MapReduce編程實戰(zhàn)2——倒排索引（jar包）

任務(wù)要求：

//輸入文件格式

18661629496 110

13107702446 110

1234567 120

2345678 120

987654 110

2897839274 18661629496

//輸出文件格式格式

11018661629496|13107702446|987654|18661629496|13107702446|987654|

1201234567|2345678|1234567|2345678|

186616294962897839274|2897839274|

mapreduce程序編寫：

import java.io.IOException;
import java.util.StringTokenizer;

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

public class Test2 {
	enum Counter
	{
		LINESKIP,//記錄出錯的行
	}
    public static class Map extends Mapper<LongWritable, Text, Text, Text>{


        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
        	 String line = value.toString();//讀取源數(shù)據(jù)
             try
             {
            	 //數(shù)據(jù)處理
            	 String [] lineSplit = line.split(" ");//18661629496,110
            	 String anum = lineSplit[0];
            	 String bnum = lineSplit[1];  
            	 //輸出格式：110,18661629496          	 
            	 context.write(new Text(bnum), new Text(anum));
            	 
             }
             catch(ArrayIndexOutOfBoundsException e)
             {
            	 context.getCounter(Counter.LINESKIP).increment(1);//出錯時計數(shù)器+1
            	 return;
             }

        }
    }

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

        public void reduce(Text key, Iterable<Text> values, Context context)
                throws IOException, InterruptedException {
            String valueString;
            String out="";
            for(Text value:values)
            {
            	valueString=value.toString();
            	out+=valueString+"|";
            }
            context.write(key, new Text(out));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        if (args.length != 2) {
            System.err.println("請配置輸入輸出路徑 ");
            System.exit(2);
        }
        //各種配置
        Job job = new Job(conf, "telephone ");//作業(yè)名稱配置
        //類配置
        job.setJarByClass(Test2.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        //map輸出格式配置
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        //作業(yè)輸出格式配置
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //增加輸入輸出路徑
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        //任務(wù)完成時退出
        System.exit(job.waitForCompletion(true) ? 0 : 1);

    }

}

將mapreduce程序打包為jar文件：

1.右鍵項目名稱->Export->java->jar file

2.配置jar文件存儲位置

3.選擇main calss

4.運行jar文件

[liuqingjie@master hadoop-0.20.2]$ bin/hadoop jar /home/liuqingjie/test2.jar /user/liuqingjie/in /user/liuqingjie/out

15/05/14 01:46:47 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.

15/05/14 01:46:47 INFO input.FileInputFormat: Total input paths to process : 2

15/05/14 01:46:48 INFO mapred.JobClient: Running job: job_201505132004_0005

15/05/14 01:46:49 INFO mapred.JobClient:  map 0% reduce 0%

15/05/14 01:46:57 INFO mapred.JobClient:  map 100% reduce 0%

15/05/14 01:47:09 INFO mapred.JobClient:  map 100% reduce 100%

……………………………………………………………………………………

查看結(jié)果

[liuqingjie@master hadoop-0.20.2]$ bin/hadoop dfs -cat ./out/*

cat: Source must be a file.

110 18661629496|13107702446|987654|18661629496|13107702446|987654|

120 1234567|2345678|1234567|2345678|

18661629496 2897839274|2897839274|