Speichern von durchsuchbaren PDFs in C#35; mit IronOCR

using IronOcr;

// Initialize IronTesseract with configuration
var ocrTesseract = new IronTesseract
{
    Configuration = 
    {
        RenderSearchablePdf = true,
        PageSegmentationMode = TesseractPageSegmentationMode.Auto
    }
};

// Load a multi-page PDF
using var pdfInput = new OcrPdfInput("multi-page-scan.pdf");

// Optionally specify page range (e.g., pages 1-10)
pdfInput.SelectPages(1, 10);

// Perform OCR with progress tracking
OcrResult result = ocrTesseract.Read(pdfInput);

// Save as searchable PDF
result.SaveAsSearchablePdf("searchable-multi-page.pdf");

// Display total pages processed
Console.WriteLine($"Processed {result.Pages.Length} pages");

Imports IronOcr

' Initialize IronTesseract with configuration
Dim ocrTesseract As New IronTesseract With {
    .Configuration = New OcrConfiguration With {
        .RenderSearchablePdf = True,
        .PageSegmentationMode = TesseractPageSegmentationMode.Auto
    }
}

' Load a multi-page PDF
Using pdfInput As New OcrPdfInput("multi-page-scan.pdf")
    ' Optionally specify page range (e.g., pages 1-10)
    pdfInput.SelectPages(1, 10)

    ' Perform OCR with progress tracking
    Dim result As OcrResult = ocrTesseract.Read(pdfInput)

    ' Save as searchable PDF
    result.SaveAsSearchablePdf("searchable-multi-page.pdf")

    ' Display total pages processed
    Console.WriteLine($"Processed {result.Pages.Length} pages")
End Using

using IronOcr;

var ocr = new IronTesseract();
var ocrInput = new OcrInput();

// Load a PDF file
ocrInput.LoadPdf("invoice.pdf");

// Apply gray scale filter
ocrInput.ToGrayScale();
OcrResult result = ocr.Read(ocrInput);

// Save the result as a searchable PDF with filters applied
result.SaveAsSearchablePdf("outputGrayscale.pdf", true);

Imports IronOcr

Dim ocr As New IronTesseract()
Dim ocrInput As New OcrInput()

' Load a PDF file
ocrInput.LoadPdf("invoice.pdf")

' Apply gray scale filter
ocrInput.ToGrayScale()
Dim result As OcrResult = ocr.Read(ocrInput)

' Save the result as a searchable PDF with filters applied
result.SaveAsSearchablePdf("outputGrayscale.pdf", True)

using IronOcr;
using System.Threading.Tasks;
using System.Collections.Concurrent;

public class BatchPdfProcessor
{
    private readonly IronTesseract _ocr;

    public BatchPdfProcessor()
    {
        _ocr = new IronTesseract
        {
            Configuration = 
            {
                RenderSearchablePdf = true,
                // Configure for optimal performance
                Language = OcrLanguage.English
            }
        };
    }

    public async Task ProcessBatchAsync(string[] filePaths)
    {
        var results = new ConcurrentBag<(string source, string output)>();

        await Parallel.ForEachAsync(filePaths, async (filePath, ct) =>
        {
            using var input = new OcrImageInput(filePath);
            var result = _ocr.Read(input);

            string outputPath = Path.ChangeExtension(filePath, ".searchable.pdf");
            result.SaveAsSearchablePdf(outputPath);

            results.Add((filePath, outputPath));
        });

        Console.WriteLine($"Processed {results.Count} files");
    }
}

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

Public Class BatchPdfProcessor
    Private ReadOnly _ocr As IronTesseract

    Public Sub New()
        _ocr = New IronTesseract With {
            .Configuration = New OcrConfiguration With {
                .RenderSearchablePdf = True,
                ' Configure for optimal performance
                .Language = OcrLanguage.English
            }
        }
    End Sub

    Public Async Function ProcessBatchAsync(filePaths As String()) As Task
        Dim results As New ConcurrentBag(Of (source As String, output As String))()

        Await Task.Run(Sub()
                           Parallel.ForEach(filePaths, Sub(filePath)
                                                           Using input As New OcrImageInput(filePath)
                                                               Dim result = _ocr.Read(input)

                                                               Dim outputPath As String = Path.ChangeExtension(filePath, ".searchable.pdf")
                                                               result.SaveAsSearchablePdf(outputPath)

                                                               results.Add((filePath, outputPath))
                                                           End Using
                                                       End Sub)
                       End Sub)

        Console.WriteLine($"Processed {results.Count} files")
    End Function
End Class

var advancedOcr = new IronTesseract
{
    Configuration = 
    {
        RenderSearchablePdf = true,
        TesseractVariables = new Dictionary<string, object>
        {
            { "preserve_interword_spaces", 1 },
            { "tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" }
        },
        PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    Language = OcrLanguage.EnglishBest
};

Imports IronOcr

Dim advancedOcr As New IronTesseract With {
    .Configuration = New TesseractConfiguration With {
        .RenderSearchablePdf = True,
        .TesseractVariables = New Dictionary(Of String, Object) From {
            {"preserve_interword_spaces", 1},
            {"tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"}
        },
        .PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    .Language = OcrLanguage.EnglishBest
}