Link Search Menu Expand Document

Parallel Processing of PDF files - VB.NET

PDF Extractor SDK sample in VB.NET demonstrating ‘Parallel Processing of PDF files’

Module1.vb
Imports System.IO
Imports System.Threading
Imports Bytescout.PDFExtractor

Module Module1

    ' Limit to 4 threads in queue.
    ' Set this value to number of your processor cores for max performance.
    ReadOnly ThreadLimiter As Semaphore = New Semaphore(4, 4)

    <MTAThread()>
    Sub Main()

        ' Get all PDF files in a folder
        Dim files = Directory.GetFiles("..\..\..\..\", "*.pdf")
        ' Array of events to wait
        Dim doneEvents(files.Length - 1) As ManualResetEvent

        For i As Integer = 0 To files.Length - 1

            ' Wait for the queue
            ThreadLimiter.WaitOne()

            ' Start thread with filename and event in params
            doneEvents(i) = New ManualResetEvent(False)
            Dim threadData As Object = New Object() {files(i), doneEvents(i)}
            ThreadPool.QueueUserWorkItem(AddressOf ConvertPdfToTxt, threadData)

        Next

        ' Wait until all threads finish
        WaitHandle.WaitAll(doneEvents)

        Console.WriteLine()
        Console.WriteLine("All is done.")
        Console.WriteLine()
        Console.WriteLine("Press any key to exit...")
        Console.ReadKey()

    End Sub

    Private Sub ConvertPdfToTxt(ByVal state As Object)

        ' Get filename and event from params
        Dim file As String = state(0)
        Dim doneEvent As ManualResetEvent = state(1)

        Dim resultFileName = Path.GetFileName(file) + ".txt"

        Try

            Console.WriteLine("Converting " + file)

            Using extractor As New TextExtractor("demo", "demo")

                extractor.LoadDocumentFromFile(file)
                extractor.SaveTextToFile(resultFileName)

            End Using

            Console.WriteLine("Finished " + resultFileName)

        Finally

            ' Signal the thread is finished
            doneEvent.Set()
            ' Release semaphore
            ThreadLimiter.Release()

        End Try

    End Sub

End Module

Resources.Designer.vb
'------------------------------------------------------------------------------
' <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("Parallel_Processing.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

Settings.Designer.vb
'------------------------------------------------------------------------------
' <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", "10.0.0.0"), _
     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.Parallel_Processing.My.MySettings
            Get
                Return Global.Parallel_Processing.My.MySettings.Default
            End Get
        End Property
    End Module
End Namespace

Download Source Code (.zip)

Return to the previous page Explore PDF Extractor SDK