Hadoop的多文件输出以及自定义文件名
最近写程序的时候要用到多文件输出。但是在网上找了很多资料，要么是老版本的方法，要么就是新版本的方法。网上很多说0.20.203.0版本的Hadoop中有MultipleOutputs类——确实有，只不过是老版的。坑啊。而他们用的MultipleOutputs是在org.apache.hadoop.mapreduce.lib.output里面的，但我笔者的Hadoop中偏偏就没有这个类。取去了一个最新版的Hadoop，才发现了这个类。最后，在网上超找了半天，才发现，从0.21开始，org.apache.hadoop.mapreduce.lib.output中才有MultipleOutputs类。所以，只有自己重写了- -。
又找了半天，终于找到自己想要的了。由于笔者还没有正式学习Java，所以，还有很多地方不理解，但是大致能看懂，如有即使不周到或者没有解释的地方，请各位见谅。同时，笔者修改了一些地方以适应自己的程序。
首先是输出格式的类，也就是job.setOutputFormatClass（……）参数列表中的类：
public class MoreFileOutputFormat extends Multiple<Text,Text>
{
@Override
protected String generateFileNameForKeyValue(Text key, Text value,Configuration conf)
{
return "Your name";
｝
}
这里，继承Multiple类后必须重写generateFileNameForKeyValue（）方法，这个方法返回的字符串作为输出文件的文件名。内容有各位自己根据需要编写。同时，key和value的值也根据自己的需要更换。
接下来是Multiple模板类的代码：
import java.io.DataOutputStream;
import java.io.IOException;
import java.util.HashMap;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapreduce.OutputCommitter;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;
public abstract class Multiple<K extends WritableComparable<?>, V extends Writable>
extends FileOutputFormat<K, V>
{
// 接口类，需要在调用程序中实现generateFileNameForKeyValue来获取文件名
private MultiRecordWriter writer = null;
public RecordWriter<K, V> getRecordWriter(TaskAttemptContext job)
throws IOException, InterruptedException
{
if (writer == null)
{
writer = new MultiRecordWriter(job, getTaskOutputPath(job));
}
return writer;
}
/**
* get task output path
*
* @param conf
* @return
* @throws IOException
*/
private Path getTaskOutputPath(TaskAttemptContext conf) throws IOException
{
Path workPath = null;
OutputCommitter committer = super.getOutputCommitter(conf);
if (committer instanceof FileOutputCommitter)
{
workPath = ((FileOutputCommitter) committer).getWorkPath();
}
else
{
Path outputPath = super.getOutputPath(conf);
if (outputPath == null)
{
throw new IOException("Undefined job output-path");
}
workPath = outputPath;
}
return workPath;
}
//继承后重写以获得文件名
protected abstract String generateFileNameForKeyValue(K key, V value,Configuration conf);
//实现记录写入器RecordWriter类 （内部类）
public class MultiRecordWriter extends RecordWriter<K, V>
{
/** RecordWriter的缓存 */
private HashMap<String, RecordWriter<K, V>> recordWriters = null;
private TaskAttemptContext job = null;
/** 输出目录 */
private Path workPath = null;
public MultiRecordWriter(TaskAttemptContext job, Path workPath)
{
super();
this.job = job;
this.workPath = workPath;
recordWriters = new HashMap<String, RecordWriter<K, V>>();
}
@Override
public void close(TaskAttemptContext context) throws IOException,
InterruptedException
{
Iterator<RecordWriter<K, V>> values = this.recordWriters.values().iterator();
while (values.hasNext())
{
values.next().close(context);
}
this.recordWriters.clear();
}
@Override
public void write(K key, V value) throws IOException,
InterruptedException
{
// 得到输出文件名
String baseName = generateFileNameForKeyValue(key, value,job.getConfiguration());
// 如果recordWriters里没有文件名，那么就建立。否则就直接写值。
RecordWriter<K, V> rw = this.recordWriters.get(baseName);
if (rw == null)
{
rw = getBaseRecordWriter(job, baseName);
this.recordWriters.put(baseName, rw);
}
rw.write(key, value);
}
// ${mapred.out.dir}/_temporary/_${taskid}/${nameWithExtension}
private RecordWriter<K, V> getBaseRecordWriter(TaskAttemptContext job,
String baseName) throws IOException, InterruptedException
{
Configuration conf = job.getConfiguration();
// 查看是否使用解码器
boolean isCompressed = getCompressOutput(job);
RecordWriter<K, V> recordWriter = null;
if (isCompressed)
{
Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(
job, GzipCodec.class);
CompressionCodec codec = ReflectionUtils.newInstance(codecClass, conf);
Path file = new Path(workPath, baseName + codec.getDefaultExtension());
FSDataOutputStream fileOut = file.getFileSystem(conf).create(file, false);
// 这里我使用的自定义的OutputFormat
recordWriter = new MyRecordWriter<K, V>(new DataOutputStream(
codec.createOutputStream(fileOut)));
}
else
{
Path file;
System.out.println("workPath = " + workPath + ", basename = " + baseName);
file = new Path(workPath, baseName);
FSDataOutputStream fileOut = file.getFileSystem(conf).create(file, false);
// 这里我使用的自定义的OutputFormat
recordWriter = new MyRecordWriter<K, V>(fileOut);
}
return recordWriter;
}
}
}
现在来实现Multiple的内部类MultiRecordWriter中的MyRecordWriter类以实现自己想要的输出方式：
public class MyRecordWriter<K, V> extends RecordWriter<K,V>
{
private static final String utf8 = "UTF-8";//定义字符编码格式
protected DataOutputStream out;
public MyRecordWriter(DataOutputStream out)
{
this.out = out;
}
private void writeObject(Object o) throws IOException
{
if (o instanceof Text)
{
Text to = (Text) o;
out.write(to.getBytes(), 0, to.getLength());
}
else
{
//输出成字节流。如果不是文本类的，请更改此处
out.write(o.toString().getBytes(utf8));
}
}
/**
* 将mapreduce的key,value以自定义格式写入到输出流中
*/
public synchronized void write(K key, V value) throws IOException
{
writeObject(value);
}
public synchronized void close(TaskAttemptContext context) throws IOException
{
out.close();
}
}
这个类中还有其它集中方法，不过笔者不需要那些方法，所以把它们都删除了，但最初的文件也删除了- -，所以现在找不到了。请大家见谅。
现在，只需在main（）或者run（）函数中将job的输出格式设置成MoreFileOutputFormat类就行了，如下：
job.setOutputFormatClass(MoreFileOutputFormatClass);
详情请参考一下网址：
http://blog.csdn.net/inkfish/article/details/5156651