DocumentPageText Class

'Declaration
 
<SerializableAttribute()>
Public Class DocumentPageText 

Public Sub DocumentPageTextExample()
   Dim documentFileName As String
   Using dlg As New OpenFileDialog()
      If dlg.ShowDialog() <> System.Windows.Forms.DialogResult.OK Then
         Return
      End If

      documentFileName = dlg.FileName
   End Using

   ' Load the document at 200 DPI
   Dim loadOptions As New DocumentReaderLoadOptions()
   loadOptions.Resolution = 200
   Dim reader As DocumentReader = DocumentReader.Create(documentFileName, loadOptions)

   ' If this is a Raster document such as TIFF or JPEG, we must use an OCR engine
   Dim ocrEngine As IOcrEngine = Nothing

   If reader.ReaderType = DocumentReaderType.Raster Then
      ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, False)
      ocrEngine.Startup(Nothing, Nothing, Nothing, Nothing)
   End If

   reader.ObjectManager.BeginParse(ocrEngine)

   ' Get the text of the first page
   Dim page As DocumentReaderPage = reader.Pages(0)
   Dim pageText As DocumentPageText = reader.ObjectManager.ParsePageText(page)

   ' Create the bitmap to draw the objects to
   Using btmp As New Bitmap(page.PixelWidth, page.PixelHeight)
      btmp.SetResolution(CType(page.DpiX, Single), CType(page.DpiY, Single))
      Using g As Graphics = Graphics.FromImage(btmp)
         g.Clear(Color.White)

         ' Render the objects

         ' Text is a word at a time
         Dim textRect As LogicalRectangle = LogicalRectangle.Empty
         Dim textFontHeight As Double = 0
         Dim textWord As New StringBuilder()

         For Each character As DocumentCharacter In pageText.Characters
            ' Add the text code and rects together
            textWord.Append(character.Code)
            If textRect.IsEmpty Then
               textRect = character.Bounds
            Else
               textRect = LogicalRectangle.Union(textRect, character.Bounds)
            End If

            textFontHeight = Math.Max(textFontHeight, character.FontSize)

            ' If this is the last object in a word, render it
                  If character.IsEndOfWord OrElse character.IsEndOfLine OrElse character.IsEndOfParagraph OrElse character.IsEndOfPage Then
                      RenderText(g, pageText, textWord.ToString(), textRect, character, textFontHeight)

                      textWord = New StringBuilder()
                      textRect = LogicalRectangle.Empty
                  End If
         Next

         ' Save the result as PNG
         Using saveDlg As New SaveFileDialog()
            saveDlg.Filter = "PNG files|*.png"
            If saveDlg.ShowDialog() = System.Windows.Forms.DialogResult.OK Then
               btmp.Save(saveDlg.FileName, System.Drawing.Imaging.ImageFormat.Png)
            End If
         End Using
      End Using
   End Using

   reader.ObjectManager.EndParse()

   If Not IsNothing(ocrEngine) Then
      ocrEngine.Dispose()
   End If

   reader.Dispose()
End Sub

  Private Shared Sub RenderText(ByVal g As Graphics, ByVal pageText As DocumentPageText, _
                                ByVal text As String, ByVal textRect As LogicalRectangle, _
                                ByVal character As DocumentCharacter, ByVal textFontHeight _
                                As Double)
      ' Create the font
      Dim font As DocumentFont = pageText.Fonts(character.FontIndex)
      Dim faceName As String = font.FaceName
      If String.IsNullOrEmpty(faceName) Then
          ' Could be an embedded font, use Arial
          faceName = "Arial"
      End If

      Dim fontStyle As FontStyle = fontStyle.Regular

      If (font.FontStyle And DocumentFontStyle.Bold) = DocumentFontStyle.Bold Then
          fontStyle = fontStyle Or fontStyle.Bold
      End If

      If (font.FontStyle And DocumentFontStyle.Italic) = DocumentFontStyle.Italic Then
          fontStyle = fontStyle Or fontStyle.Italic
      End If

      If (font.FontStyle And DocumentFontStyle.Underline) = DocumentFontStyle.Underline Then
          fontStyle = fontStyle Or fontStyle.Underline
      End If

      Using f As New Font(faceName, CType(textFontHeight * 72 / g.DpiY, Single), fontStyle)
          Dim rect As New Rectangle(CType(textRect.X, Integer), CType(textRect.Y, Integer), _
                                    CType(textRect.Width, Integer), CType(textRect.Height, _
                                    Integer))

          Using sf As New StringFormat()
              sf.Alignment = StringAlignment.Center
              sf.LineAlignment = StringAlignment.Center
              sf.FormatFlags = sf.FormatFlags Or StringFormatFlags.NoClip Or StringFormatFlags.NoWrap

              g.DrawString(text, f, Brushes.Black, rect, sf)
          End Using
      End Using
  End Sub