读取SequenceFile中自定义Writable类型值

时间：2016-01-21 12:01:23 阅读：200 评论：0 收藏：0 [点我收藏+]

标签：

1）hadoop允许程序员创建自定义的数据类型，如果是key则必须要继承WritableComparable，因为key要参与排序，而value只需要继承Writable就可以了。以下定义一个DoubleArrayWritable，继承自ArrayWritable。代码如下：

 1 package matrix;
 2 import org.apache.hadoop.io.*;
 3 public class DoubleArrayWritable extends ArrayWritable {   
 4       public DoubleArrayWritable(){
 5           super(DoubleWritable.class);
 6       }
 7       public  double[] convert2double(DoubleWritable[] w){
 8           double[] value=new double[w.length];
 9           for (int i = 0; i < value.length; i++) {
10               value[i]=Double.valueOf(w[i].get());
11           }
12           return value;
13       }
14       
15 
16     }
17     
18

2)以下就是读取tansB.txt文件，将其值转化为DoubleArrayWritable存储到SequenceFile中。

 1 package convert;
 2 
 3 /**
 4  * Created with IntelliJ IDEA.
 5  * User: hadoop
 6  * Date: 16-1-19
 7  * Time: 下午3:09
 8  * To change this template use File | Settings | File Templates.
 9  */
10 import java.io.IOException;
11 import java.net.URI;
12 
13 import org.apache.hadoop.conf.Configuration;
14 import org.apache.hadoop.fs.FileSystem;
15 import org.apache.hadoop.fs.Path;
16 import org.apache.hadoop.io.DoubleWritable;
17 import org.apache.hadoop.io.IOUtils;
18 import org.apache.hadoop.io.IntWritable;
19 import org.apache.hadoop.io.LongWritable;
20 import org.apache.hadoop.io.SequenceFile;
21 import org.apache.hadoop.io.Text;
22 import org.apache.commons.io.FileUtils;
23 import org.apache.commons.io.LineIterator;
24 
25 
26 
27 //import Jama.Matrix.*;
28 //import  java.io.IOException;
29 import java.io.File;
30 
31 //import javax.sound.midi.SysexMessage;
32 public class SequenceFileWriteDemo {
33     public static void main(String[] args) throws IOException {
34         String uri ="/home/hadoop/srcData/bDoubleArraySeq";
35         Configuration conf = new Configuration();
36         FileSystem fs = FileSystem.get(URI.create(uri), conf);
37         Path path = new Path(uri);
38         IntWritable key = new IntWritable();
39         DoubleArrayWritable value = new DoubleArrayWritable();
40         SequenceFile.Writer writer = null;
41         try {
42             writer = SequenceFile.createWriter(fs, conf, path, key.getClass(),
43                     value.getClass());
44 
45 
46             final LineIterator it2 = FileUtils.lineIterator(new File("/home/hadoop/srcData/transB.txt"), "UTF-8");
47             try {
48                 int i=0;
49                 String[] strings;
50                 DoubleWritable[] ArrayDoubleWritables;
51                 while (it2.hasNext()) {
52                     ++i;
53                     final String line = it2.nextLine();
54                     key.set(i);
55                     strings=line.split("\t");
56                     ArrayDoubleWritables=new DoubleWritable[strings.length];
57                     for (int j = 0; j < ArrayDoubleWritables.length; j++) {
58                         ArrayDoubleWritables[j] =new DoubleWritable(Double.valueOf(strings[j]));
59                         
60                     }
61                     
62                     value.set(ArrayDoubleWritables);
63                     writer.append(key,value);
64                     //System.out.println("ffd");
65 
66                 }
67             } finally {
68                 it2.close();
69             }
70 
71         }finally {
72             IOUtils.closeStream(writer);
73         }
74         System.out.println("ok");
75 
76     }
77 
78 }