MapReduce程式設計之實作多表關聯

多表關聯和單表關聯類似，它也是通過對原始資料進行一定的處理，從其中挖掘出關心的資訊。如下

輸入的是兩個檔案，一個代表工廠表，包含工廠名列和位址編号列；另一個代表位址表，包含位址名列和位址編号列。

要求從輸入資料中找出工廠名和位址名的對應關系，輸出工廠名-位址名表

樣本如下：

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>
           

結果：

<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>
           

代碼如下：

<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中先區分輸入行屬于左表還是右表，然後對兩列值進行分割，
     * 儲存連接配接列在key值，剩餘列和左右表标志在value中，最後輸出
     */

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

        // 實作map函數</span>
           

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

            // 輸入檔案首行，不處理

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

            // 輸入的一行預處理文本

            StringTokenizer itr = new StringTokenizer(line);
            String mapkey = new String();
            String mapvalue = new String();
            int i = 0;
            while (itr.hasMoreTokens()) {

                // 先讀取一個單詞

                String token = itr.nextToken();
                // 判斷該位址ID就把存到"values[0]"
                if (token.charAt(0) >= '0' && token.charAt(0) <= '9') {
                    mapkey = token;
                    if (i > 0) {
                        relationtype = "1";
                    } else {
                        relationtype = "2";
                    }
                    continue;

                }

 

                // 存工廠名

                mapvalue += token + " ";

                i++;

            }

            // 輸出左右表

            context.write(new Text(mapkey), new Text(relationtype + "+"+ mapvalue));

        }

    }

 
    /*
     * reduce解析map輸出，将value中資料按照左右表分别儲存，
　　 * 然後求出笛卡爾積，并輸出。
     */

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

 

        // 實作reduce函數

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

                throws IOException, InterruptedException {

 

            // 輸出表頭

            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;

                }

 

                // 取得左右表辨別

                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++;

                }

            }

 

            // 求笛卡爾積

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

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

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

                        // 輸出結果

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

                                new Text(address[n]));

                    }

                }

            }

 

        }

    }

 

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

        Configuration conf = new Configuration();

        // 這句話很關鍵

  //      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);

        // 設定Map和Reduce處理類

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

        // 設定輸出類型

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

 

        // 設定輸入和輸出目錄

        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>
           

删除已經存在的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>
           

運作

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

檢視結果

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