多表关联和单表关联类似。它也是通过对原始数据进行一定的处理。从当中挖掘出关心的信息。例如以下

输入的是两个文件，一个代表工厂表，包括工厂名列和地址编号列；还有一个代表地址表，包括地址名列和地址编号列。

要求从输入数据中找出工厂名和地址名的相应关系。输出工厂名-地址名表

样本例如以下：

factory:

<span style="font-size:14px;">factoryname addressed
Beijing Red Star 1
Shenzhen Thunder 3
Guangzhou Honda 2
Beijing Rising 1
Guangzhou Development Bank 2
Tencent 3
Back of Beijing 1
</span>

address:

<span style="font-size:14px;">addressID addressname
1 Beijing
2 Guangzhou
3 Shenzhen
4 Xian
</span>

结果：

<span style="font-size:14px;">factoryname     addressname
Beijing Red Star        Beijing
Beijing Rising  Beijing
Bank of Beijing         Beijing
Guangzhou Honda         Guangzhou
Guangzhou Development Bank      Guangzhou
Shenzhen Thunder        Shenzhen
Tencent         Shenzhen
</span>

代码例如以下：

<span style="font-size:14px;">import java.io.IOException;
import java.util.*;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

 
public class MTjoin {

 
    public static int time = 0;

    /*
     * 在map中先区分输入行属于左表还是右表，然后对两列值进行切割，
     * 保存连接列在key值，剩余列和左右表标志在value中，最后输出
     */

    public static class Map extends Mapper<Object, Text, Text, Text> {

        // 实现map函数</span>

<span style="font-size:14px;">        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();// 每行文件
            String relationtype = new String();// 左右表标识 

            // 输入文件首行，不处理

            if (line.contains("factoryname") == true
                    || line.contains("addressed") == true) {
                return;
            }

            // 输入的一行预处理文本

            StringTokenizer itr = new StringTokenizer(line);
            String mapkey = new String();
            String mapvalue = http://www.mamicode.com/new String();>

     */

    public static class Reduce extends Reducer<Text, Text, Text, Text> {

 

        // 实现reduce函数

        public void reduce(Text key, Iterable<Text> values, Context context)

                throws IOException, InterruptedException {

 

            // 输出表头

            if (0 == time) {

                context.write(new Text("factoryname"), new Text("addressname"));
                time++;

            }

 

            int factorynum = 0;

            String[] factory = new String[10];
            int addressnum = 0;
            String[] address = new String[10];

            Iterator ite = values.iterator();

            while (ite.hasNext()) {

                String record = ite.next().toString();

                int len = record.length();

                int i = 2;

                if (0 == len) {

                    continue;

                }

 

                // 取得左右表标识

                char relationtype = record.charAt(0);

 

                // 左表

                if ('1' == relationtype) {

                    factory[factorynum] = record.substring(i);

                    factorynum++;

                }

 

                // 右表

                if ('2' == relationtype) {

                    address[addressnum] = record.substring(i);

                    addressnum++;

                }

            }

 

            // 求笛卡尔积

            if (0 != factorynum && 0 != addressnum) {

                for (int m = 0; m < factorynum; m++) {

                    for (int n = 0; n < addressnum; n++) {

                        // 输出结果

                        context.write(new Text(factory[m]),

                                new Text(address[n]));

                    }

                }

            }

 

        }

    }

 

    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();

        // 这句话非常关键

  //      conf.set("mapred.job.tracker", "192.168.1.2:9001");

 
	//可使用args
//      String[] ioArgs = new String[] { "MTjoin_in", "MTjoin_out" };

        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        if (otherArgs.length != 2) {

            System.err.println("Usage: Multiple Table Join <in> <out>");
            System.exit(2);

        }

        Job job = new Job(conf, "Multiple Table Join");
        job.setJarByClass(MTjoin.class);

        // 设置Map和Reduce处理类

        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        // 设置输出类型

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

 

        // 设置输入和输出文件夹

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);

    }

}

</span>

<span style="font-size:14px;">javac -classpath hadoop-core-1.1.2.jar:/opt/hadoop-1.1.2/lib/commons-cli-1.2.jar -d firstProject firstProject/MTJoin.java
</span>

<span style="font-size:14px;">jar -cvf MTJoin.jar -C firstProject/ .     </span>

<span style="font-size:14px;"></span>

删除已经存在的output

<span style="font-size:14px;">hadoop fs -rmr output
</span>

<span style="font-size:14px;">hadoop fs -mkdir input
</span>

<span style="font-size:14px;">hadoop fs -put factory input
</span>

<span style="font-size:14px;"> hadoop fs -put address input
</span>

执行

<span style="font-size:14px;">hadoop jar  MTJoin.jar MTJoin input output
</span>

查看结果

<span style="font-size:14px;"> hadoop fs -cat output/part-r-00000</span>