DocumentWriter Class

Imports Leadtools
Imports Leadtools.Codecs
Imports Leadtools.Forms.DocumentWriters
Imports Leadtools.Forms.Ocr

' Windows API functions needed to load/delete an EMF
<DllImport("gdi32.dll")> _
Private Shared Function GetEnhMetaFile(ByVal lpszMetaFile As String) As IntPtr
End Function
<DllImport("gdi32.dll")> _
Private Shared Function DeleteEnhMetaFile(ByVal hemf As IntPtr) As Boolean
End Function
Private Sub DocumentWriterExample()
    Dim tifFileName1 As String = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.tif")
    Dim tifFileName2 As String = Path.Combine(LEAD_VARS.ImagesDir, "Ocr2.tif")

    Dim outputDirectory As String = LEAD_VARS.ImagesDir

    ' Create the output directory
    If Directory.Exists(outputDirectory) Then
        Directory.Delete(outputDirectory, True)
    End If

    Directory.CreateDirectory(outputDirectory)

    ' Create an instance of the engine
    Using ocrEngine As IOcrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, False)
        ' Start the engine using default parameters
        Console.WriteLine("Starting up the engine...")
        ocrEngine.Startup(Nothing, Nothing, Nothing, LEAD_VARS.OcrAdvantageRuntimeDir)

        ' Create the OCR document
        Console.WriteLine("Creating the OCR document...")
        Dim ocrDocumentManager As IOcrDocumentManager = ocrEngine.DocumentManager
        Using ocrDocument As IOcrDocument = ocrDocumentManager.CreateDocument()
            ' Add the pages to the document
            Console.WriteLine("Adding the pages...")
            ocrDocument.Pages.AddPage(tifFileName1, Nothing)
            ocrDocument.Pages.AddPage(tifFileName2, Nothing)

            ' Recognize the pages to this document. Note, we did not call AutoZone, it will explicitly be called by Recognize
            Console.WriteLine("Recognizing all the pages...")
            ocrDocument.Pages.Recognize(Nothing)

            ' Save to all the formats supported by this OCR engine
            Dim formats As Array = [Enum].GetValues(GetType(DocumentFormat))
            For Each format As DocumentFormat In formats
                Dim friendlyName As String = DocumentWriter.GetFormatFriendlyName(format)
                Console.WriteLine("Saving (using default options) to {0}...", friendlyName)

                ' Construct the output file name (output_directory + document_format_name + . + extension)
                Dim extension As String = DocumentWriter.GetFormatFileExtension(format)
                Dim outputFileName As String = Path.Combine(outputDirectory, format.ToString() + "." + extension)

                ' Save the document
                ocrDocument.Save(outputFileName, format, Nothing)

                ' If this is the LTD format, convert it to PDF
                If format = DocumentFormat.Ltd Then
                    Console.WriteLine("Converting the LTD file to PDF...")
                    Dim pdfFileName As String = Path.Combine(outputDirectory, format.ToString() + "_pdf.pdf")
                    Dim docWriter As DocumentWriter = ocrEngine.DocumentWriterInstance
                    docWriter.Convert(outputFileName, pdfFileName, DocumentFormat.Pdf)
                End If
            Next

            ' Now save to all the engine native formats (if any) supported by the engine
            Dim engineFormats() As String = ocrDocumentManager.GetSupportedEngineFormats()
            For Each engineFormat As String In engineFormats
                Dim friendlyName As String = ocrDocumentManager.GetEngineFormatFriendlyName(engineFormat)
                Console.WriteLine("Saving to engine native format {0}...", friendlyName)

                ' Construct the output file name (output_directory + "engine" + engine_format_name + . + extension)
                Dim extension As String = ocrDocumentManager.GetEngineFormatFileExtension(engineFormat)
                Dim outputFileName As String = Path.Combine(outputDirectory, "engine_" + engineFormat + "." + extension)

                ' To use this format, set it in the IOcrDocumentManager.EngineFormat and do a normal save using DocumentFormat.User
                ' Save the document
                ocrDocumentManager.EngineFormat = engineFormat
                ocrDocument.Save(outputFileName, DocumentFormat.User, Nothing)
            Next
        End Using

        ' Shutdown the engine
        ' Note: calling Dispose will also automatically shutdown the engine if it has been started
        Console.WriteLine("Shutting down...")
        ocrEngine.Shutdown()
    End Using
End Sub

Public NotInheritable Class LEAD_VARS
Public Const ImagesDir As String = "C:\Users\Public\Documents\LEADTOOLS Images"
Public Const OcrAdvantageRuntimeDir As String = "C:\LEADTOOLS 18\Bin\Common\OcrAdvantageRuntime"
End Class