Imports System.IO
Imports Bytescout.PDFExtractor

''' <summary>
''' The example demonstrates detection of empty pages, splitting the document to separate 
''' pages excluding empty ones, then combine parts back to a single document.
''' </summary>
Module Module1

    Dim InputFile = ".\sample.pdf"
    Dim OutputFile = ".\result.pdf"
    Dim TempFolder = ".\temp"

    Sub Main()

        ' Create and setup Bytescout.PDFExtractor.TextExtractor instance
        Dim extractor As New TextExtractor("demo", "demo")
        
        ' Load PDF document
        extractor.LoadDocumentFromFile(InputFile)

        ' List to keep non-empty page numbers
        Dim nonEmptyPages = New List(Of String)()

        ' Iterate through pages 
        For pageIndex = 0 To extractor.GetPageCount() - 1
            ' Extract page text
            Dim pageText = extractor.GetTextFromPage(pageIndex)
            ' If extracted text is not empty keep the page number
            If pageText.Length > 0 Then
                nonEmptyPages.Add((pageIndex + 1).ToString())
            End If
        Next
        
        ' Cleanup
        extractor.Dispose()


        ' Form comma-separated list of page numbers to split ("1,3,5")
        Dim ranges As String = String.Join(",", nonEmptyPages)

        ' Create Bytescout.PDFExtractor.DocumentSplitter instance
        Dim splitter = new DocumentSplitter("demo", "demo")
        splitter.OptimizeSplittedDocuments = true

        ' Split document by non-empty in temp folder
        Dim parts = splitter.Split(InputFile, ranges, TempFolder)

        ' Cleanup
        splitter.Dispose()

        
        ' Create Bytescout.PDFExtractor.DocumentMerger instance
        Dim merger = New DocumentMerger("demo", "demo")

        ' Merge parts
        merger.Merge(parts, OutputFile)

        ' Cleanup
        merger.Dispose()

        ' Delete temp folder
        Directory.Delete(TempFolder, true)
        

        ' Open the result file in default PDF viewer (for demo purposes)
        Process.Start(OutputFile)

    End Sub

End Module

'------------------------------------------------------------------------------
' <auto-generated>
'     This code was generated by a tool.
'     Runtime Version:4.0.30319.42000
'
'     Changes to this file may cause incorrect behavior and will be lost if
'     the code is regenerated.
' </auto-generated>
'------------------------------------------------------------------------------

Option Strict On
Option Explicit On


Namespace My.Resources

    'This class was auto-generated by the StronglyTypedResourceBuilder
    'class via a tool like ResGen or Visual Studio.
    'To add or remove a member, edit your .ResX file then rerun ResGen
    'with the /str option, or rebuild your VS project.
    '''<summary>
    '''  A strongly-typed resource class, for looking up localized strings, etc.
    '''</summary>
    <Global.System.CodeDom.Compiler.GeneratedCodeAttribute("System.Resources.Tools.StronglyTypedResourceBuilder", "4.0.0.0"), _
     Global.System.Diagnostics.DebuggerNonUserCodeAttribute(), _
     Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute(), _
     Global.Microsoft.VisualBasic.HideModuleNameAttribute()> _
    Friend Module Resources

        Private resourceMan As Global.System.Resources.ResourceManager

        Private resourceCulture As Global.System.Globalization.CultureInfo

        '''<summary>
        '''  Returns the cached ResourceManager instance used by this class.
        '''</summary>
        <Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
        Friend ReadOnly Property ResourceManager() As Global.System.Resources.ResourceManager
            Get
                If Object.ReferenceEquals(resourceMan, Nothing) Then
                    Dim temp As Global.System.Resources.ResourceManager = New Global.System.Resources.ResourceManager("RemoveEmptyPagesExample.Resources", GetType(Resources).Assembly)
                    resourceMan = temp
                End If
                Return resourceMan
            End Get
        End Property

        '''<summary>
        '''  Overrides the current thread's CurrentUICulture property for all
        '''  resource lookups using this strongly typed resource class.
        '''</summary>
        <Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
        Friend Property Culture() As Global.System.Globalization.CultureInfo
            Get
                Return resourceCulture
            End Get
            Set(ByVal value As Global.System.Globalization.CultureInfo)
                resourceCulture = value
            End Set
        End Property
    End Module
End Namespace

'------------------------------------------------------------------------------
' <auto-generated>
'     This code was generated by a tool.
'     Runtime Version:4.0.30319.42000
'
'     Changes to this file may cause incorrect behavior and will be lost if
'     the code is regenerated.
' </auto-generated>
'------------------------------------------------------------------------------

Option Strict On
Option Explicit On


Namespace My

    <Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute(), _
     Global.System.CodeDom.Compiler.GeneratedCodeAttribute("Microsoft.VisualStudio.Editors.SettingsDesigner.SettingsSingleFileGenerator", "11.0.0.0"), _
     Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
    Partial Friend NotInheritable Class MySettings
        Inherits Global.System.Configuration.ApplicationSettingsBase

        Private Shared defaultInstance As MySettings = CType(Global.System.Configuration.ApplicationSettingsBase.Synchronized(New MySettings), MySettings)

#Region "My.Settings Auto-Save Functionality"
#If _MyType = "WindowsForms" Then
        Private Shared addedHandler As Boolean

        Private Shared addedHandlerLockObject As New Object

        <Global.System.Diagnostics.DebuggerNonUserCodeAttribute(), Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
        Private Shared Sub AutoSaveSettings(ByVal sender As Global.System.Object, ByVal e As Global.System.EventArgs)
            If My.Application.SaveMySettingsOnExit Then
                My.Settings.Save()
            End If
        End Sub
#End If
#End Region

        Public Shared ReadOnly Property [Default]() As MySettings
            Get

#If _MyType = "WindowsForms" Then
                   If Not addedHandler Then
                        SyncLock addedHandlerLockObject
                            If Not addedHandler Then
                                AddHandler My.Application.Shutdown, AddressOf AutoSaveSettings
                                addedHandler = True
                            End If
                        End SyncLock
                    End If
#End If
                Return defaultInstance
            End Get
        End Property
    End Class
End Namespace

Namespace My

    <Global.Microsoft.VisualBasic.HideModuleNameAttribute(), _
     Global.System.Diagnostics.DebuggerNonUserCodeAttribute(), _
     Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute()> _
    Friend Module MySettingsProperty

        <Global.System.ComponentModel.Design.HelpKeywordAttribute("My.Settings")> _
        Friend ReadOnly Property Settings() As Global.RemoveEmptyPagesExample.My.MySettings
            Get
                Return Global.RemoveEmptyPagesExample.My.MySettings.Default
            End Get
        End Property
    End Module
End Namespace