Decompress GZIP

GZIP data is often decompressed before use. A byte array containing GZIP bytes can be translated into one with the original representation of bits.

Method notes

It is possible to use a wrapper method around the GZipStream and other streams. We can implement reliable decompression methods in C# code.

This program receives a byte array that contains GZIP data. It transforms the data into a byte array that contains the original representation of bytes.

using System;
using System.IO;
using System.IO.Compression;

class Program
{
    static void Main()
    {
        // Open a compressed file on disk.
        // ... Then decompress it with the method here.
        // ... Then write the length of each array.
        byte[] file = File.ReadAllBytes("C:\\perlgzips\\~stat.gz");
        byte[] decompressed = Decompress(file);
        Console.WriteLine(file.Length);
        Console.WriteLine(decompressed.Length);
    }

    static byte[] Decompress(byte[] gzip)
    {
        // Create a GZIP stream with decompression mode.
        // ... Then create a buffer and write into while reading from the GZIP stream.
        using (GZipStream stream = new GZipStream(new MemoryStream(gzip), CompressionMode.Decompress))
        {
            const int size = 4096;
            byte[] buffer = new byte[size];
            using (MemoryStream memory = new MemoryStream())
            {
                int count = 0;
                do
                {
                    count = stream.Read(buffer, 0, size);
                    if (count > 0)
                    {
                        memory.Write(buffer, 0, count);
                    }
                }
                while (count > 0);
                return memory.ToArray();
            }
        }
    }
}
9106
36339

Decompress web page

This C# console program decompresses web pages in GZIP format. It uses types from System.IO, System.IO.Compression and System.Net namespaces.

using System;
using System.IO;
using System.IO.Compression;
using System.Net;

class Program
{
    static byte[] Decompress(byte[] gzip)
    {
        using (GZipStream stream = new GZipStream(new MemoryStream(gzip), CompressionMode.Decompress))
        {
            const int size = 4096;
            byte[] buffer = new byte[size];
            using (MemoryStream memory = new MemoryStream())
            {
                int count = 0;
                do
                {
                    count = stream.Read(buffer, 0, size);
                    if (count > 0)
                    {
                        memory.Write(buffer, 0, count);
                    }
                }
                while (count > 0);
                return memory.ToArray();
            }
        }
    }

    static void Main(string[] args)
    {
        try
        {
            Console.WriteLine("*** Decompress web page ***");
            Console.WriteLine("    Specify file to download");
            Console.WriteLine("Downloading: {0}", args[0]);

            // Download url.
            using (WebClient client = new WebClient())
            {
                client.Headers[HttpRequestHeader.AcceptEncoding] = "gzip";
                byte[] data = client.DownloadData(args[0]);
                byte[] decompress = Decompress(data);
                string text = System.Text.ASCIIEncoding.ASCII.GetString(decompress);

                Console.WriteLine("Size from network: {0}", data.Length);
                Console.WriteLine("Size decompressed: {0}", decompress.Length);
                Console.WriteLine("First chars:       {0}", text.Substring(0, 5));
            }
        }
        finally
        {
            Console.WriteLine("[Done]");
        }
    }
}
*** Decompress web page ***
    Specify file to download
Downloading: http://en.wikipedia.org/
Size from network: 15228
Size decompressed: 56362
First chars:       <!DOC
[Done]

Summary

We decompressed an array of GZIP bytes into an array of the original bytes. The C# method shown receives a GZIP byte array and returns the original byte array.