hadoop文本转换为序列文件

在以前使用hadoop的时候因为mahout里面很多都要求输入文件时序列文件，所以涉及到把文本文件转换为序列文件或者序列文件转为文本文件（因为当时要分析mahout的源码，所以就要看到它的输入文件是什么，文本比较好看其内容）。一般这个有两种做法，其一：按照《hadoop权威指南》上面的方面直接读出序列文件然后写入一个文本；其二，编写一个job任务，直接设置输出文件的格式，这样也可以把序列文件读成文本（个人一般采用这样方法）。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<Writable,Text,Writable,VectorWritable>{
		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<str.length;i++){
				vector.set(i, Double.parseDouble(str[i]));
			}
			VectorWritable va=new VectorWritable(vector);
			context.write(key, va);
		}
	}
	
}

这样在运行的时候老是提示说 我的Map的value的类型不是Text，不管我设置为什么类型都会是这样的情况。后来我就想会不会是map的输出时Text的格式？，然后我就把上面的程序加入了Reducer，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.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
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 Text2VectorWritableCopy 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,"text2vectorWritableCopy with input:"+input.getName());
	 //   job.setInputFormatClass(SequenceFileInputFormat.class);
	    job.setOutputFormatClass(SequenceFileOutputFormat.class);
	    job.setMapperClass(Text2VectorWritableMapper.class);
	    job.setMapOutputKeyClass(LongWritable.class);
	    job.setMapOutputValueClass(VectorWritable.class);
	    job.setReducerClass(Text2VectorWritableReducer.class);
	    job.setOutputKeyClass(LongWritable.class);
	    job.setOutputValueClass(VectorWritable.class);
	    job.setJarByClass(Text2VectorWritableCopy.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<LongWritable,Text,LongWritable,VectorWritable>{
		public void map(LongWritable key,Text value,Context context)throws IOException,InterruptedException{
			String[] str=value.toString().split(",");
			Vector vector=new RandomAccessSparseVector(str.length);
			for(int i=0;i<str.length;i++){
				vector.set(i, Double.parseDouble(str[i]));
			}
			VectorWritable va=new VectorWritable(vector);
			context.write(key, va);
		}
	}
	
	public static class Text2VectorWritableReducer extends Reducer<LongWritable,VectorWritable,LongWritable,VectorWritable>{
		public void reduce(LongWritable key,Iterable<VectorWritable> values,Context context)throws IOException,InterruptedException{
			for(VectorWritable v:values){
				context.write(key, v);
			}
		}
	}
	
}

然后在运行，就可以了。

不过关于map的输出是否一定是text格式的，还有待论证。

分享，快乐，成长

转载请注明出处：http://blog.csdn.net/fansy1990