iTextSharp Twisting CCITTFaxDecode extracted data with GetDrawingImage()

Question

On certain images, when I call:

PdfImageObject pimg = new PdfImageObject(stream);
Image bmp = pimg.GetDrawingImage();

The Image that is returned is twisted. I've seen this before and it usually has to do with byte alignment but I'm not sure how to get around this.

The /DecodeParms for this object are /EndOfLine true /K 0 /Columns 3300.

I have tried using the GetStreamBytesRaw() with BitMiracle.LibTiff and with it I can get the data formatted properly although the image is rotated. I'd prefer for GetDrawingImage() to decode the data properly if possible, assuming that is the problem.

I could provide the PDF via email if requested.

Thanks, Darren

Answer 1

For anyone else that runs across this scenario here is my solution. The key to this puzzle was understanding that /K 0 is G3, /K -1 (or anything less than 0) is G4 /K 1 (or anything greater than 0) is G3-2D.

The twisting happens when you try to make G3 compressed data fit into a G4 image which it appears that is what iTextSharp may be doing. I know it definitely does not work with how I have iTextSharp implemented in my project. I confess that I cannot decipher all the decoding stuff that iTextSharp is doing so it could be something I'm missing too.

EndOfLine didn't have any part in this puzzle but I still think putting line feeds in binary data is a strange practice.

99% of this code came from BitMiracle.LibTiff.Net - Thank you.

int nK = 0;// Default to 0 like the PDF Spec
PdfObject oDecodeParms = stream.Get(PdfName.DECODEPARMS);
if (oDecodeParms is PdfDictionary)
{
    PdfObject oK0 = ((PdfDictionary)oDecodeParms).Get(PdfName.K);
    if (oK0 != null)
        nK = ((PdfNumber)oK0).IntValue;
}

using (MemoryStream ms = new MemoryStream())
{
    using (Tiff tiff = Tiff.ClientOpen("custom", "w", ms, new TiffStream()))
    {
        tiff.SetField(TiffTag.IMAGEWIDTH, width);
        tiff.SetField(TiffTag.IMAGELENGTH, height);
        if (nK == 0 || nK > 0) // 0 = Group 3, > 0 = Group 3 2D
            tiff.SetField(TiffTag.COMPRESSION, Compression.CCITTFAX3);
        else if (nK < 0) // < 0 = Group 4
            tiff.SetField(TiffTag.COMPRESSION, Compression.CCITTFAX4);
        tiff.SetField(TiffTag.BITSPERSAMPLE, bpc);
        tiff.SetField(TiffTag.SAMPLESPERPIXEL, 1);
        tiff.WriteRawStrip(0, rawBytes, rawBytes.Length); //saving the tiff file using the raw bytes retrieved from the PDF.
        tiff.Close();
    }

    TiffStreamForBytes byteStream = new TiffStreamForBytes(ms.ToArray());

    using (Tiff input = Tiff.ClientOpen("bytes", "r", null, byteStream))
    {
        int stride = input.ScanlineSize();

        Bitmap result = new Bitmap(width, height, pixelFormat);
        ColorPalette palette = result.Palette;
        palette.Entries[0] = System.Drawing.Color.White;
        palette.Entries[1] = System.Drawing.Color.Black;
        result.Palette = palette;

        for (int i = 0; i < height; i++)
        {
            Rectangle imgRect = new Rectangle(0, i, width, 1);
            BitmapData imgData = result.LockBits(imgRect, ImageLockMode.WriteOnly, pixelFormat);

            byte[] buffer = new byte[stride];
            input.ReadScanline(buffer, i);

            System.Runtime.InteropServices.Marshal.Copy(buffer, 0, imgData.Scan0, buffer.Length);
            result.UnlockBits(imgData);
        }
    }
}

/// <summary>
/// Custom read-only stream for byte buffer that can be used
/// with Tiff.ClientOpen method.
/// </summary>
public class TiffStreamForBytes : TiffStream
{
    private byte[] m_bytes;
    private int m_position;

    public TiffStreamForBytes(byte[] bytes)
    {
        m_bytes = bytes;
        m_position = 0;
    }

    public override int Read(object clientData, byte[] buffer, int offset, int count)
    {
        if ((m_position + count) > m_bytes.Length)
            return -1;

        Buffer.BlockCopy(m_bytes, m_position, buffer, offset, count);
        m_position += count;
        return count;
    }

    public override void Write(object clientData, byte[] buffer, int offset, int count)
    {
        throw new InvalidOperationException("This stream is read-only");
    }

    public override long Seek(object clientData, long offset, SeekOrigin origin)
    {
        switch (origin)
        {
            case SeekOrigin.Begin:
                if (offset > m_bytes.Length)
                    return -1;

                m_position = (int)offset;
                return m_position;

            case SeekOrigin.Current:
                if ((offset + m_position) > m_bytes.Length)
                    return -1;

                m_position += (int)offset;
                return m_position;

            case SeekOrigin.End:
                if ((m_bytes.Length - offset) < 0)
                    return -1;

                m_position = (int)(m_bytes.Length - offset);
                return m_position;
        }

        return -1;
    }

    public override void Close(object clientData)
    {
        // nothing to do
        return;
    }

    public override long Size(object clientData)
    {
        return m_bytes.Length;
    }
}