Hadoop文件解压缩
package Compress; import java.io.File;import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.io.compress.CompressionInputStream;
import org.apache.hadoop.mapreduce.Job;
/**
* 解压缩
* @author liguodong
*/
public> final static String file = "/liguodong/data.gz";
public static void main(String[] args) throws IOException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "DeCodec");
//打包执行必须执行的方法
job.setJarByClass(Decompression.class);
CompressionCodecFactory codecFactory = new CompressionCodecFactory(conf);
//返回一个解压缩的实例
CompressionCodec codec = codecFactory.getCodec(new Path(file));
//返回被算法解压了的输入流
CompressionInputStream inputStream = codec.createInputStream
(new FileInputStream(new File(file)));
//将输入流文件写出到去除了扩展名的文件
FileOutputStream outputStream = new FileOutputStream
(new File(codecFactory.removeSuffix(file, codec.getDefaultExtension())));
IOUtils.copyBytes(inputStream, outputStream, conf);
}
}
页:
[1]