.NET GZipStream compress and decompress

Question

What is wrong with this code below. I always get FALSE, meaning after compression, decompressed data does not match original value.

public static bool Test()
        {
            string sample = "This is a compression test of microsoft .net gzip compression method and decompression methods";
            System.Text.ASCIIEncoding encoding = new System.Text.ASCIIEncoding();
            byte[] data = encoding.GetBytes(sample);
            bool result = false;

            //Compress
            MemoryStream cmpStream;
            cmpStream = new MemoryStream();
            GZipStream hgs = new GZipStream(cmpStream, CompressionMode.Compress);
            hgs.Write(data, 0, data.Length);
            byte[] cmpData = cmpStream.ToArray();

            MemoryStream decomStream;
            decomStream = new MemoryStream(cmpData);
            hgs = new GZipStream(decomStream, CompressionMode.Decompress);
            hgs.Read(data, 0, data.Length);

            string sampleOut = System.BitConverter.ToString(data);

            result = String.Equals(sample, sampleOut) ;
            return result;
        }

I will really appreciate if you can point out where I am making a mistake.

Answer 1

Close the GZipStream after the Write call.

Without calling Close, there's a possibility that some data is buffered and is not written to the underlying stream yet.

Answer 2

Try this code:

public static bool Test()
        {
            string sample = "This is a compression test of microsoft .net gzip compression method and decompression methods";

            System.Text.ASCIIEncoding encoding = new System.Text.ASCIIEncoding();

            byte[] data = encoding.GetBytes(sample);
            bool result = false;

            // Compress
            MemoryStream cmpStream = new MemoryStream();

            GZipStream hgs = new GZipStream(cmpStream, CompressionMode.Compress);

            hgs.Write(data, 0, data.Length);

            byte[] cmpData = cmpStream.ToArray();

            MemoryStream decomStream = new MemoryStream(cmpData);

            hgs = new GZipStream(decomStream, CompressionMode.Decompress);
            hgs.Read(data, 0, data.Length);

            string sampleOut = encoding.GetString(data);

            result = String.Equals(sample, sampleOut);
            return result;
        }

The problem what that you were not using the ASCIIEncoder to get the string back for sampleData.

EDIT: Here's a cleaned up version of the code to help with Closing/Disposing:

public static bool Test()
        {
            string sample = "This is a compression test of microsoft .net gzip compression method and decompression methods";

            System.Text.ASCIIEncoding encoding = new System.Text.ASCIIEncoding();

            byte[] data = encoding.GetBytes(sample);

            // Compress.
            GZipStream hgs;
            byte[] cmpData;

            using(MemoryStream cmpStream = new MemoryStream())
            using(hgs = new GZipStream(cmpStream, CompressionMode.Compress))
            {
                hgs.Write(data, 0, data.Length);
                hgs.Close()

                // Do this AFTER the stream is closed which sounds counter intuitive 
                // but if you do it before the stream will not be flushed
                // (even if you call flush which has a null implementation).
                cmpData = cmpStream.ToArray();
            }  

            using(MemoryStream decomStream = new MemoryStream(cmpData))
            using(hgs = new GZipStream(decomStream, CompressionMode.Decompress))
            {
                hgs.Read(data, 0, data.Length);
            }

            string sampleOut = encoding.GetString(data);

            bool result = String.Equals(sample, sampleOut);
            return result;
        }