AppendLtd Method

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

Public Shared Sub AppendLtdExample()
    ' Get a multi-page source file
    Dim sourceFileName As String = GetImageFileName()
    Dim destFileName As String = Path.Combine(LEAD_VARS.ImagesDir, "AppendLtdExample.pdf")
    File.Delete(destFileName)
    ' Use OCR Advantage engine
    Using ocrEngine As IOcrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, False)
        ocrEngine.Startup(Nothing, Nothing, Nothing, LEAD_VARS.OcrAdvantageRuntimeDir)

        ' Get the number of pages in the source file
        Dim pageCount As Integer
        Using imageInfo As CodecsImageInfo = ocrEngine.RasterCodecsInstance.GetInformation(sourceFileName, True)
            pageCount = imageInfo.TotalPages
        End Using

        Console.WriteLine("OCRing {0} pages", pageCount)

        ' Use all possible cores
        Dim maxThreads As Integer = Environment.ProcessorCount
        Console.WriteLine("Machine has {0} cores", maxThreads)

        Dim threadCount As Integer = Math.Min(maxThreads, pageCount)
        Console.WriteLine("Using {0} threads", threadCount)

        ' Initialie the thread parameters
        Dim threadParams(threadCount - 1) As MyThreadParam
        For i As Integer = 0 To threadCount - 1
            threadParams(i) = New MyThreadParam()
            threadParams(i).ThreadFinishedEvent = New AutoResetEvent(False)
            threadParams(i).OcrEngine = ocrEngine
            ' We can re-use the documents, so create them once here
            threadParams(i).OcrDocument = ocrEngine.DocumentManager.CreateDocument()
            threadParams(i).SourceFileName = sourceFileName
            ' We can re-use the LTD files, so get them here once
            threadParams(i).LtdFileName = Path.GetTempFileName()
        Next

        ' This is the LTD file we will use to append all recognition data
        ' from all threads
        Dim mainLtdFileName As String = Path.GetTempFileName()
        File.Delete(mainLtdFileName)

        Dim pageNumber As Integer = 1
        While pageNumber <= pageCount
            Dim queuedUpEvents As New List(Of AutoResetEvent)

            ' Queue up the threads, each thread will have its own
            ' IOcrDocument to recognize one page to a separate LTD file
            Dim ltdCounter As Integer = 0
            For threadIndex As Integer = 0 To threadCount - 1
                If pageNumber <= pageCount Then
                    ' Queue up this page
                    Console.WriteLine("Queing up page {0}", pageNumber)
                    threadParams(threadIndex).PageNumber = pageNumber
                    queuedUpEvents.Add(threadParams(threadIndex).ThreadFinishedEvent)
                    ThreadPool.QueueUserWorkItem(AddressOf MyThreadProc, threadParams(threadIndex))
                    pageNumber = pageNumber + 1
                    ltdCounter = ltdCounter + 1
                End If
            Next

            ' Wait for the queued up threads to finish
            Console.WriteLine("Waiting on queued up pages to finished")
            WaitHandle.WaitAll(queuedUpEvents.ToArray())

            Console.WriteLine("Appending LTDs")
            For i As Integer = 0 To ltdCounter - 1
                ' Notice, first time, the main LTD does not exist, AppendLtd will
                ' just copy the data over from the source file
                ocrEngine.DocumentWriterInstance.AppendLtd(threadParams(i).LtdFileName, mainLtdFileName)
            Next
        End While

        ' We are done, convert the LTD to final format, here, we will
        ' use PDF
        Console.WriteLine("Converting to final format")
        ocrEngine.DocumentWriterInstance.Convert(mainLtdFileName, destFileName, DocumentFormat.Pdf)

        ' Clean-up
        For i As Integer = 0 To threadCount - 1
            threadParams(i).ThreadFinishedEvent.Close()
            threadParams(i).OcrDocument.Dispose()
        Next

        Console.WriteLine("Success, file {0} is created", destFileName)
    End Using
End Sub

Class MyThreadParam
    ' Event to trigger when recognition is done
    Public ThreadFinishedEvent As AutoResetEvent
    ' OCR engine to use
    Public OcrEngine As IOcrEngine
    ' OCR Document to use
    Public OcrDocument As IOcrDocument
    ' Source image file
    Public SourceFileName As String
    ' Page number to recognize by this thread
    Public PageNumber As Integer
    ' LTD file to save temporary recognition data
    Public LtdFileName As String
End Class

Private Shared Sub MyThreadProc(ByVal state As Object)
    Dim threadParams As MyThreadParam = CType(state, MyThreadParam)
    Console.WriteLine("  Thread {0} is working on pages {1}", Thread.CurrentThread.GetHashCode(), threadParams.PageNumber)

    Try
        ' Delete the LTD file if it exists so we can put fresh data in it
        File.Delete(threadParams.LtdFileName)

        ' Clear any previous pages in this document
        threadParams.OcrDocument.Pages.Clear()

        ' Load the page
        Console.WriteLine("  Thread {0} is loading the page", Thread.CurrentThread.GetHashCode())
        threadParams.OcrDocument.Pages.AddPages(threadParams.SourceFileName, threadParams.PageNumber, threadParams.PageNumber, Nothing)

        ' Get it, it is the last page we added
        Dim ocrPage As IOcrPage = threadParams.OcrDocument.Pages(threadParams.OcrDocument.Pages.Count - 1)

        ' Auto-zone it
        Console.WriteLine("  Thread {0} is auto-zoning the page", Thread.CurrentThread.GetHashCode())
        ocrPage.AutoZone(Nothing)

        ' Recognize it
        Console.WriteLine("  Thread {0} is recognizing the page", Thread.CurrentThread.GetHashCode())
        ocrPage.Recognize(Nothing)

        ' Save it
        Console.WriteLine("  Thread {0} is saving the page", Thread.CurrentThread.GetHashCode())
        threadParams.OcrDocument.Save(threadParams.LtdFileName, DocumentFormat.Ltd, Nothing)
    Finally
        Console.WriteLine("  Thread {0} is done", Thread.CurrentThread.GetHashCode())
        threadParams.ThreadFinishedEvent.Set()
    End Try
End Sub

Private Shared Function GetImageFileName() As String
    Dim pageTileTemplate As String = Path.Combine(LEAD_VARS.ImagesDir, "Ocr{0}.tif")
    Dim multiPageImageFileName As String = Path.Combine(LEAD_VARS.ImagesDir, "AppendLtdExample.tif")

    File.Delete(multiPageImageFileName)

    ' Create a multi-page TIF file by stitching OCR1 to OCR4.tif shipped with LEADTOOLS
    Using codecs As New RasterCodecs()
        Dim finalImage As RasterImage = Nothing

        For page As Integer = 1 To 4
            Dim pageImage As RasterImage = codecs.Load(String.Format(pageTileTemplate, page))
            If IsNothing(finalImage) Then
                finalImage = pageImage
            Else
                finalImage.AddPage(pageImage)
                pageImage.Dispose()
            End If
        Next

        ' Save the final image
        codecs.Save(finalImage, multiPageImageFileName, RasterImageFormat.CcittGroup4, 1)
    End Using

    Return multiPageImageFileName
End Function

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