// Syncfusion: tessdata path required — fails in any environment where this path is wrong
private const string TessDataPath = @"tessdata/";

using var document = new PdfLoadedDocument("scanned-invoice.pdf");
using var processor = new OCRProcessor(TessDataPath);  // throws if path does not resolve
processor.Settings.Language = Languages.English;
processor.PerformOCR(document);

var text = new StringBuilder();
foreach (PdfLoadedPage page in document.Pages)
    text.AppendLine(page.ExtractText());

// Syncfusion: tessdata path required — fails in any environment where this path is wrong
private const string TessDataPath = @"tessdata/";

using var document = new PdfLoadedDocument("scanned-invoice.pdf");
using var processor = new OCRProcessor(TessDataPath);  // throws if path does not resolve
processor.Settings.Language = Languages.English;
processor.PerformOCR(document);

var text = new StringBuilder();
foreach (PdfLoadedPage page in document.Pages)
    text.AppendLine(page.ExtractText());

// IronOCR: no tessdata path, no path configuration, no folder to deploy
var text = new IronTesseract().Read("scanned-invoice.pdf").Text;

// IronOCR: no tessdata path, no path configuration, no folder to deploy
var text = new IronTesseract().Read("scanned-invoice.pdf").Text;

dotnet remove package Syncfusion.PDF.OCR.Net.Core
dotnet remove package Syncfusion.Pdf.Net.Core
dotnet remove package Syncfusion.Compression.Net.Core

dotnet remove package Syncfusion.PDF.OCR.Net.Core
dotnet remove package Syncfusion.Pdf.Net.Core
dotnet remove package Syncfusion.Compression.Net.Core

// Before (Syncfusion)
using Syncfusion.OCRProcessor;
using Syncfusion.PDF;
using Syncfusion.Pdf.Parsing;

// After (IronOCR)
using IronOcr;

// Before (Syncfusion)
using Syncfusion.OCRProcessor;
using Syncfusion.PDF;
using Syncfusion.Pdf.Parsing;

// After (IronOCR)
using IronOcr;

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class DocumentOcrService
{
    // Path hardcoded — different on every deployment target
    private const string TessDataPath = @"tessdata/";

    private bool ValidateTessdataBeforeUse(string languageCode)
    {
        // Guard required because missing files cause runtime exceptions
        if (!Directory.Exists(TessDataPath))
            throw new InvalidOperationException(
                "tessdata directory not found. Download from github.com/tesseract-ocr/tessdata_best");

        string filePath = Path.Combine(TessDataPath, $"{languageCode}.traineddata");
        if (!File.Exists(filePath))
            throw new InvalidOperationException(
                $"{languageCode}.traineddata not found — file must be downloaded manually");

        return true;
    }

    public string ExtractText(string pdfPath, string languageCode = "eng")
    {
        ValidateTessdataBeforeUse(languageCode);  // defensive check before every call

        using var document = new PdfLoadedDocument(pdfPath);
        using var processor = new OCRProcessor(TessDataPath);
        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        var sb = new StringBuilder();
        foreach (PdfLoadedPage page in document.Pages)
            sb.AppendLine(page.ExtractText());

        return sb.ToString();
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class DocumentOcrService
{
    // Path hardcoded — different on every deployment target
    private const string TessDataPath = @"tessdata/";

    private bool ValidateTessdataBeforeUse(string languageCode)
    {
        // Guard required because missing files cause runtime exceptions
        if (!Directory.Exists(TessDataPath))
            throw new InvalidOperationException(
                "tessdata directory not found. Download from github.com/tesseract-ocr/tessdata_best");

        string filePath = Path.Combine(TessDataPath, $"{languageCode}.traineddata");
        if (!File.Exists(filePath))
            throw new InvalidOperationException(
                $"{languageCode}.traineddata not found — file must be downloaded manually");

        return true;
    }

    public string ExtractText(string pdfPath, string languageCode = "eng")
    {
        ValidateTessdataBeforeUse(languageCode);  // defensive check before every call

        using var document = new PdfLoadedDocument(pdfPath);
        using var processor = new OCRProcessor(TessDataPath);
        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        var sb = new StringBuilder();
        foreach (PdfLoadedPage page in document.Pages)
            sb.AppendLine(page.ExtractText());

        return sb.ToString();
    }
}

using IronOcr;

public class DocumentOcrService
{
    //Neintessdata path — no validation logic — no defensive checks
    public string ExtractText(string pdfPath)
    {
        return new IronTesseract().Read(pdfPath).Text;
    }
}

using IronOcr;

public class DocumentOcrService
{
    //Neintessdata path — no validation logic — no defensive checks
    public string ExtractText(string pdfPath)
    {
        return new IronTesseract().Read(pdfPath).Text;
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class SearchablePdfService
{
    private const string TessDataPath = @"tessdata/";

    public void ConvertToSearchable(string inputPdfPath, string outputPdfPath)
    {
        // Load document — mutable: PerformOCR modifies it in place
        using var document = new PdfLoadedDocument(inputPdfPath);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;

        // Step 1: OCR modifies the document object
        processor.PerformOCR(document);

        // Step 2: Save the modified document to a separate output file
        using var outputStream = new FileStream(outputPdfPath, FileMode.Create, FileAccess.Write);
        document.Save(outputStream);
    }

    public byte[] ConvertToSearchableBytes(string inputPdfPath)
    {
        using var document = new PdfLoadedDocument(inputPdfPath);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        using var outputStream = new MemoryStream();
        document.Save(outputStream);
        return outputStream.ToArray();
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class SearchablePdfService
{
    private const string TessDataPath = @"tessdata/";

    public void ConvertToSearchable(string inputPdfPath, string outputPdfPath)
    {
        // Load document — mutable: PerformOCR modifies it in place
        using var document = new PdfLoadedDocument(inputPdfPath);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;

        // Step 1: OCR modifies the document object
        processor.PerformOCR(document);

        // Step 2: Save the modified document to a separate output file
        using var outputStream = new FileStream(outputPdfPath, FileMode.Create, FileAccess.Write);
        document.Save(outputStream);
    }

    public byte[] ConvertToSearchableBytes(string inputPdfPath)
    {
        using var document = new PdfLoadedDocument(inputPdfPath);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        using var outputStream = new MemoryStream();
        document.Save(outputStream);
        return outputStream.ToArray();
    }
}

using IronOcr;

public class SearchablePdfService
{
    public void ConvertToSearchable(string inputPdfPath, string outputPdfPath)
    {
        var result = new IronTesseract().Read(inputPdfPath);
        result.SaveAsSearchablePdf(outputPdfPath);
    }

    public byte[] ConvertToSearchableBytes(string inputPdfPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);

        var result = new IronTesseract().Read(input);

        // SaveAsSearchablePdf also accepts a MemoryStream
        using var ms = new MemoryStream();
        result.SaveAsSearchablePdf(ms);
        return ms.ToArray();
    }
}

using IronOcr;

public class SearchablePdfService
{
    public void ConvertToSearchable(string inputPdfPath, string outputPdfPath)
    {
        var result = new IronTesseract().Read(inputPdfPath);
        result.SaveAsSearchablePdf(outputPdfPath);
    }

    public byte[] ConvertToSearchableBytes(string inputPdfPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);

        var result = new IronTesseract().Read(input);

        // SaveAsSearchablePdf also accepts a MemoryStream
        using var ms = new MemoryStream();
        result.SaveAsSearchablePdf(ms);
        return ms.ToArray();
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class StreamOcrService
{
    private const string TessDataPath = @"tessdata/";

    public string ExtractFromStream(Stream pdfStream)
    {
        // Stream input works, but tessdata path constraint remains
        using var document = new PdfLoadedDocument(pdfStream);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        var sb = new StringBuilder();
        foreach (PdfLoadedPage page in document.Pages)
            sb.AppendLine(page.ExtractText());

        return sb.ToString();
    }

    public async Task<string> ExtractFromStreamAsync(Stream pdfStream)
    {
        //Neinnative async — must wrap in Task.Run
        return await Task.Run(() => ExtractFromStream(pdfStream));
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class StreamOcrService
{
    private const string TessDataPath = @"tessdata/";

    public string ExtractFromStream(Stream pdfStream)
    {
        // Stream input works, but tessdata path constraint remains
        using var document = new PdfLoadedDocument(pdfStream);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        var sb = new StringBuilder();
        foreach (PdfLoadedPage page in document.Pages)
            sb.AppendLine(page.ExtractText());

        return sb.ToString();
    }

    public async Task<string> ExtractFromStreamAsync(Stream pdfStream)
    {
        //Neinnative async — must wrap in Task.Run
        return await Task.Run(() => ExtractFromStream(pdfStream));
    }
}

using IronOcr;

public class StreamOcrService
{
    public string ExtractFromStream(Stream pdfStream)
    {
        using var input = new OcrInput();
        input.LoadPdf(pdfStream);    // accepts Stream directly

        return new IronTesseract().Read(input).Text;
    }

    public async Task<string> ExtractFromStreamAsync(Stream pdfStream)
    {
        using var input = new OcrInput();
        input.LoadPdf(pdfStream);

        var ocr = new IronTesseract();
        var result = await ocr.ReadAsync(input);   // native async support
        return result.Text;
    }
}

using IronOcr;

public class StreamOcrService
{
    public string ExtractFromStream(Stream pdfStream)
    {
        using var input = new OcrInput();
        input.LoadPdf(pdfStream);    // accepts Stream directly

        return new IronTesseract().Read(input).Text;
    }

    public async Task<string> ExtractFromStreamAsync(Stream pdfStream)
    {
        using var input = new OcrInput();
        input.LoadPdf(pdfStream);

        var ocr = new IronTesseract();
        var result = await ocr.ReadAsync(input);   // native async support
        return result.Text;
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class StructuredExtractionService
{
    private const string TessDataPath = @"tessdata/";

    public Dictionary<int, string> ExtractPerPage(string pdfPath)
    {
        var pageTexts = new Dictionary<int, string>();

        using var document = new PdfLoadedDocument(pdfPath);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        // Page-level is the finest granularity available
        int pageNum = 1;
        foreach (PdfLoadedPage page in document.Pages)
        {
            pageTexts[pageNum] = page.ExtractText();
            pageNum++;
        }

        return pageTexts;
        //Neinword coordinates, no paragraph boundaries, no per-token confidence
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class StructuredExtractionService
{
    private const string TessDataPath = @"tessdata/";

    public Dictionary<int, string> ExtractPerPage(string pdfPath)
    {
        var pageTexts = new Dictionary<int, string>();

        using var document = new PdfLoadedDocument(pdfPath);
        using var processor = new OCRProcessor(TessDataPath);

        processor.Settings.Language = Languages.English;
        processor.PerformOCR(document);

        // Page-level is the finest granularity available
        int pageNum = 1;
        foreach (PdfLoadedPage page in document.Pages)
        {
            pageTexts[pageNum] = page.ExtractText();
            pageNum++;
        }

        return pageTexts;
        //Neinword coordinates, no paragraph boundaries, no per-token confidence
    }
}

using IronOcr;

public class StructuredExtractionService
{
    public void ExtractWithStructure(string pdfPath)
    {
        var result = new IronTesseract().Read(pdfPath);

        Console.WriteLine($"Overall confidence: {result.Confidence}%");

        foreach (var page in result.Pages)
        {
            Console.WriteLine($"Page {page.PageNumber}: {page.Words.Length} words");

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

    public IEnumerable<string> ExtractHighConfidenceWords(string pdfPath, int minConfidence = 80)
    {
        var result = new IronTesseract().Read(pdfPath);

        // Per-word confidence filtering — not possible with Syncfusion's page-level model
        return result.Pages
            .SelectMany(p => p.Words)
            .Where(w => w.Confidence >= minConfidence)
            .Select(w => w.Text);
    }
}

using IronOcr;

public class StructuredExtractionService
{
    public void ExtractWithStructure(string pdfPath)
    {
        var result = new IronTesseract().Read(pdfPath);

        Console.WriteLine($"Overall confidence: {result.Confidence}%");

        foreach (var page in result.Pages)
        {
            Console.WriteLine($"Page {page.PageNumber}: {page.Words.Length} words");

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

    public IEnumerable<string> ExtractHighConfidenceWords(string pdfPath, int minConfidence = 80)
    {
        var result = new IronTesseract().Read(pdfPath);

        // Per-word confidence filtering — not possible with Syncfusion's page-level model
        return result.Pages
            .SelectMany(p => p.Words)
            .Where(w => w.Confidence >= minConfidence)
            .Select(w => w.Text);
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class BatchOcrService
{
    private const string TessDataPath = @"tessdata/";

    public Dictionary<string, string> ProcessBatch(IEnumerable<string> pdfPaths)
    {
        var results = new Dictionary<string, string>();

        // Sequential processing — OCRProcessor thread safety not guaranteed
        foreach (var path in pdfPaths)
        {
            using var document = new PdfLoadedDocument(path);
            using var processor = new OCRProcessor(TessDataPath);

            processor.Settings.Language = Languages.English;
            processor.PerformOCR(document);

            var sb = new StringBuilder();
            foreach (PdfLoadedPage page in document.Pages)
                sb.AppendLine(page.ExtractText());

            results[path] = sb.ToString();
        }

        return results;
    }
}

using Syncfusion.OCRProcessor;
using Syncfusion.Pdf.Parsing;

public class BatchOcrService
{
    private const string TessDataPath = @"tessdata/";

    public Dictionary<string, string> ProcessBatch(IEnumerable<string> pdfPaths)
    {
        var results = new Dictionary<string, string>();

        // Sequential processing — OCRProcessor thread safety not guaranteed
        foreach (var path in pdfPaths)
        {
            using var document = new PdfLoadedDocument(path);
            using var processor = new OCRProcessor(TessDataPath);

            processor.Settings.Language = Languages.English;
            processor.PerformOCR(document);

            var sb = new StringBuilder();
            foreach (PdfLoadedPage page in document.Pages)
                sb.AppendLine(page.ExtractText());

            results[path] = sb.ToString();
        }

        return results;
    }
}

using IronOcr;

public class BatchOcrService
{
    public Dictionary<string, string> ProcessBatch(IEnumerable<string> pdfPaths)
    {
        var results = new ConcurrentDictionary<string, string>();

        // Parallel processing — IronTesseract is safe per-thread
        Parallel.ForEach(pdfPaths, pdfPath =>
        {
            var ocr = new IronTesseract();   // one instance per thread
            var text = ocr.Read(pdfPath).Text;
            results[pdfPath] = text;
        });

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

using IronOcr;

public class BatchOcrService
{
    public Dictionary<string, string> ProcessBatch(IEnumerable<string> pdfPaths)
    {
        var results = new ConcurrentDictionary<string, string>();

        // Parallel processing — IronTesseract is safe per-thread
        Parallel.ForEach(pdfPaths, pdfPath =>
        {
            var ocr = new IronTesseract();   // one instance per thread
            var text = ocr.Read(pdfPath).Text;
            results[pdfPath] = text;
        });

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

// Delete these entirely — they have no equivalent in IronOCR
// private const string TessDataPath = @"tessdata/";
// private bool ValidateTessdata() { ... }

// The only error handling needed after migration:
try
{
    return new IronTesseract().Read(pdfPath).Text;
}
catch (FileNotFoundException)
{
    throw new ArgumentException($"PDF file not found: {pdfPath}");
}

// Delete these entirely — they have no equivalent in IronOCR
// private const string TessDataPath = @"tessdata/";
// private bool ValidateTessdata() { ... }

// The only error handling needed after migration:
try
{
    return new IronTesseract().Read(pdfPath).Text;
}
catch (FileNotFoundException)
{
    throw new ArgumentException($"PDF file not found: {pdfPath}");
}

# Languages install as NuGet packages — no manual file management
dotnet add package IronOcr.Languages.French
dotnet add package IronOcr.Languages.German
dotnet add package IronOcr.Languages.ChineseSimplified

# Languages install as NuGet packages — no manual file management
dotnet add package IronOcr.Languages.French
dotnet add package IronOcr.Languages.German
dotnet add package IronOcr.Languages.ChineseSimplified

// Language configuration after migration
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.French;
ocr.AddSecondaryLanguage(OcrLanguage.German);
var result = ocr.Read("multilingual-report.pdf");

// Language configuration after migration
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.French;
ocr.AddSecondaryLanguage(OcrLanguage.German);
var result = ocr.Read("multilingual-report.pdf");

// Verify the searchable PDF contains the expected text
var result = new IronTesseract().Read("scanned.pdf");
result.SaveAsSearchablePdf("output-searchable.pdf");

// Validation: confirm text layer is present and readable
var verificationText = new IronTesseract().Read("output-searchable.pdf").Text;
Assert.True(verificationText.Contains("expected content"));

// Verify the searchable PDF contains the expected text
var result = new IronTesseract().Read("scanned.pdf");
result.SaveAsSearchablePdf("output-searchable.pdf");

// Validation: confirm text layer is present and readable
var verificationText = new IronTesseract().Read("output-searchable.pdf").Text;
Assert.True(verificationText.Contains("expected content"));

# Entfernen this layer entirely after migration
# COPY tessdata/ /app/tessdata/

#IronOCR requires only the standard .NET runtime
FROM mcr.microsoft.com/dotnet/aspnet:8.0 AS runtime
WORKDIR /app
COPY --from=build /app/publish .
ENTRYPOINT ["dotnet", "YourService.dll"]

# Entfernen this layer entirely after migration
# COPY tessdata/ /app/tessdata/

#IronOCR requires only the standard .NET runtime
FROM mcr.microsoft.com/dotnet/aspnet:8.0 AS runtime
WORKDIR /app
COPY --from=build /app/publish .
ENTRYPOINT ["dotnet", "YourService.dll"]

// Replace split PerformOCR / ExtractText pattern
public OcrResult ProcessDocument(string pdfPath)
{
    // One call, immutable result, all data available
    return new IronTesseract().Read(pdfPath);
}

// Callers decide what they need from the result
var result = service.ProcessDocument("contract.pdf");
var fullText = result.Text;
var confidence = result.Confidence;
result.SaveAsSearchablePdf("contract-searchable.pdf");

// Replace split PerformOCR / ExtractText pattern
public OcrResult ProcessDocument(string pdfPath)
{
    // One call, immutable result, all data available
    return new IronTesseract().Read(pdfPath);
}

// Callers decide what they need from the result
var result = service.ProcessDocument("contract.pdf");
var fullText = result.Text;
var confidence = result.Confidence;
result.SaveAsSearchablePdf("contract-searchable.pdf");

// Entfernen (causes compile error after package removal)
// Syncfusion.Licensing.SyncfusionLicenseProvider.RegisterLicense("SYNCFUSION-KEY");

// Add at application startup
IronOcr.License.LicenseKey = "YOUR-IRONOCR-KEY";

// Entfernen (causes compile error after package removal)
// Syncfusion.Licensing.SyncfusionLicenseProvider.RegisterLicense("SYNCFUSION-KEY");

// Add at application startup
IronOcr.License.LicenseKey = "YOUR-IRONOCR-KEY";

# Find all Syncfusion namespace imports
grep -r "using Syncfusion" --include="*.cs" .

# Find OCRProcessor usage
grep -r "OCRProcessor\|PerformOCR\|PdfLoadedDocument\|ExtractText" --include="*.cs" .

# Find tessdata path references
grep -r "TessDataPath\|tessdata\|traineddata" --include="*.cs" .

# Find Syncfusion license registration
grep -r "SyncfusionLicenseProvider\|RegisterLicense" --include="*.cs" .

# Find csproj tessdata copy rules
grep -r "tessdata\|traineddata" --include="*.csproj" .

# Find Dockerfile tessdata layers
grep -r "tessdata" Dockerfile* docker-compose*.yml .

# Find all Syncfusion namespace imports
grep -r "using Syncfusion" --include="*.cs" .

# Find OCRProcessor usage
grep -r "OCRProcessor\|PerformOCR\|PdfLoadedDocument\|ExtractText" --include="*.cs" .

# Find tessdata path references
grep -r "TessDataPath\|tessdata\|traineddata" --include="*.cs" .

# Find Syncfusion license registration
grep -r "SyncfusionLicenseProvider\|RegisterLicense" --include="*.cs" .

# Find csproj tessdata copy rules
grep -r "tessdata\|traineddata" --include="*.csproj" .

# Find Dockerfile tessdata layers
grep -r "tessdata" Dockerfile* docker-compose*.yml .