DataUtilities.java

package org.deeplearning4j.examples.utilities;

import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;

import java.io.*;

/**
 * Created by Alex on 27/01/2017.
 */
public class DataUtilities {

    private static final int BUFFER_SIZE = 4096;

    public static void extractTarGz(String filePath, String outputPath) throws IOException {
        int fileCount = 0;
        int dirCount = 0;
        System.out.print("Extracting files");
        try(TarArchiveInputStream tais = new TarArchiveInputStream(
            new GzipCompressorInputStream( new BufferedInputStream( new FileInputStream(filePath))))){
            TarArchiveEntry entry;

            /** Read the tar entries using the getNextEntry method **/
            while ((entry = (TarArchiveEntry) tais.getNextEntry()) != null) {
                //System.out.println("Extracting file: " + entry.getName());

                //Create directories as required
                if (entry.isDirectory()) {
                    new File(outputPath + entry.getName()).mkdirs();
                    dirCount++;
                }else {
                    int count;
                    byte data[] = new byte[BUFFER_SIZE];

                    FileOutputStream fos = new FileOutputStream(outputPath + entry.getName());
                    BufferedOutputStream dest = new BufferedOutputStream(fos,BUFFER_SIZE);
                    while ((count = tais.read(data, 0, BUFFER_SIZE)) != -1) {
                        dest.write(data, 0, count);
                    }
                    dest.close();
                    fileCount++;
                }
                if(fileCount % 1000 == 0) System.out.print(".");
            }
        }

        System.out.println("\n" + fileCount + " files and " + dirCount + " directories extracted to: " + outputPath);
    }


}