// charlesw Tesseract: OS detection required just to find native DLLs
// DllNotFoundException on any platform where binaries do not resolve
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
    Environment.SetEnvironmentVariable("LD_LIBRARY_PATH", "/app/lib");
}
var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
using var img = Pix.LoadFromFile(imagePath); // Requires leptonica native DLL
using var page = engine.Process(img);
return page.GetText();

// charlesw Tesseract: OS detection required just to find native DLLs
// DllNotFoundException on any platform where binaries do not resolve
if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
{
    Environment.SetEnvironmentVariable("LD_LIBRARY_PATH", "/app/lib");
}
var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
using var img = Pix.LoadFromFile(imagePath); // Requires leptonica native DLL
using var page = engine.Process(img);
return page.GetText();

// IronOCR: no path management, no OS detection, no leptonica dependency
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
var text = new IronTesseract().Read(imagePath).Text;

// IronOCR: no path management, no OS detection, no leptonica dependency
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
var text = new IronTesseract().Read(imagePath).Text;

dotnet remove package Tesseract

dotnet remove package Tesseract

// Before (charlesw Tesseract)
using Tesseract;

// After (IronOCR)
using IronOcr;

// Before (charlesw Tesseract)
using Tesseract;

// After (IronOCR)
using IronOcr;

// A realistic factory found in production charlesw/Tesseract projects
public static class OcrEngineFactory
{
    private static string GetTessDataPath()
    {
        // Different path per environment — all wrong until explicitly configured
        if (Environment.GetEnvironmentVariable("DOTNET_RUNNING_IN_CONTAINER") == "true")
            return "/app/tessdata";                                    // Docker
        if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
            return Path.Combine(AppContext.BaseDirectory, "tessdata"); // Linux bare metal
        if (RuntimeInformation.IsOSPlatform(OSPlatform.OSX))
            return "/usr/local/share/tessdata";                        // macOS Homebrew install
        return @".\tessdata";                                          // Windows dev machine
    }

    public static TesseractEngine Create(string language = "eng")
    {
        // If leptonica-1.82.0.dll is not in output directory: DllNotFoundException at this line
        // If tessdata folder is missing: TesseractException at engine construction
        return new TesseractEngine(GetTessDataPath(), language, EngineMode.Default);
    }
}

// Call site
using var engine = OcrEngineFactory.Create();
using var img = Pix.LoadFromFile("invoice.jpg");
using var page = engine.Process(img);
Console.WriteLine(page.GetText());

// A realistic factory found in production charlesw/Tesseract projects
public static class OcrEngineFactory
{
    private static string GetTessDataPath()
    {
        // Different path per environment — all wrong until explicitly configured
        if (Environment.GetEnvironmentVariable("DOTNET_RUNNING_IN_CONTAINER") == "true")
            return "/app/tessdata";                                    // Docker
        if (RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
            return Path.Combine(AppContext.BaseDirectory, "tessdata"); // Linux bare metal
        if (RuntimeInformation.IsOSPlatform(OSPlatform.OSX))
            return "/usr/local/share/tessdata";                        // macOS Homebrew install
        return @".\tessdata";                                          // Windows dev machine
    }

    public static TesseractEngine Create(string language = "eng")
    {
        // If leptonica-1.82.0.dll is not in output directory: DllNotFoundException at this line
        // If tessdata folder is missing: TesseractException at engine construction
        return new TesseractEngine(GetTessDataPath(), language, EngineMode.Default);
    }
}

// Call site
using var engine = OcrEngineFactory.Create();
using var img = Pix.LoadFromFile("invoice.jpg");
using var page = engine.Process(img);
Console.WriteLine(page.GetText());

// IronOCR: no factory, no path logic, no OS detection
// Runs identically on Windows, Linux, macOS, and ARM64
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var result = new IronTesseract().Read("invoice.jpg");
Console.WriteLine(result.Text);

// IronOCR: no factory, no path logic, no OS detection
// Runs identically on Windows, Linux, macOS, and ARM64
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var result = new IronTesseract().Read("invoice.jpg");
Console.WriteLine(result.Text);

// Pix is Leptonica's image type — requires leptonica native DLL
// Converting from System.Drawing.Bitmap requires a temp file round-trip
public string ProcessInMemoryImage(Bitmap bitmap)
{
    // No direct Bitmap → Pix conversion; must write to temp file
    var tempPath = Path.Combine(Path.GetTempPath(), $"ocr_{Guid.NewGuid()}.png");
    try
    {
        bitmap.Save(tempPath, System.Drawing.Imaging.ImageFormat.Png);

        using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
        using var pix = Pix.LoadFromFile(tempPath);   // Leptonica file I/O
        using var page = engine.Process(pix);

        return page.GetText();
    }
    finally
    {
        if (File.Exists(tempPath)) File.Delete(tempPath);
    }
}

// Pix is Leptonica's image type — requires leptonica native DLL
// Converting from System.Drawing.Bitmap requires a temp file round-trip
public string ProcessInMemoryImage(Bitmap bitmap)
{
    // No direct Bitmap → Pix conversion; must write to temp file
    var tempPath = Path.Combine(Path.GetTempPath(), $"ocr_{Guid.NewGuid()}.png");
    try
    {
        bitmap.Save(tempPath, System.Drawing.Imaging.ImageFormat.Png);

        using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
        using var pix = Pix.LoadFromFile(tempPath);   // Leptonica file I/O
        using var page = engine.Process(pix);

        return page.GetText();
    }
    finally
    {
        if (File.Exists(tempPath)) File.Delete(tempPath);
    }
}

// OcrInput accepts byte arrays and streams — no temp file, no Leptonica
public string ProcessInMemoryImage(byte[] imageBytes)
{
    using var input = new OcrInput();
    input.LoadImage(imageBytes);   // Direct byte array loading

    var result = new IronTesseract().Read(input);
    return result.Text;
}

// Or from a stream — same pattern
public string ProcessFromStream(Stream imageStream)
{
    using var input = new OcrInput();
    input.LoadImage(imageStream);

    var result = new IronTesseract().Read(input);
    return result.Text;
}

// OcrInput accepts byte arrays and streams — no temp file, no Leptonica
public string ProcessInMemoryImage(byte[] imageBytes)
{
    using var input = new OcrInput();
    input.LoadImage(imageBytes);   // Direct byte array loading

    var result = new IronTesseract().Read(input);
    return result.Text;
}

// Or from a stream — same pattern
public string ProcessFromStream(Stream imageStream)
{
    using var input = new OcrInput();
    input.LoadImage(imageStream);

    var result = new IronTesseract().Read(input);
    return result.Text;
}

// Word-level confidence filtering requires iterator boilerplate
public List<string> ExtractHighConfidenceWords(string imagePath, float minConfidence = 0.8f)
{
    var highConfidenceWords = new List<string>();

    using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
    using var img = Pix.LoadFromFile(imagePath);
    using var page = engine.Process(img);

    // Page-level confidence only: fine-grained requires the iterator
    Console.WriteLine($"Page confidence: {page.GetMeanConfidence():P1}");

    using var iter = page.GetIterator();
    iter.Begin();
    do
    {
        if (iter.IsAtBeginningOf(PageIteratorLevel.Word))
        {
            var wordText = iter.GetText(PageIteratorLevel.Word)?.Trim();
            var wordConf  = iter.GetConfidence(PageIteratorLevel.Word) / 100f; // Returns 0-100
            if (!string.IsNullOrEmpty(wordText) && wordConf >= minConfidence)
                highConfidenceWords.Add(wordText);
        }
    } while (iter.Next(PageIteratorLevel.Para, PageIteratorLevel.Word));

    return highConfidenceWords;
}

// Word-level confidence filtering requires iterator boilerplate
public List<string> ExtractHighConfidenceWords(string imagePath, float minConfidence = 0.8f)
{
    var highConfidenceWords = new List<string>();

    using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
    using var img = Pix.LoadFromFile(imagePath);
    using var page = engine.Process(img);

    // Page-level confidence only: fine-grained requires the iterator
    Console.WriteLine($"Page confidence: {page.GetMeanConfidence():P1}");

    using var iter = page.GetIterator();
    iter.Begin();
    do
    {
        if (iter.IsAtBeginningOf(PageIteratorLevel.Word))
        {
            var wordText = iter.GetText(PageIteratorLevel.Word)?.Trim();
            var wordConf  = iter.GetConfidence(PageIteratorLevel.Word) / 100f; // Returns 0-100
            if (!string.IsNullOrEmpty(wordText) && wordConf >= minConfidence)
                highConfidenceWords.Add(wordText);
        }
    } while (iter.Next(PageIteratorLevel.Para, PageIteratorLevel.Word));

    return highConfidenceWords;
}

// Confidence is a property on each result object — no iterator required
public List<string> ExtractHighConfidenceWords(string imagePath, double minConfidence = 80.0)
{
    var result = new IronTesseract().Read(imagePath);

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

    // LINQ directly on the word collection — no iterator state management
    return result.Pages
        .SelectMany(p => p.Lines)
        .SelectMany(l => l.Words)
        .Where(w => w.Confidence >= minConfidence && !string.IsNullOrWhiteSpace(w.Text))
        .Select(w => w.Text)
        .ToList();
}

// Confidence is a property on each result object — no iterator required
public List<string> ExtractHighConfidenceWords(string imagePath, double minConfidence = 80.0)
{
    var result = new IronTesseract().Read(imagePath);

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

    // LINQ directly on the word collection — no iterator state management
    return result.Pages
        .SelectMany(p => p.Lines)
        .SelectMany(l => l.Words)
        .Where(w => w.Confidence >= minConfidence && !string.IsNullOrWhiteSpace(w.Text))
        .Select(w => w.Text)
        .ToList();
}

// charlesw/Tesseract has no multi-frame TIFF support
// Each frame must be extracted via System.Drawing before OCR can run
public string ProcessMultiFrameTiff(string tiffPath)
{
    var fullText = new StringBuilder();

    using var tiffImage = Image.FromFile(tiffPath);
    var frameCount = tiffImage.GetFrameCount(FrameDimension.Page);

    using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);

    for (int i = 0; i < frameCount; i++)
    {
        tiffImage.SelectActiveFrame(FrameDimension.Page, i);

        // Must save each frame as a temp file for Pix to load
        var tempPath = Path.Combine(Path.GetTempPath(), $"tiff_frame_{i}.png");
        try
        {
            tiffImage.Save(tempPath, System.Drawing.Imaging.ImageFormat.Png);

            using var pix  = Pix.LoadFromFile(tempPath);
            using var page = engine.Process(pix);
            fullText.AppendLine(page.GetText());
        }
        finally
        {
            if (File.Exists(tempPath)) File.Delete(tempPath);
        }
    }

    return fullText.ToString();
}

// charlesw/Tesseract has no multi-frame TIFF support
// Each frame must be extracted via System.Drawing before OCR can run
public string ProcessMultiFrameTiff(string tiffPath)
{
    var fullText = new StringBuilder();

    using var tiffImage = Image.FromFile(tiffPath);
    var frameCount = tiffImage.GetFrameCount(FrameDimension.Page);

    using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);

    for (int i = 0; i < frameCount; i++)
    {
        tiffImage.SelectActiveFrame(FrameDimension.Page, i);

        // Must save each frame as a temp file for Pix to load
        var tempPath = Path.Combine(Path.GetTempPath(), $"tiff_frame_{i}.png");
        try
        {
            tiffImage.Save(tempPath, System.Drawing.Imaging.ImageFormat.Png);

            using var pix  = Pix.LoadFromFile(tempPath);
            using var page = engine.Process(pix);
            fullText.AppendLine(page.GetText());
        }
        finally
        {
            if (File.Exists(tempPath)) File.Delete(tempPath);
        }
    }

    return fullText.ToString();
}

// LoadImageFrames handles multi-frame TIFFs natively — no frame extraction loop
public string ProcessMultiFrameTiff(string tiffPath)
{
    using var input = new OcrInput();
    input.LoadImageFrames(tiffPath);   // All frames loaded in one call

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

    // Pages maps directly to TIFF frames
    foreach (var page in result.Pages)
        Console.WriteLine($"Frame {page.PageNumber}: {page.Words.Count()} words");

    return result.Text;
}

// LoadImageFrames handles multi-frame TIFFs natively — no frame extraction loop
public string ProcessMultiFrameTiff(string tiffPath)
{
    using var input = new OcrInput();
    input.LoadImageFrames(tiffPath);   // All frames loaded in one call

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

    // Pages maps directly to TIFF frames
    foreach (var page in result.Pages)
        Console.WriteLine($"Frame {page.PageNumber}: {page.Words.Count()} words");

    return result.Text;
}

// charlesw/Tesseract produces text only.
// Creating a searchable PDF requires a second library and significant code.
// The pattern below is representative — actual implementation varies by PDF library.
public void CreateSearchablePdf(string imagePath, string outputPdfPath)
{
    // Step 1: Extract text from image
    string extractedText;
    using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
    using var img = Pix.LoadFromFile(imagePath);
    using var page = engine.Process(img);
    extractedText = page.GetText();

    // Step 2: Build a PDF with the image as background and text overlay
    // Requires a separate PDF library (not shown — 50-100+ additional lines)
    // The text layer must be positioned to match the original image layout
    // Word-level coordinates from the iterator are needed for accurate alignment
    throw new NotImplementedException(
        "Searchable PDF generation requires a separate PDF library. " +
        "Add PdfSharp, IronPDF, or similar, then implement text layer overlay.");
}

// charlesw/Tesseract produces text only.
// Creating a searchable PDF requires a second library and significant code.
// The pattern below is representative — actual implementation varies by PDF library.
public void CreateSearchablePdf(string imagePath, string outputPdfPath)
{
    // Step 1: Extract text from image
    string extractedText;
    using var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default);
    using var img = Pix.LoadFromFile(imagePath);
    using var page = engine.Process(img);
    extractedText = page.GetText();

    // Step 2: Build a PDF with the image as background and text overlay
    // Requires a separate PDF library (not shown — 50-100+ additional lines)
    // The text layer must be positioned to match the original image layout
    // Word-level coordinates from the iterator are needed for accurate alignment
    throw new NotImplementedException(
        "Searchable PDF generation requires a separate PDF library. " +
        "Add PdfSharp, IronPDF, or similar, then implement text layer overlay.");
}

// SaveAsSearchablePdf produces a PDF/A-compatible searchable document
// No secondary library, no text overlay code, no coordinate mapping
public void CreateSearchablePdf(string imagePath, string outputPdfPath)
{
    var result = new IronTesseract().Read(imagePath);
    result.SaveAsSearchablePdf(outputPdfPath);
    Console.WriteLine($"Searchable PDF saved: {outputPdfPath}");
}

// Same API works for multi-page TIFF or existing PDF input
public void MakePdfSearchable(string scannedPdfPath, string outputPdfPath)
{
    var result = new IronTesseract().Read(scannedPdfPath);
    result.SaveAsSearchablePdf(outputPdfPath);
}

// SaveAsSearchablePdf produces a PDF/A-compatible searchable document
// No secondary library, no text overlay code, no coordinate mapping
public void CreateSearchablePdf(string imagePath, string outputPdfPath)
{
    var result = new IronTesseract().Read(imagePath);
    result.SaveAsSearchablePdf(outputPdfPath);
    Console.WriteLine($"Searchable PDF saved: {outputPdfPath}");
}

// Same API works for multi-page TIFF or existing PDF input
public void MakePdfSearchable(string scannedPdfPath, string outputPdfPath)
{
    var result = new IronTesseract().Read(scannedPdfPath);
    result.SaveAsSearchablePdf(outputPdfPath);
}

dotnet remove package Tesseract
dotnet add package IronOcr

dotnet remove package Tesseract
dotnet add package IronOcr

# Replace this manual tessdata file management:
#   tessdata/eng.traineddata  (15 MB, manually downloaded)
#   tessdata/fra.traineddata  (15 MB, manually downloaded)
#   .csproj <CopyToOutputDirectory> entry

# With NuGet packages:
dotnet add package IronOcr.Languages.French

# Replace this manual tessdata file management:
#   tessdata/eng.traineddata  (15 MB, manually downloaded)
#   tessdata/fra.traineddata  (15 MB, manually downloaded)
#   .csproj <CopyToOutputDirectory> entry

# With NuGet packages:
dotnet add package IronOcr.Languages.French

# Before: Leptonica explicit install — breaks on base image updates
RUN apt-get update && apt-get install -y libleptonica-dev

# After: standard .NET Linux requirement only
RUN apt-get update && apt-get install -y libgdiplus

# Before: Leptonica explicit install — breaks on base image updates
RUN apt-get update && apt-get install -y libleptonica-dev

# After: standard .NET Linux requirement only
RUN apt-get update && apt-get install -y libgdiplus

// Before: null checks required at every iterator level
var wordText = iter.GetText(PageIteratorLevel.Word);
if (wordText != null && wordText.Trim().Length > 0)
    results.Add(wordText.Trim());

// After: collection is safe to enumerate; check content as needed
foreach (var word in result.Pages.SelectMany(p => p.Lines).SelectMany(l => l.Words))
{
    if (!string.IsNullOrWhiteSpace(word.Text))
        results.Add(word.Text);
}

// Before: null checks required at every iterator level
var wordText = iter.GetText(PageIteratorLevel.Word);
if (wordText != null && wordText.Trim().Length > 0)
    results.Add(wordText.Trim());

// After: collection is safe to enumerate; check content as needed
foreach (var word in result.Pages.SelectMany(p => p.Lines).SelectMany(l => l.Words))
{
    if (!string.IsNullOrWhiteSpace(word.Text))
        results.Add(word.Text);
}

// Thread-safe parallel processing — IronTesseract handles concurrent access
var results = new System.Collections.Concurrent.ConcurrentBag<string>();
Parallel.ForEach(imageFiles, imagePath =>
{
    var ocr    = new IronTesseract();
    var result = ocr.Read(imagePath);
    results.Add(result.Text);
});

// Thread-safe parallel processing — IronTesseract handles concurrent access
var results = new System.Collections.Concurrent.ConcurrentBag<string>();
Parallel.ForEach(imageFiles, imagePath =>
{
    var ocr    = new IronTesseract();
    var result = ocr.Read(imagePath);
    results.Add(result.Text);
});

# Find all references to Tesseract namespace (engine creation, Pix usage, iterator usage)
grep -rn "using Tesseract" --include="*.cs" .

# Find TesseractEngine instantiation points
grep -rn "TesseractEngine" --include="*.cs" .

# Find Pix usage (Leptonica image type)
grep -rn "Pix\." --include="*.cs" .

# Find tessdata path constants and methods
grep -rn "tessdata\|TessDataPath\|traineddata" --include="*.cs" .

# Find platform-conditional deployment code
grep -rn "IsOSPlatform\|DOTNET_RUNNING_IN_CONTAINER\|LD_LIBRARY_PATH" --include="*.cs" .

# Find iterator pattern usage
grep -rn "GetIterator\|ResultIterator\|PageIteratorLevel" --include="*.cs" .

# Find confidence calls
grep -rn "GetMeanConfidence\|GetConfidence" --include="*.cs" .

# Find .csproj tessdata copy entries
grep -rn "tessdata" --include="*.csproj" .

# Find all references to Tesseract namespace (engine creation, Pix usage, iterator usage)
grep -rn "using Tesseract" --include="*.cs" .

# Find TesseractEngine instantiation points
grep -rn "TesseractEngine" --include="*.cs" .

# Find Pix usage (Leptonica image type)
grep -rn "Pix\." --include="*.cs" .

# Find tessdata path constants and methods
grep -rn "tessdata\|TessDataPath\|traineddata" --include="*.cs" .

# Find platform-conditional deployment code
grep -rn "IsOSPlatform\|DOTNET_RUNNING_IN_CONTAINER\|LD_LIBRARY_PATH" --include="*.cs" .

# Find iterator pattern usage
grep -rn "GetIterator\|ResultIterator\|PageIteratorLevel" --include="*.cs" .

# Find confidence calls
grep -rn "GetMeanConfidence\|GetConfidence" --include="*.cs" .

# Find .csproj tessdata copy entries
grep -rn "tessdata" --include="*.csproj" .