Display Unicode characters in converting Html to Pdf

Question

I am using itextsharp dll to convert HTML to PDF.

The HTML has some Unicode characters like α, β... when I try to convert HTML to PDF, Unicode characters are not shown in PDF.

My function:

Document doc = new Document(PageSize.LETTER);

using (FileStream fs = new FileStream(Path.Combine("Test.pdf"), FileMode.Create, FileAccess.Write, FileShare.Read))
{
    PdfWriter.GetInstance(doc, fs);

    doc.Open();
    doc.NewPage();

    string arialuniTff = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Fonts),
                                      "ARIALUNI.TTF");

    BaseFont bf = BaseFont.CreateFont(arialuniTff, BaseFont.IDENTITY_H, BaseFont.EMBEDDED);

    Font fontNormal = new Font(bf, 12, Font.NORMAL);

    List<IElement> list = HTMLWorker.ParseToList(new StringReader(stringBuilder.ToString()),
                                                 new StyleSheet());
    Paragraph p = new Paragraph {Font = fontNormal};

    foreach (var element in list)
    {
        p.Add(element);
        doc.Add(p);
    }

    doc.Close();
}

Answer 1

You can also use the new XMLWorkerHelper (from library itextsharp.xmlworker), you need to override the default FontFactory implementation however.

void GeneratePdfFromHtml()
{
  const string outputFilename = @".\Files\report.pdf";
  const string inputFilename = @".\Files\report.html";

  using (var input = new FileStream(inputFilename, FileMode.Open))
  using (var output = new FileStream(outputFilename, FileMode.Create))
  {
    CreatePdf(input, output);
  }
}

void CreatePdf(Stream htmlInput, Stream pdfOutput)
{
  using (var document = new Document(PageSize.A4, 30, 30, 30, 30))
  {
    var writer = PdfWriter.GetInstance(document, pdfOutput);
    var worker = XMLWorkerHelper.GetInstance();

    document.Open();
    worker.ParseXHtml(writer, document, htmlInput, null, Encoding.UTF8, new UnicodeFontFactory());

    document.Close();
  }    
}

public class UnicodeFontFactory : FontFactoryImp
{
    private static readonly string FontPath = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Fonts),
      "arialuni.ttf");

    private readonly BaseFont _baseFont;

    public UnicodeFontFactory()
    {
      _baseFont = BaseFont.CreateFont(FontPath, BaseFont.IDENTITY_H, BaseFont.EMBEDDED);

    }

    public override Font GetFont(string fontname, string encoding, bool embedded, float size, int style, BaseColor color,
      bool cached)
    {
      return new Font(_baseFont, size, style, color);
    }
}