// TessDataPath must exist and be populated — breaks on first clean deployment
private const string TessDataPath = @"./tessdata";

public static string ExtractText(string imagePath)
{
    // Runtime failure if eng.traineddata is missing from TessDataPath
    if (!Directory.Exists(TessDataPath))
        throw new DirectoryNotFoundException(
            $"Tessdata not found at {TessDataPath}. " +
            "Download from https://github.com/tesseract-ocr/tessdata");

    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var img   = Pix.LoadFromFile(imagePath);  // Leptonica Pix object
    using var page  = engine.Process(img);
    return page.GetText();
}

// TessDataPath must exist and be populated — breaks on first clean deployment
private const string TessDataPath = @"./tessdata";

public static string ExtractText(string imagePath)
{
    // Runtime failure if eng.traineddata is missing from TessDataPath
    if (!Directory.Exists(TessDataPath))
        throw new DirectoryNotFoundException(
            $"Tessdata not found at {TessDataPath}. " +
            "Download from https://github.com/tesseract-ocr/tessdata");

    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var img   = Pix.LoadFromFile(imagePath);  // Leptonica Pix object
    using var page  = engine.Process(img);
    return page.GetText();
}

// No tessdata folder. No path. No file check. Just OCR.
var text = new IronTesseract().Read("document.jpg").Text;

// No tessdata folder. No path. No file check. Just OCR.
var text = new IronTesseract().Read("document.jpg").Text;

dotnet remove package Tesseract

dotnet remove package Tesseract

// Before
using Tesseract;

// After
using IronOcr;

// Before
using Tesseract;

// After
using IronOcr;

// Every class that uses OCR must handle this initialization block
private const string TessDataPath = @"./tessdata";

public string RecognizeInvoiceNumber(string imagePath)
{
    // Check tessdata presence — missing file = silent runtime failure
    foreach (var lang in new[] { "eng" })
    {
        if (!File.Exists(Path.Combine(TessDataPath, $"{lang}.traineddata")))
            throw new FileNotFoundException(
                $"Missing {lang}.traineddata. " +
                "Download from https://github.com/tesseract-ocr/tessdata");
    }

    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);

    // Pix is a Leptonica wrapper type — not a standard .NET image
    using var img  = Pix.LoadFromFile(imagePath);
    using var page = engine.Process(img);

    string text = page.GetText();
    float  conf = page.GetMeanConfidence();

    return conf > 0.7f ? text : string.Empty;
}

// Every class that uses OCR must handle this initialization block
private const string TessDataPath = @"./tessdata";

public string RecognizeInvoiceNumber(string imagePath)
{
    // Check tessdata presence — missing file = silent runtime failure
    foreach (var lang in new[] { "eng" })
    {
        if (!File.Exists(Path.Combine(TessDataPath, $"{lang}.traineddata")))
            throw new FileNotFoundException(
                $"Missing {lang}.traineddata. " +
                "Download from https://github.com/tesseract-ocr/tessdata");
    }

    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);

    // Pix is a Leptonica wrapper type — not a standard .NET image
    using var img  = Pix.LoadFromFile(imagePath);
    using var page = engine.Process(img);

    string text = page.GetText();
    float  conf = page.GetMeanConfidence();

    return conf > 0.7f ? text : string.Empty;
}

using IronOcr;

public string RecognizeInvoiceNumber(string imagePath)
{
    var result = new IronTesseract().Read(imagePath);

    // Confidence property returns 0-100 double
    return result.Confidence > 70 ? result.Text : string.Empty;
}

using IronOcr;

public string RecognizeInvoiceNumber(string imagePath)
{
    var result = new IronTesseract().Read(imagePath);

    // Confidence property returns 0-100 double
    return result.Confidence > 70 ? result.Text : string.Empty;
}

using Tesseract;
using System.Drawing;
using System.Drawing.Imaging;

private const string TessDataPath = @"./tessdata";

public static string ExtractFromMultiPageTiff(string tiffPath)
{
    var allText = new System.Text.StringBuilder();

    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var tiffImage = Image.FromFile(tiffPath);

    int frameCount = tiffImage.GetFrameCount(FrameDimension.Page);

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

        // Must save each frame to disk — Pix.LoadFromFile requires a path
        string tempPath = Path.GetTempFileName() + ".png";
        try
        {
            tiffImage.Save(tempPath, ImageFormat.Png);

            using var img  = Pix.LoadFromFile(tempPath);
            using var page = engine.Process(img);
            allText.AppendLine(page.GetText());
        }
        finally
        {
            File.Delete(tempPath); // Uncleaned temp files fill disk on failure
        }
    }

    return allText.ToString();
}

using Tesseract;
using System.Drawing;
using System.Drawing.Imaging;

private const string TessDataPath = @"./tessdata";

public static string ExtractFromMultiPageTiff(string tiffPath)
{
    var allText = new System.Text.StringBuilder();

    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var tiffImage = Image.FromFile(tiffPath);

    int frameCount = tiffImage.GetFrameCount(FrameDimension.Page);

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

        // Must save each frame to disk — Pix.LoadFromFile requires a path
        string tempPath = Path.GetTempFileName() + ".png";
        try
        {
            tiffImage.Save(tempPath, ImageFormat.Png);

            using var img  = Pix.LoadFromFile(tempPath);
            using var page = engine.Process(img);
            allText.AppendLine(page.GetText());
        }
        finally
        {
            File.Delete(tempPath); // Uncleaned temp files fill disk on failure
        }
    }

    return allText.ToString();
}

using IronOcr;

public static string ExtractFromMultiPageTiff(string tiffPath)
{
    using var input = new OcrInput();
    input.LoadImageFrames(tiffPath);  // Loads all frames at once
    input.Deskew();                   // Applied to every frame uniformly
    input.DeNoise();

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

using IronOcr;

public static string ExtractFromMultiPageTiff(string tiffPath)
{
    using var input = new OcrInput();
    input.LoadImageFrames(tiffPath);  // Loads all frames at once
    input.Deskew();                   // Applied to every frame uniformly
    input.DeNoise();

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

// Requires: PdfiumViewer + Tesseract + a PDF writer library (iText, PdfSharp)
// Each library adds its own native dependencies and license considerations

using Tesseract;
// using PdfiumViewer;  // Comment: must add NuGet + deploy native pdfium.dll
// using iText.Kernel.Pdf;  // Comment: AGPL or commercial license required

private const string TessDataPath = @"./tessdata";

public static void CreateSearchablePdf(string inputPdfPath, string outputPdfPath)
{
    // Step 1: Render PDF pages to images (requires PdfiumViewer)
    // Step 2: Run OCR on each image (Tesseract)
    // Step 3: Write text positions back into PDF (requires iText or PDFsharp)
    //
    // Total: ~150 lines across three libraries
    // Native binaries required: tesseract*.dll, leptonica*.dll, pdfium.dll
    // License risk: iText is AGPL unless you purchase a commercial license

    throw new NotImplementedException(
        "Requires PdfiumViewer + Tesseract + a PDF writer. " +
        "No single-package solution exists with this stack.");
}

// Requires: PdfiumViewer + Tesseract + a PDF writer library (iText, PdfSharp)
// Each library adds its own native dependencies and license considerations

using Tesseract;
// using PdfiumViewer;  // Comment: must add NuGet + deploy native pdfium.dll
// using iText.Kernel.Pdf;  // Comment: AGPL or commercial license required

private const string TessDataPath = @"./tessdata";

public static void CreateSearchablePdf(string inputPdfPath, string outputPdfPath)
{
    // Step 1: Render PDF pages to images (requires PdfiumViewer)
    // Step 2: Run OCR on each image (Tesseract)
    // Step 3: Write text positions back into PDF (requires iText or PDFsharp)
    //
    // Total: ~150 lines across three libraries
    // Native binaries required: tesseract*.dll, leptonica*.dll, pdfium.dll
    // License risk: iText is AGPL unless you purchase a commercial license

    throw new NotImplementedException(
        "Requires PdfiumViewer + Tesseract + a PDF writer. " +
        "No single-package solution exists with this stack.");
}

using IronOcr;

public static void CreateSearchablePdf(string inputPdfPath, string outputPdfPath)
{
    using var input = new OcrInput();
    input.LoadPdf(inputPdfPath);
    input.Deskew();    // Correct scanned page skew before OCR
    input.DeNoise();   // Remove scanner artifacts

    var result = new IronTesseract().Read(input);
    result.SaveAsSearchablePdf(outputPdfPath);
}

using IronOcr;

public static void CreateSearchablePdf(string inputPdfPath, string outputPdfPath)
{
    using var input = new OcrInput();
    input.LoadPdf(inputPdfPath);
    input.Deskew();    // Correct scanned page skew before OCR
    input.DeNoise();   // Remove scanner artifacts

    var result = new IronTesseract().Read(input);
    result.SaveAsSearchablePdf(outputPdfPath);
}

using Tesseract;

private const string TessDataPath = @"./tessdata";

public static void ExtractStructuredData(string imagePath)
{
    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var img    = Pix.LoadFromFile(imagePath);
    using var page   = engine.Process(img);
    using var iter   = page.GetIterator();

    iter.Begin();
    do
    {
        if (iter.IsAtBeginningOf(PageIteratorLevel.Para))
            Console.WriteLine("-- New Paragraph --");

        if (iter.TryGetBoundingBox(PageIteratorLevel.Word, out var bounds))
        {
            string word       = iter.GetText(PageIteratorLevel.Word);
            float  confidence = iter.GetConfidence(PageIteratorLevel.Word);
            Console.WriteLine(
                $"Word: '{word?.Trim()}' " +
                $"at ({bounds.X1},{bounds.Y1})-({bounds.X2},{bounds.Y2}) " +
                $"conf={confidence:P0}");
        }
    }
    while (iter.Next(PageIteratorLevel.Word));
}

using Tesseract;

private const string TessDataPath = @"./tessdata";

public static void ExtractStructuredData(string imagePath)
{
    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var img    = Pix.LoadFromFile(imagePath);
    using var page   = engine.Process(img);
    using var iter   = page.GetIterator();

    iter.Begin();
    do
    {
        if (iter.IsAtBeginningOf(PageIteratorLevel.Para))
            Console.WriteLine("-- New Paragraph --");

        if (iter.TryGetBoundingBox(PageIteratorLevel.Word, out var bounds))
        {
            string word       = iter.GetText(PageIteratorLevel.Word);
            float  confidence = iter.GetConfidence(PageIteratorLevel.Word);
            Console.WriteLine(
                $"Word: '{word?.Trim()}' " +
                $"at ({bounds.X1},{bounds.Y1})-({bounds.X2},{bounds.Y2}) " +
                $"conf={confidence:P0}");
        }
    }
    while (iter.Next(PageIteratorLevel.Word));
}

using IronOcr;

public static void ExtractStructuredData(string imagePath)
{
    var result = new IronTesseract().Read(imagePath);

    foreach (var page in result.Pages)
    {
        Console.WriteLine($"Page {page.PageNumber} — confidence: {result.Confidence}%");

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

            foreach (var word in paragraph.Words)
            {
                Console.WriteLine(
                    $"    Word: '{word.Text}' " +
                    $"at ({word.X},{word.Y}) " +
                    $"size {word.Width}x{word.Height} " +
                    $"conf={word.Confidence:P0}");
            }
        }
    }
}

using IronOcr;

public static void ExtractStructuredData(string imagePath)
{
    var result = new IronTesseract().Read(imagePath);

    foreach (var page in result.Pages)
    {
        Console.WriteLine($"Page {page.PageNumber} — confidence: {result.Confidence}%");

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

            foreach (var word in paragraph.Words)
            {
                Console.WriteLine(
                    $"    Word: '{word.Text}' " +
                    $"at ({word.X},{word.Y}) " +
                    $"size {word.Width}x{word.Height} " +
                    $"conf={word.Confidence:P0}");
            }
        }
    }
}

using Tesseract;

private const string TessDataPath = @"./tessdata";

public static string ExtractFromEuropeanDocument(string imagePath)
{
    // Before this call works, these files must exist:
    // ./tessdata/eng.traineddata  (~15 MB, from GitHub)
    // ./tessdata/fra.traineddata  (~15 MB, from GitHub)
    // ./tessdata/deu.traineddata  (~15 MB, from GitHub)
    // ./tessdata/spa.traineddata  (~15 MB, from GitHub)
    // Total: ~60 MB to download, version-match, and deploy to every environment

    foreach (var lang in new[] { "eng", "fra", "deu", "spa" })
    {
        if (!File.Exists(Path.Combine(TessDataPath, $"{lang}.traineddata")))
            throw new FileNotFoundException(
                $"Download {lang}.traineddata from " +
                "https://github.com/tesseract-ocr/tessdata " +
                $"and place in {TessDataPath}");
    }

    // Language string is a concatenation — order affects recognition priority
    using var engine = new TesseractEngine(TessDataPath, "eng+fra+deu+spa", EngineMode.Default);
    using var img    = Pix.LoadFromFile(imagePath);
    using var page   = engine.Process(img);
    return page.GetText();
}

using Tesseract;

private const string TessDataPath = @"./tessdata";

public static string ExtractFromEuropeanDocument(string imagePath)
{
    // Before this call works, these files must exist:
    // ./tessdata/eng.traineddata  (~15 MB, from GitHub)
    // ./tessdata/fra.traineddata  (~15 MB, from GitHub)
    // ./tessdata/deu.traineddata  (~15 MB, from GitHub)
    // ./tessdata/spa.traineddata  (~15 MB, from GitHub)
    // Total: ~60 MB to download, version-match, and deploy to every environment

    foreach (var lang in new[] { "eng", "fra", "deu", "spa" })
    {
        if (!File.Exists(Path.Combine(TessDataPath, $"{lang}.traineddata")))
            throw new FileNotFoundException(
                $"Download {lang}.traineddata from " +
                "https://github.com/tesseract-ocr/tessdata " +
                $"and place in {TessDataPath}");
    }

    // Language string is a concatenation — order affects recognition priority
    using var engine = new TesseractEngine(TessDataPath, "eng+fra+deu+spa", EngineMode.Default);
    using var img    = Pix.LoadFromFile(imagePath);
    using var page   = engine.Process(img);
    return page.GetText();
}

// Install language packs once per project:
// dotnet add package IronOcr.Languages.French
// dotnet add package IronOcr.Languages.German
// dotnet add package IronOcr.Languages.Spanish
using IronOcr;

public static string ExtractFromEuropeanDocument(string imagePath)
{
    var ocr = new IronTesseract();
    ocr.Language = OcrLanguage.English;
    ocr.AddSecondaryLanguage(OcrLanguage.French);
    ocr.AddSecondaryLanguage(OcrLanguage.German);
    ocr.AddSecondaryLanguage(OcrLanguage.Spanish);

    return ocr.Read(imagePath).Text;
}

// Install language packs once per project:
// dotnet add package IronOcr.Languages.French
// dotnet add package IronOcr.Languages.German
// dotnet add package IronOcr.Languages.Spanish
using IronOcr;

public static string ExtractFromEuropeanDocument(string imagePath)
{
    var ocr = new IronTesseract();
    ocr.Language = OcrLanguage.English;
    ocr.AddSecondaryLanguage(OcrLanguage.French);
    ocr.AddSecondaryLanguage(OcrLanguage.German);
    ocr.AddSecondaryLanguage(OcrLanguage.Spanish);

    return ocr.Read(imagePath).Text;
}

# Find all tessdata references in source
grep -r "TessDataPath\|tessdata\|traineddata" --include="*.cs" .
grep -r "tessdata" --include="*.csproj" .

# Find all tessdata references in source
grep -r "TessDataPath\|tessdata\|traineddata" --include="*.cs" .
grep -r "tessdata" --include="*.csproj" .

// Before: iterator loop
using var iter = page.GetIterator();
iter.Begin();
do
{
    if (iter.TryGetBoundingBox(PageIteratorLevel.Word, out var bounds))
    {
        string text = iter.GetText(PageIteratorLevel.Word);
        // process text and bounds
    }
}
while (iter.Next(PageIteratorLevel.Word));

// After: enumerable collection
var result = new IronTesseract().Read(imagePath);
foreach (var word in result.Words)
{
    // word.Text, word.X, word.Y, word.Width, word.Height, word.Confidence
}

// Before: iterator loop
using var iter = page.GetIterator();
iter.Begin();
do
{
    if (iter.TryGetBoundingBox(PageIteratorLevel.Word, out var bounds))
    {
        string text = iter.GetText(PageIteratorLevel.Word);
        // process text and bounds
    }
}
while (iter.Next(PageIteratorLevel.Word));

// After: enumerable collection
var result = new IronTesseract().Read(imagePath);
foreach (var word in result.Words)
{
    // word.Text, word.X, word.Y, word.Width, word.Height, word.Confidence
}

// Before: ~50-150 lines of PdfiumViewer + Tesseract + temp file management
// After:
using var input = new OcrInput();
input.LoadPdf("document.pdf");
input.Deskew();
input.DeNoise();
var result = new IronTesseract().Read(input);

// Before: ~50-150 lines of PdfiumViewer + Tesseract + temp file management
// After:
using var input = new OcrInput();
input.LoadPdf("document.pdf");
input.Deskew();
input.DeNoise();
var result = new IronTesseract().Read(input);

// Before: engine per thread, 40-100 MB per language model, times thread count
Parallel.ForEach(files, file =>
{
    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var img    = Pix.LoadFromFile(file);
    using var page   = engine.Process(img);
    results[file] = page.GetText();
});

// After: single engine, thread-safe, shared pool
var ocr = new IronTesseract();
Parallel.ForEach(files, file =>
{
    var result = ocr.Read(file);
    results[file] = result.Text;
});

// Before: engine per thread, 40-100 MB per language model, times thread count
Parallel.ForEach(files, file =>
{
    using var engine = new TesseractEngine(TessDataPath, "eng", EngineMode.Default);
    using var img    = Pix.LoadFromFile(file);
    using var page   = engine.Process(img);
    results[file] = page.GetText();
});

// After: single engine, thread-safe, shared pool
var ocr = new IronTesseract();
Parallel.ForEach(files, file =>
{
    var result = ocr.Read(file);
    results[file] = result.Text;
});

# Find all using directives for the Tesseract namespace
grep -rn "using Tesseract" --include="*.cs" .

# Find TesseractEngine constructors
grep -rn "TesseractEngine\|TessDataPath\|tessdata" --include="*.cs" .

# Find Pix object usage
grep -rn "Pix\." --include="*.cs" .

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

# Find PDF rendering libraries added for Tesseract
grep -rn "PdfiumViewer\|PDFtoImage\|Docnet\|GhostScript" --include="*.cs" .

# Find tessdata references in project files
grep -rn "tessdata\|traineddata" --include="*.csproj" .

# Find tessdata references in Dockerfiles
grep -rn "tessdata\|TESSDATA_PREFIX\|libtesseract" Dockerfile* .

# Find all using directives for the Tesseract namespace
grep -rn "using Tesseract" --include="*.cs" .

# Find TesseractEngine constructors
grep -rn "TesseractEngine\|TessDataPath\|tessdata" --include="*.cs" .

# Find Pix object usage
grep -rn "Pix\." --include="*.cs" .

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

# Find PDF rendering libraries added for Tesseract
grep -rn "PdfiumViewer\|PDFtoImage\|Docnet\|GhostScript" --include="*.cs" .

# Find tessdata references in project files
grep -rn "tessdata\|traineddata" --include="*.csproj" .

# Find tessdata references in Dockerfiles
grep -rn "tessdata\|TESSDATA_PREFIX\|libtesseract" Dockerfile* .