'
' PDFNet Copyright (c) 2001-2008 by PDFTron Systems Inc. All Rights Reserved.
'

Imports System

Imports pdftron
Imports pdftron.Common
Imports pdftron.Filters
Imports pdftron.SDF
Imports pdftron.PDF

Module Module1

    Sub ProcessElements(ByVal reader As ElementReader)
        Dim element As Element = reader.Next()
        While Not IsNothing(Element)  ' Read page contents
            If Element.GetType() = Element.Type.e_path Then
                ' Process path data...
                Dim data As Double() = Element.GetPathPoints()
				Dim sz As Integer = element.GetPointCount()
				Console.WriteLine("Process Element.Type.e_path")
            ElseIf Element.GetType() = Element.Type.e_text Then
                ' Process text strings...
                Dim sz As Integer = Element.GetTextDataSize()
                Dim data As String = element.GetTextString()
				Console.WriteLine("Process Element.Type.e_text")
                ' Console.WriteLine(data)
			ElseIf element.GetType() = element.Type.e_image Then
				' Process images...
				Console.WriteLine("Process Element.Type.e_image")
			ElseIf element.GetType() = element.Type.e_form Then
				' Process form XObjects
				reader.FormBegin()
				Console.WriteLine("Process Element.Type.e_form")
				ProcessElements(reader)
				reader.End()
			End If
			element = reader.Next()
		End While
    End Sub

    Sub Main()

        PDFNet.Initialize()
		PDFNet.SetResourcesPath("../../../../resources")

		' Relative path to the folder containing test files.
		Dim input_path As String = "../../../TestFiles/"
		' Dim output_path As String = "../../../TestFiles/Output/"

        Console.WriteLine("-------------------------------------------------")
        Console.WriteLine("Extract text data from all pages in the document.")

        ' Open the test file
        Console.WriteLine("Opening the input file...")
		Dim doc As PDFDoc = New PDFDoc(input_path + "newsletter.pdf")
		doc.InitSecurityHandler()

        Dim itr As PageIterator = doc.GetPageIterator()

        Dim page_reader As ElementReader = New ElementReader
        While itr.HasNext()  '  Read every page
            Console.WriteLine("Page {0:d} ----------------------------------------", _
                itr.GetPageNumber())

            page_reader.Begin(itr.Current())
            ProcessElements(page_reader)
            page_reader.End()
            itr.Next()
        End While

        doc.Close()
        Console.WriteLine("Done.")

        PDFNet.Terminate()

    End Sub

End Module