学习Java压缩技术 BZIP2

http://www.java3z.com/cwbwebhome/article/article8/81131.html

 

BZip2与GZip有什么渊源,我这里不深究。我要说的只是,这两种算法,你在linux下都可以找到相应的操作命令。

GZip
压缩
gzip <file> 将得到压缩文件<file>.gz,同时删除文件<file>
解压缩
gzip -d <file>.gz 将得到压缩文件<file>,同时删除文件<file>.gz

BZip2与之相当,几乎没有什么差别~~
BZip2
压缩
bzip2 <file> 将得到压缩文件<file>.bz2,同时删除文件<file>
解压缩
bzip2 -d <file>.bz2 将得到压缩文件<file>,同时删除文件<file>.bz2

除了命令不同外,几乎是一样的!

再说实现。GZIP是JDK自带的算法实现,但BZip2则不曾享受这个待遇。 不过,强大的Apache坚决不会让这些个在Linux下如鱼得水的算法在Java世界中销声匿迹。Apache在Commons Compress中提供了相应的实现。同时,还包括众所周知的tar、cpio、zip等算法实现,其中最为丰富的当属zip实现了!

我继续依葫芦画瓢~~~
BZip2CompressorOutputStream类用于压缩
BZip2CompressorInputStream类用于解压缩


先说压缩实现,BZip2CompressorOutputStream只有一个方法用于压缩,就是带定长的write方法。简单调用如下文所示:

	/**
	 * 数据压缩
	 * 
	 * @param is
	 * @param os
	 * @throws Exception
	 */
	public static void compress(InputStream is, OutputStream os)
			throws Exception {
		BZip2CompressorOutputStream gos = new BZip2CompressorOutputStream(os);
		int count;
		byte data[] = new byte[BUFFER];
		while ((count = is.read(data, 0, BUFFER)) != -1) {
			gos.write(data, 0, count);
		}
		gos.finish();
		gos.flush();
		gos.close();
	}


与GZip实现有何差别?除了换掉了GZIPOutputStream没有任何差别。

解压缩就更不用说了,BZip2CompressorInputStream提供了一个带定长的read方法。简单调用如下文所示:

	/**
	 * 数据解压缩
	 * 
	 * @param is
	 * @param os
	 * @throws Exception
	 */
	public static void decompress(InputStream is, OutputStream os)
			throws Exception {
		BZip2CompressorInputStream gis = new BZip2CompressorInputStream(is);
		int count;
		byte data[] = new byte[BUFFER];
		while ((count = gis.read(data, 0, BUFFER)) != -1) {
			os.write(data, 0, count);
		}
		gis.close();
	}

嗯,没什么难度!
IT这行就是这样,只要你肯用心,能触类旁通,就能融会贯通!
给一个完整实现:

/**
 * 2010-4-15
 */
package org.zlex.commons.compress.compress;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.OutputStream;
import org.apache.commons.compress.compressors.bzip2.BZip2CompressorInputStream;
import org.apache.commons.compress.compressors.bzip2.BZip2CompressorOutputStream;
/**
 * BZip2工具
 * 
 * @author  <a href="mailto:zlex.dongliang@gmail.com">梁栋</a>
 * @since 1.0
 */
public abstract class BZip2Utils {
	public static final int BUFFER = 1024;
	public static final CharSequence EXT = ".bz2";
	/**
	 * 数据压缩
	 * 
	 * @param data
	 * @return
	 * @throws Exception
	 */
	public static byte[] compress(byte[] data) throws Exception {
		ByteArrayInputStream bais = new ByteArrayInputStream(data);
		ByteArrayOutputStream baos = new ByteArrayOutputStream();
		// 压缩
		compress(bais, baos);
		byte[] output = baos.toByteArray();
		baos.flush();
		baos.close();
		bais.close();
		return output;
	}
	/**
	 * 文件压缩
	 * 
	 * @param file
	 * @throws Exception
	 */
	public static void compress(File file) throws Exception {
		compress(file, true);
	}
	/**
	 * 文件压缩
	 * 
	 * @param file
	 * @param delete
	 *            是否删除原始文件
	 * @throws Exception
	 */
	public static void compress(File file, boolean delete) throws Exception {
		FileInputStream fis = new FileInputStream(file);
		FileOutputStream fos = new FileOutputStream(file.getPath() + EXT);
		compress(fis, fos);
		fis.close();
		fos.flush();
		fos.close();
		if (delete) {
			file.delete();
		}
	}
	/**
	 * 数据压缩
	 * 
	 * @param is
	 * @param os
	 * @throws Exception
	 */
	public static void compress(InputStream is, OutputStream os)
			throws Exception {
		BZip2CompressorOutputStream gos = new BZip2CompressorOutputStream(os);
		int count;
		byte data[] = new byte[BUFFER];
		while ((count = is.read(data, 0, BUFFER)) != -1) {
			gos.write(data, 0, count);
		}
		gos.finish();
		gos.flush();
		gos.close();
	}
	/**
	 * 文件压缩
	 * 
	 * @param path
	 * @throws Exception
	 */
	public static void compress(String path) throws Exception {
		compress(path, true);
	}
	/**
	 * 文件压缩
	 * 
	 * @param path
	 * @param delete
	 *            是否删除原始文件
	 * @throws Exception
	 */
	public static void compress(String path, boolean delete) throws Exception {
		File file = new File(path);
		compress(file, delete);
	}
	/**
	 * 数据解压缩
	 * 
	 * @param data
	 * @return
	 * @throws Exception
	 */
	public static byte[] decompress(byte[] data) throws Exception {
		ByteArrayInputStream bais = new ByteArrayInputStream(data);
		ByteArrayOutputStream baos = new ByteArrayOutputStream();
		// 解压缩
		decompress(bais, baos);
		data = baos.toByteArray();
		baos.flush();
		baos.close();
		bais.close();
		return data;
	}
	/**
	 * 文件解压缩
	 * 
	 * @param file
	 * @throws Exception
	 */
	public static void decompress(File file) throws Exception {
		decompress(file, true);
	}
	/**
	 * 文件解压缩
	 * 
	 * @param file
	 * @param delete
	 *            是否删除原始文件
	 * @throws Exception
	 */
	public static void decompress(File file, boolean delete) throws Exception {
		FileInputStream fis = new FileInputStream(file);
		FileOutputStream fos = new FileOutputStream(file.getPath().replace(EXT,
				""));
		decompress(fis, fos);
		fis.close();
		fos.flush();
		fos.close();
		if (delete) {
			file.delete();
		}
	}
	/**
	 * 数据解压缩
	 * 
	 * @param is
	 * @param os
	 * @throws Exception
	 */
	public static void decompress(InputStream is, OutputStream os)
			throws Exception {
		BZip2CompressorInputStream gis = new BZip2CompressorInputStream(is);
		int count;
		byte data[] = new byte[BUFFER];
		while ((count = gis.read(data, 0, BUFFER)) != -1) {
			os.write(data, 0, count);
		}
		gis.close();
	}
	/**
	 * 文件解压缩
	 * 
	 * @param path
	 * @throws Exception
	 */
	public static void decompress(String path) throws Exception {
		decompress(path, true);
	}
	/**
	 * 文件解压缩
	 * 
	 * @param path
	 * @param delete
	 *            是否删除原始文件
	 * @throws Exception
	 */
	public static void decompress(String path, boolean delete) throws Exception {
		File file = new File(path);
		decompress(file, delete);
	}
}


对应再来个测试用例,测试用例如下所示:

/**
 * 2010-4-13
 */
package org.zlex.commons.compress.compress;
import static org.junit.Assert.assertEquals;
import java.io.DataInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import org.junit.Test;
/**
 * BZip2
 * 
 * @author <a href="mailto:zlex.dongliang@gmail.com">梁栋</a>
 * @since 1.0
 */
public class BZip2UtilsTest {
	private String inputStr = "zlex@zlex.org,snowolf@zlex.org,zlex.snowolf@zlex.org,zlex@zlex.org,
snowolf@zlex.org,zlex.snowolf@zlex.org,zlex@zlex.org,snowolf@zlex.org,zlex.snowolf@zlex.org,
zlex@zlex.org,snowolf@zlex.org,zlex.snowolf@zlex.org,zlex@zlex.org,snowolf@zlex.org,
zlex.snowolf@zlex.org,zlex@zlex.org,snowolf@zlex.org,zlex.snowolf@zlex.org,zlex@zlex.org,
snowolf@zlex.org,zlex.snowolf@zlex.org,zlex@zlex.org,snowolf@zlex.org,zlex.snowolf@zlex.
org,zlex@zlex.org,snowolf@zlex.org,zlex.snowolf@zlex.org,zlex@zlex.org,
snowolf@zlex.org,zlex.snowolf@zlex.org";
@Testpublic final void testDataCompress() throws Exception {byte[] input = inputStr.getBytes();System.err.println("原文:\t" + inputStr);System.err.println("长度:\t" + input.length);byte[] data = BZip2Utils.compress(input);System.err.println("压缩后:\t");System.err.println("长度:\t" + data.length);byte[] output = BZip2Utils.decompress(data);String outputStr = new String(output);System.err.println("解压缩后:\t" + outputStr);System.err.println("长度:\t" + output.length);assertEquals(inputStr, outputStr);}@Testpublic final void testFileCompress() throws Exception {FileOutputStream fos = new FileOutputStream("d:/f.txt");fos.write(inputStr.getBytes());fos.flush();fos.close();BZip2Utils.compress("d:/f.txt");BZip2Utils.decompress("d:/f.txt.bz2");File file = new File("d:/f.txt");FileInputStream fis = new FileInputStream(file);DataInputStream dis = new DataInputStream(fis);byte[] data = new byte[(int) file.length()];dis.readFully(data);fis.close();String outputStr = new String(data);assertEquals(inputStr, outputStr);}}


虽然,两种算法在代码实现上几乎没有什么差别,但在压缩上想要看到效果,还真让我费了点事!
控制台输出(略)


GZIP本身不需要太长的内容,经过压缩就能体现出压缩效果,而BZip2则需要压缩很长的内容时,才能体现其压缩效果,这说明BZip2更适合大数据压缩?!

 

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值