoadImage(invoicePath, new CropRectangle(450, 80, 200, 30));
            results[invoicePath] = new IronTesseract().Read(input).Text.Trim();
        });

        return new Dictionary<string, string>(results);
    }
}

using IronOcr;

public class FormFieldExtractor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    // Each field gets its own CropRectangle-scoped Read() call
    // No zone index management, no zone ordering dependency
    public InvoiceFields ExtractInvoiceFields(string invoicePath)
    {
        return new InvoiceFields
        {
            InvoiceNumber = ReadRegion(invoicePath, 450, 80,  200, 30),
            InvoiceDate   = ReadRegion(invoicePath, 450, 115, 200, 30),
            VendorName    = ReadRegion(invoicePath, 50,  150, 300, 40),
            TotalAmount   = ReadRegion(invoicePath, 450, 600, 200, 30)
        };
    }

    private string ReadRegion(string imagePath, int x, int y, int width, int height)
    {
        using var input = new OcrInput();
        input.LoadImage(imagePath, new CropRectangle(x, y, width, height));
        return _ocr.Read(input).Text.Trim();
    }

    // Batch: extract the same field from many invoices in parallel
    public Dictionary<string, string> ExtractInvoiceNumbersBatch(string[] invoicePaths)
    {
        var results = new System.Collections.Concurrent.ConcurrentDictionary<string, string>();

        Parallel.ForEach(invoicePaths, invoicePath =>
        {
            using var input = new OcrInput();
            input.LoadImage(invoicePath, new CropRectangle(450, 80, 200, 30));
            results[invoicePath] = new IronTesseract().Read(input).Text.Trim();
        });

        return new Dictionary<string, string>(results);
    }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsStructuredExtractor
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public List<WordLocation> ExtractWordsWithLocations(string imagePath)
    {
        var wordLocations = new List<WordLocation>();

        using var image = _codecs.Load(imagePath);
        using var document = _engine.DocumentManager.CreateDocument();
        var page = document.Pages.AddPage(image, null);
        page.Recognize(null);

        // Access words through the zone collection
        foreach (OcrZone zone in page.Zones)
        {
            foreach (OcrWord word in zone.Words)
            {
                wordLocations.Add(new WordLocation
                {
                    Text       = word.Value,
                    X          = word.Bounds.X,
                    Y          = word.Bounds.Y,
                    Width      = word.Bounds.Width,
                    Height     = word.Bounds.Height,
                    Confidence = word.Confidence
                });
            }
        }

        return wordLocations;
    }
}

public class WordLocation
{
    public string Text       { get; set; }
    public int    X          { get; set; }
    public int    Y          { get; set; }
    public int    Width      { get; set; }
    public int    Height     { get; set; }
    public int    Confidence { get; set; }
}

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsStructuredExtractor
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public List<WordLocation> ExtractWordsWithLocations(string imagePath)
    {
        var wordLocations = new List<WordLocation>();

        using var image = _codecs.Load(imagePath);
        using var document = _engine.DocumentManager.CreateDocument();
        var page = document.Pages.AddPage(image, null);
        page.Recognize(null);

        // Access words through the zone collection
        foreach (OcrZone zone in page.Zones)
        {
            foreach (OcrWord word in zone.Words)
            {
                wordLocations.Add(new WordLocation
                {
                    Text       = word.Value,
                    X          = word.Bounds.X,
                    Y          = word.Bounds.Y,
                    Width      = word.Bounds.Width,
                    Height     = word.Bounds.Height,
                    Confidence = word.Confidence
                });
            }
        }

        return wordLocations;
    }
}

public class WordLocation
{
    public string Text       { get; set; }
    public int    X          { get; set; }
    public int    Y          { get; set; }
    public int    Width      { get; set; }
    public int    Height     { get; set; }
    public int    Confidence { get; set; }
}

using IronOcr;

public class StructuredExtractor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public List<WordLocation> ExtractWordsWithLocations(string imagePath)
    {
        var result = _ocr.Read(imagePath);

        // Five-level hierarchy: Pages > Paragraphs > Lines > Words > Characters
        return result.Pages
            .SelectMany(page => page.Paragraphs)
            .SelectMany(para => para.Lines)
            .SelectMany(line => line.Words)
            .Select(word => new WordLocation
            {
                Text       = word.Text,
                X          = word.X,
                Y          = word.Y,
                Width      = word.Width,
                Height     = word.Height,
                Confidence = (int)word.Confidence
            })
            .ToList();
    }

    // Paragraph-level extraction with position data
    public void PrintDocumentStructure(string imagePath)
    {
        var result = _ocr.Read(imagePath);
        Console.WriteLine($"Document confidence: {result.Confidence}%");

        foreach (var page in result.Pages)
        {
            Console.WriteLine($"Page {page.PageNumber}:");
            foreach (var paragraph in page.Paragraphs)
            {
                Console.WriteLine($"  Paragraph at ({paragraph.X}, {paragraph.Y}):");
                Console.WriteLine($"  {paragraph.Text}");
            }
        }
    }
}

using IronOcr;

public class StructuredExtractor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public List<WordLocation> ExtractWordsWithLocations(string imagePath)
    {
        var result = _ocr.Read(imagePath);

        // Five-level hierarchy: Pages > Paragraphs > Lines > Words > Characters
        return result.Pages
            .SelectMany(page => page.Paragraphs)
            .SelectMany(para => para.Lines)
            .SelectMany(line => line.Words)
            .Select(word => new WordLocation
            {
                Text       = word.Text,
                X          = word.X,
                Y          = word.Y,
                Width      = word.Width,
                Height     = word.Height,
                Confidence = (int)word.Confidence
            })
            .ToList();
    }

    // Paragraph-level extraction with position data
    public void PrintDocumentStructure(string imagePath)
    {
        var result = _ocr.Read(imagePath);
        Console.WriteLine($"Document confidence: {result.Confidence}%");

        foreach (var page in result.Pages)
        {
            Console.WriteLine($"Page {page.PageNumber}:");
            foreach (var paragraph in page.Paragraphs)
            {
                Console.WriteLine($"  Paragraph at ({paragraph.X}, {paragraph.Y}):");
                Console.WriteLine($"  {paragraph.Text}");
            }
        }
    }
}

// Remove this:
// RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath));

// Replace with this:
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")
    ?? throw new InvalidOperationException("IRONOCR_LICENSE environment variable not set");

// Remove this:
// RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath));

// Replace with this:
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")
    ?? throw new InvalidOperationException("IRONOCR_LICENSE environment variable not set");

// Remove the guard:
// if (!_engine.IsStarted)
//     throw new InvalidOperationException("Engine not started");

// IronTesseract is always ready — just call Read()
var result = _ocr.Read(imagePath);

// Remove the guard:
// if (!_engine.IsStarted)
//     throw new InvalidOperationException("Engine not started");

// IronTesseract is always ready — just call Read()
var result = _ocr.Read(imagePath);

// Remove this pattern:
// GC.Collect();
// GC.WaitForPendingFinalizers();

// Replace with standard using scope:
foreach (var filePath in filePaths)
{
    using var input = new OcrInput();
    input.LoadImage(filePath);
    var text = _ocr.Read(input).Text;
    // input disposed here — no accumulation
}

// Remove this pattern:
// GC.Collect();
// GC.WaitForPendingFinalizers();

// Replace with standard using scope:
foreach (var filePath in filePaths)
{
    using var input = new OcrInput();
    input.LoadImage(filePath);
    var text = _ocr.Read(input).Text;
    // input disposed here — no accumulation
}

// Remove the options setup:
// var pdfOptions = new PdfDocumentOptions { ... };
// _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);
// document.Save(outputPath, DocumentFormat.Pdf, null);

// Replace with:
result.SaveAsSearchablePdf(outputPath);

// Remove the options setup:
// var pdfOptions = new PdfDocumentOptions { ... };
// _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);
// document.Save(outputPath, DocumentFormat.Pdf, null);

// Replace with:
result.SaveAsSearchablePdf(outputPath);

// Each field is independent — reorder freely without breaking extraction
var invoiceNumber = ReadRegion(imagePath, 450, 80,  200, 30);
var invoiceDate   = ReadRegion(imagePath, 450, 115, 200, 30);
var vendorName    = ReadRegion(imagePath, 50,  150, 300, 40);
var totalAmount   = ReadRegion(imagePath, 450, 600, 200, 30);

// Each field is independent — reorder freely without breaking extraction
var invoiceNumber = ReadRegion(imagePath, 450, 80,  200, 30);
var invoiceDate   = ReadRegion(imagePath, 450, 115, 200, 30);
var vendorName    = ReadRegion(imagePath, 50,  150, 300, 40);
var totalAmount   = ReadRegion(imagePath, 450, 600, 200, 30);

# Find all LEADTOOLS namespace imports
grep -rn "using Leadtools" --include="*.cs" .

# Find engine lifecycle calls
grep -rn "OcrEngineManager\|\.Startup(\|\.Shutdown()" --include="*.cs" .

# Find license file references
grep -rn "SetLicense\|LEADTOOLS\.LIC\|\.LIC\.KEY" --include="*.cs" .

# Find RasterCodecs usage
grep -rn "RasterCodecs\|_codecs\.Load\|GetInformation" --include="*.cs" .

# Find DocumentWriter usage
grep -rn "DocumentWriterInstance\|PdfDocumentOptions\|DocumentFormat\." --include="*.cs" .

# Find zone-based OCR
grep -rn "OcrZone\|page\.Zones\|LeadRect\|ZoneType" --include="*.cs" .

# Find GC workarounds to remove
grep -rn "GC\.Collect\|WaitForPendingFinalizers" --include="*.cs" .

# Find all LEADTOOLS namespace imports
grep -rn "using Leadtools" --include="*.cs" .

# Find engine lifecycle calls
grep -rn "OcrEngineManager\|\.Startup(\|\.Shutdown()" --include="*.cs" .

# Find license file references
grep -rn "SetLicense\|LEADTOOLS\.LIC\|\.LIC\.KEY" --include="*.cs" .

# Find RasterCodecs usage
grep -rn "RasterCodecs\|_codecs\.Load\|GetInformation" --include="*.cs" .

# Find DocumentWriter usage
grep -rn "DocumentWriterInstance\|PdfDocumentOptions\|DocumentFormat\." --include="*.cs" .

# Find zone-based OCR
grep -rn "OcrZone\|page\.Zones\|LeadRect\|ZoneType" --include="*.cs" .

# Find GC workarounds to remove
grep -rn "GC\.Collect\|WaitForPendingFinalizers" --include="*.cs" .