-
-
Save davetransom/553aeb3c4388c3eb448c0afe564cd2e3 to your computer and use it in GitHub Desktop.
Use pure C# to extract .tar and .tar.gz files
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using System; | |
using System.IO; | |
using System.IO.Compression; | |
using System.Text; | |
namespace TarExample | |
{ | |
public class Tar | |
{ | |
/// <summary> | |
/// Extracts a <i>.tar.gz</i> archive to the specified directory. | |
/// </summary> | |
/// <param name="filename">The <i>.tar.gz</i> to decompress and extract.</param> | |
/// <param name="outputDir">Output directory to write the files.</param> | |
public static void ExtractTarGz(string filename, string outputDir) | |
{ | |
using (var stream = File.OpenRead(filename)) | |
ExtractTarGz(stream, outputDir); | |
} | |
/// <summary> | |
/// Extracts a <i>.tar.gz</i> archive stream to the specified directory. | |
/// </summary> | |
/// <param name="stream">The <i>.tar.gz</i> to decompress and extract.</param> | |
/// <param name="outputDir">Output directory to write the files.</param> | |
public static void ExtractTarGz(Stream stream, string outputDir) | |
{ | |
// A GZipStream is not seekable, so copy it first to a MemoryStream | |
using (var gzip = new GZipStream(stream, CompressionMode.Decompress)) | |
{ | |
const int chunk = 4096; | |
using (var ms = new MemoryStream()) | |
{ | |
int read; | |
var buffer = new byte[chunk]; | |
do | |
{ | |
read = gzip.Read(buffer, 0, chunk); | |
ms.Write(buffer, 0, read); | |
} | |
while (read == chunk); | |
ms.Seek(0, SeekOrigin.Begin); | |
ExtractTar(ms, outputDir); | |
} | |
} | |
} | |
/// <summary> | |
/// Extracts a <c>tar</c> archive to the specified directory. | |
/// </summary> | |
/// <param name="filename">The <i>.tar</i> to extract.</param> | |
/// <param name="outputDir">Output directory to write the files.</param> | |
public static void ExtractTar(string filename, string outputDir) | |
{ | |
using (var stream = File.OpenRead(filename)) | |
ExtractTar(stream, outputDir); | |
} | |
/// <summary> | |
/// Extracts a <c>tar</c> archive to the specified directory. | |
/// </summary> | |
/// <param name="stream">The <i>.tar</i> to extract.</param> | |
/// <param name="outputDir">Output directory to write the files.</param> | |
public static void ExtractTar(Stream stream, string outputDir) | |
{ | |
var buffer = new byte[100]; | |
while (true) | |
{ | |
stream.Read(buffer, 0, 100); | |
var name = Encoding.ASCII.GetString(buffer).Trim('\0', ' '); | |
if (string.IsNullOrWhiteSpace(name)) | |
break; | |
stream.Seek(24, SeekOrigin.Current); | |
stream.Read(buffer, 0, 12); | |
long size; | |
string hex = Encoding.ASCII.GetString(buffer, 0, 12).Trim('\0', ' '); | |
try | |
{ | |
size = Convert.ToInt64(hex, 8); | |
} | |
catch (Exception ex) | |
{ | |
throw new Exception("Could not parse hex: " + hex, ex); | |
} | |
stream.Seek(376L, SeekOrigin.Current); | |
var output = Path.Combine(outputDir, name); | |
if (size > 0) // ignores directory entries | |
{ | |
Directory.CreateDirectory(Path.GetDirectoryName(output)); | |
using (var fs = File.Open(output, FileMode.OpenOrCreate, FileAccess.Write)) | |
{ | |
var blob = new byte[size]; | |
stream.Read(blob, 0, blob.Length); | |
fs.Write(blob, 0, blob.Length); | |
} | |
} | |
var pos = stream.Position; | |
var offset = 512 - (pos % 512); | |
if (offset == 512) | |
offset = 0; | |
stream.Seek(offset, SeekOrigin.Current); | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
You can do it better on line 95
Insted of ignore 0 size files also, you can only ignore directories using:
Look my forked file.