'''' This code is part of Document Solutions for PDF .NET demos.'' Copyright (c) MESCIUS inc. All rights reserved.''Imports System.IOImports System.Collections.GenericImports GrapeCity.Documents.Pdf
'' When merging PDFs that contain identical images, by default the resulting PDF'' will end up containing several copies of the same image.'' To ensure that the PDF is not larger than necessary, DsPdf provides the method'' GcPdfDocument.RemoveDuplicateImages() that scans the PDF, finds and removes duplicates.'' The MergeDocumentOptions class also has the property RemoveDuplicateImages,'' which allows you to scan for/remove duplicates at once when merging PDFs,'' but by default it is false. This is because the occurrence of duplicate images'' in merged PDFs is not a very common scenario, while scanning for duplicates'' may affect the performance of the merge. Also, if you are merging multiple PDFs'' that contain duplicate images, it is better to merge all PDFs first, and then'' remove all duplicates from the final PDF at once with a single call to'' GcPdfDocument.RemoveDuplicateImages(), as demonstrated by this demo.'''' In this demo we merge several sample invoices that include the same company logo,'' and then call GcPdfDocument.RemoveDuplicateImages() and compare the sizes of the'' resulting PDF before and after that call.'''' See also OptimizeFonts.Public Class RemoveDuplicateImages    Private Shared Function MergePDFs(dest As GcPdfDocument, fpath As String) As FileStream        Dim d = New GcPdfDocument()        Dim fs = File.OpenRead(fpath)        d.Load(fs)        dest.MergeWithDocument(d)        Return fs    End Function
    Public Function CreatePDF(ByVal stream As Stream) As Integer        '' Input file names:        Const N = 7        Dim fpaths = New List(Of String)(N)        For i = 1 To 7            fpaths.Add(Path.Combine("Resources", "PDFs", $"DsDemoInvoice{i}.pdf"))        Next        ' Facilitate clean up:        Dim fss = New List(Of FileStream)()        Dim tempPdfBefore As String = Nothing        Dim tempPdfAfter As String = Nothing        Try            Dim doc = New GcPdfDocument()            '' Merge the invoices into a single PDF:            For i = 0 To N - 1                fss.Add(MergePDFs(doc, fpaths(i)))            Next
            '' Compare the merged PDF size before and after removing duplicates:            tempPdfBefore = Path.GetTempFileName()            doc.Save(tempPdfBefore)            Dim sizeBefore = New FileInfo(tempPdfBefore).Length            doc.RemoveDuplicateImages()            tempPdfAfter = Path.GetTempFileName()            doc.Save(tempPdfAfter)            Dim sizeAfter = New FileInfo(tempPdfAfter).Length            Util.AddNote(String.Format(                "Using the GcPdfDocument.RemoveDuplicateImages() method on this document (which was produced by merging " &                "several demo invoices with the same company logo) reduced the size of the merged PDF from {0:N0} to {1:N0} bytes.",                sizeBefore, sizeAfter),                doc.Pages.Insert(0))            doc.Save(stream)            '' Done:            Return doc.Pages.Count        Finally            If tempPdfBefore IsNot Nothing Then                File.Delete(tempPdfBefore)            End If            If tempPdfAfter IsNot Nothing Then                File.Delete(tempPdfAfter)            End If            fss.ForEach(Sub(fs_) fs_.Dispose())        End Try    End FunctionEnd Class