相关阅读：

时隔好久，今天又重新试了下，居然不行了？，比如，我要编写一个把文本转为序列文件的java程序如下：

package mahout.fansy.canopy.transformdata;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;

public class Text2VectorWritable extends AbstractJob{

@Override
public int run(String[] arg0) throws Exception {
addInputOption();
addOutputOption();
if (parseArguments(arg0) == null) {
return -1;
}
Path input=getInputPath();
Path output=getOutputPath();
Configuration conf=getConf();
Job job=new Job(conf,"text2vectorWritable with input:"+input.getName());
// job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setMapperClass(Text2VectorWritableMapper.class);
job.setMapOutputKeyClass(Writable.class);
job.setMapOutputValueClass(VectorWritable.class);
job.setNumReduceTasks(0);
job.setJarByClass(Text2VectorWritable.class);

FileInputFormat.addInputPath(job, input);
SequenceFileOutputFormat.setOutputPath(job, output);
if (!job.waitForCompletion(true)) {
throw new InterruptedException("Canopy Job failed processing " + input);
}
return 0;
}

public static class Text2VectorWritableMapper extends Mapper{
public void map(Writable key,Text value,Context context)throws IOException,InterruptedException{
String[] str=value.toString().split(",");
Vector vector=new RandomAccessSparseVector(str.length);
for(int i=0;i vector.set(i, Double.parseDouble(str[i]));
}
VectorWritable va=new VectorWritable(vector);
context.write(key, va);
}
}

}