脱离Hadoop的环境下使用Lzo 转自http://heipark.iteye.com/blog/1605721
动机:希望通过Java API将日志行压缩到lzo文件,然后上传到HDFS。因为kevinweil-hadoop-lzo提供了LzopOutpuStream,所以这一切很容易实现,需要注意的是该jar包依赖native code和lzo本身。本人试过Karmasphere的lzo-java项目,该项目用java重写了lzo压缩算法,但是该项目好久不更新,提问没人回,性能也只有原生lzo压缩性能一半,最难以忍受的是会有压缩后文件损坏的情况,果断放弃。
工具:lzo
地址:http://www.oberhumer.com/opensource/lzo/download/lzo-2.06.tar.gz
或者到 http://rpmfind.net 查找rpm包,下面两个是32bit redhat4和5的rpm包
ftp://rpmfind.net/linux/dag/redhat/el4/en/i386/dag/RPMS/lzo-2.06-1.el4.rf.i386.rpm
ftp://rpmfind.net/linux/dag/redhat/el5/en/i386/dag/RPMS/lzo-2.06-1.el5.rf.i386.rpm
工具:kevinweil-hadoop-lzo
地址:https://github.com/kevinweil/hadoop-lzo
1. 安装lzo和kevinweil-hadoop-lzo
详见:http://heipark.iteye.com/blog/1172759
2. 设置环境变量
export LD_LIBRARY_PATH=/xxx/build/native/Linux-i386-32/lib
3. 写java代码
- public class TestLzo {
- @Test
- public void test(String input, String output) throws IOException {
- BufferedReader textBr = new BufferedReader(new InputStreamReader(new FileInputStream(input)));
- int lzoBufferSize = 256 * 1024;
- LzoCompressor.CompressionStrategy strategy = LzoCompressor.CompressionStrategy.LZO1X_1;
- LzoCompressor lzoCompressor = new LzoCompressor(strategy, lzoBufferSize);
- LzopOutputStream lzopOut = new LzopOutputStream(new FileOutputStream(output), lzoCompressor, lzoBufferSize, strategy);
- String textLine;
- while ((textLine = textBr.readLine()) != null) {
- textLine += "\n";
- byte[] bytes = textLine.getBytes();
- lzopOut.write(bytes, 0, bytes.length);
- }
- textBr.close();
- lzopOut.close();
- }
- public static void main(String[] args) throws IOException {
- TestLzo lzo = new TestLzo();
- lzo.test(args[0], args[1]);
- }
- }
public class TestLzo {
@Test
public void test(String input, String output) throws IOException {
BufferedReader textBr = new BufferedReader(new InputStreamReader(new FileInputStream(input)));
int lzoBufferSize = 256 * 1024;
LzoCompressor.CompressionStrategy strategy = LzoCompressor.CompressionStrategy.LZO1X_1;
LzoCompressor lzoCompressor = new LzoCompressor(strategy, lzoBufferSize);
LzopOutputStream lzopOut = new LzopOutputStream(new FileOutputStream(output), lzoCompressor, lzoBufferSize, strategy);
String textLine;
while ((textLine = textBr.readLine()) != null) {
textLine += "\n";
byte[] bytes = textLine.getBytes();
lzopOut.write(bytes, 0, bytes.length);
}
textBr.close();
lzopOut.close();
}
public static void main(String[] args) throws IOException {
TestLzo lzo = new TestLzo();
lzo.test(args[0], args[1]);
}
}
4. 运行
/usr/java/latest/bin/java -cp .:hadoop-lzo-0.4.15.jar:hadoop-core-0.20.2-cdh3u4.jar:commons-logging-1.1.1.jar com/hadoop/compression/lzo/TestLzo abc.txt abc.txt.lzo
--heipark