Charlesw TesseractからIronOCRへの移行

// 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();

Imports System
Imports System.Runtime.InteropServices
Imports Tesseract

' charlesw Tesseract: OS detection required just to find native DLLs
' DllNotFoundException on any platform where binaries do not resolve
If RuntimeInformation.IsOSPlatform(OSPlatform.Linux) Then
    Environment.SetEnvironmentVariable("LD_LIBRARY_PATH", "/app/lib")
End If

Dim engine As New TesseractEngine("./tessdata", "eng", EngineMode.Default)
Using img As Pix = Pix.LoadFromFile(imagePath) ' Requires leptonica native DLL
    Using page As Page = engine.Process(img)
        Return page.GetText()
    End Using
End Using

// 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"
Dim text As String = New IronTesseract().Read(imagePath).Text

dotnet remove package Tesseract

// Before (charlesw Tesseract)
using Tesseract;

// After (IronOCR)
using IronOcr;

Imports IronOcr

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

// 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());

Imports System
Imports System.IO
Imports System.Runtime.InteropServices
Imports Tesseract

Public Module OcrEngineFactory
    Private Function GetTessDataPath() As String
        ' Different path per environment — all wrong until explicitly configured
        If Environment.GetEnvironmentVariable("DOTNET_RUNNING_IN_CONTAINER") = "true" Then
            Return "/app/tessdata"                                    ' Docker
        End If
        If RuntimeInformation.IsOSPlatform(OSPlatform.Linux) Then
            Return Path.Combine(AppContext.BaseDirectory, "tessdata") ' Linux bare metal
        End If
        If RuntimeInformation.IsOSPlatform(OSPlatform.OSX) Then
            Return "/usr/local/share/tessdata"                        ' macOS Homebrew install
        End If
        Return ".\tessdata"                                           ' Windows dev machine
    End Function

    Public Function Create(Optional language As String = "eng") As TesseractEngine
        ' 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)
    End Function
End Module

' Call site
Using engine As TesseractEngine = OcrEngineFactory.Create()
    Using img As Pix = Pix.LoadFromFile("invoice.jpg")
        Using page As Page = engine.Process(img)
            Console.WriteLine(page.GetText())
        End Using
    End Using
End Using

// 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"

Dim 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)
{
    // なし 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);
    }
}

Imports System
Imports System.Drawing
Imports System.IO
Imports Tesseract

' Pix is Leptonica's image type — requires leptonica native DLL
' Converting from System.Drawing.Bitmap requires a temp file round-trip
Public Function ProcessInMemoryImage(bitmap As Bitmap) As String
    ' なし direct Bitmap → Pix conversion; must write to temp file
    Dim tempPath As String = Path.Combine(Path.GetTempPath(), $"ocr_{Guid.NewGuid()}.png")
    Try
        bitmap.Save(tempPath, System.Drawing.Imaging.ImageFormat.Png)

        Using engine As New TesseractEngine("./tessdata", "eng", EngineMode.Default)
            Using pix As Pix = Pix.LoadFromFile(tempPath) ' Leptonica file I/O
                Using page As Page = engine.Process(pix)
                    Return page.GetText()
                End Using
            End Using
        End Using
    Finally
        If File.Exists(tempPath) Then File.Delete(tempPath)
    End Try
End Function

// 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;
}

Imports System.IO

' OcrInput accepts byte arrays and streams — no temp file, no Leptonica
Public Function ProcessInMemoryImage(imageBytes As Byte()) As String
    Using input As New OcrInput()
        input.LoadImage(imageBytes)   ' Direct byte array loading

        Dim result = New IronTesseract().Read(input)
        Return result.Text
    End Using
End Function

' Or from a stream — same pattern
Public Function ProcessFromStream(imageStream As Stream) As String
    Using input As New OcrInput()
        input.LoadImage(imageStream)

        Dim result = New IronTesseract().Read(input)
        Return result.Text
    End Using
End Function

// 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;
}

Imports System
Imports Tesseract

Public Class WordExtractor
    Public Function ExtractHighConfidenceWords(imagePath As String, Optional minConfidence As Single = 0.8F) As List(Of String)
        Dim highConfidenceWords As New List(Of String)()

        Using engine As New TesseractEngine("./tessdata", "eng", EngineMode.Default)
            Using img As Pix = Pix.LoadFromFile(imagePath)
                Using page As Page = engine.Process(img)
                    ' Page-level confidence only: fine-grained requires the iterator
                    Console.WriteLine($"Page confidence: {page.GetMeanConfidence():P1}")

                    Using iter As ResultIterator = page.GetIterator()
                        iter.Begin()
                        Do
                            If iter.IsAtBeginningOf(PageIteratorLevel.Word) Then
                                Dim wordText As String = iter.GetText(PageIteratorLevel.Word)?.Trim()
                                Dim wordConf As Single = iter.GetConfidence(PageIteratorLevel.Word) / 100.0F ' Returns 0-100
                                If Not String.IsNullOrEmpty(wordText) AndAlso wordConf >= minConfidence Then
                                    highConfidenceWords.Add(wordText)
                                End If
                            End If
                        Loop While iter.Next(PageIteratorLevel.Para, PageIteratorLevel.Word)
                    End Using
                End Using
            End Using
        End Using

        Return highConfidenceWords
    End Function
End Class

// 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();
}

Imports System
Imports System.Collections.Generic
Imports System.Linq

Public Function ExtractHighConfidenceWords(imagePath As String, Optional minConfidence As Double = 80.0) As List(Of String)
    Dim 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(Function(p) p.Lines) _
        .SelectMany(Function(l) l.Words) _
        .Where(Function(w) w.Confidence >= minConfidence AndAlso Not String.IsNullOrWhiteSpace(w.Text)) _
        .Select(Function(w) w.Text) _
        .ToList()
End Function

// 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();
}

Imports System.Drawing
Imports System.Drawing.Imaging
Imports Tesseract
Imports System.IO
Imports System.Text

Public Function ProcessMultiFrameTiff(tiffPath As String) As String
    Dim fullText As New StringBuilder()

    Using tiffImage As Image = Image.FromFile(tiffPath)
        Dim frameCount As Integer = tiffImage.GetFrameCount(FrameDimension.Page)

        Using engine As New TesseractEngine("./tessdata", "eng", EngineMode.Default)
            For i As Integer = 0 To frameCount - 1
                tiffImage.SelectActiveFrame(FrameDimension.Page, i)

                ' Must save each frame as a temp file for Pix to load
                Dim tempPath As String = Path.Combine(Path.GetTempPath(), $"tiff_frame_{i}.png")
                Try
                    tiffImage.Save(tempPath, Imaging.ImageFormat.Png)

                    Using pix As Pix = Pix.LoadFromFile(tempPath)
                        Using page As Page = engine.Process(pix)
                            fullText.AppendLine(page.GetText())
                        End Using
                    End Using
                Finally
                    If File.Exists(tempPath) Then File.Delete(tempPath)
                End Try
            Next
        End Using
    End Using

    Return fullText.ToString()
End Function

// 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;
}

Imports System
Imports IronOcr

Public Class TiffProcessor
    ' LoadImageFrames handles multi-frame TIFFs natively — no frame extraction loop
    Public Function ProcessMultiFrameTiff(tiffPath As String) As String
        Using input As New OcrInput()
            input.LoadImageFrames(tiffPath) ' All frames loaded in one call

            Dim result = New IronTesseract().Read(input)

            ' Pages maps directly to TIFF frames
            For Each page In result.Pages
                Console.WriteLine($"Frame {page.PageNumber}: {page.Words.Count()} words")
            Next

            Return result.Text
        End Using
    End Function
End Class

// 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.");
}

Imports Tesseract

Public Sub CreateSearchablePdf(imagePath As String, outputPdfPath As String)
    ' Step 1: Extract text from image
    Dim extractedText As String
    Using engine As New TesseractEngine("./tessdata", "eng", EngineMode.Default)
        Using img As Pix = Pix.LoadFromFile(imagePath)
            Using page As Page = engine.Process(img)
                extractedText = page.GetText()
            End Using
        End Using
    End Using

    ' 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.")
End Sub

// SaveAsSearchablePdf produces a PDF/A-compatible searchable document
// なし 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
' なし secondary library, no text overlay code, no coordinate mapping
Public Sub CreateSearchablePdf(imagePath As String, outputPdfPath As String)
    Dim result = New IronTesseract().Read(imagePath)
    result.SaveAsSearchablePdf(outputPdfPath)
    Console.WriteLine($"Searchable PDF saved: {outputPdfPath}")
End Sub

' Same API works for multi-page TIFF or existing PDF input
Public Sub MakePdfSearchable(scannedPdfPath As String, outputPdfPath As String)
    Dim result = New IronTesseract().Read(scannedPdfPath)
    result.SaveAsSearchablePdf(outputPdfPath)
End Sub

dotnet remove package Tesseract
:InstallCmd 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

// 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
Dim wordText = iter.GetText(PageIteratorLevel.Word)
If wordText IsNot Nothing AndAlso wordText.Trim().Length > 0 Then
    results.Add(wordText.Trim())
End If

' After: collection is safe to enumerate; check content as needed
For Each word In result.Pages.SelectMany(Function(p) p.Lines).SelectMany(Function(l) l.Words)
    If Not String.IsNullOrWhiteSpace(word.Text) Then
        results.Add(word.Text)
    End If
Next

// 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);
});

Imports System.Collections.Concurrent
Imports System.Threading.Tasks

' Thread-safe parallel processing — IronTesseract handles concurrent access
Dim results As New ConcurrentBag(Of String)()
Parallel.ForEach(imageFiles, Sub(imagePath)
    Dim ocr As New IronTesseract()
    Dim result = ocr.Read(imagePath)
    results.Add(result.Text)
End Sub)

# 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" .