MapReduce编程实例之倒排索引 1

任务描述：
有一批电话清单，记录了用户A拨打给用户B的记录
做一个倒排索引，记录拨打给用户B所有的用户A、

example data：

13614004876 110
18940084808 10086
13342445911 10001
13614004876 120
18940084808 1008611
13342445911 110
15847985621 10000

code：

<span style="font-size:14px;">package mrTest;import java.io.IOException;import java.util.Date;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;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 com.ibm.icu.text.SimpleDateFormat;public class daopaisuoyin {enum Counter{        LINESKIP,      //出错的行       }   public static class Map extends Mapper<Object, Text, Text, Text>{public void map(Object key,Text value,Context context){String line = value.toString();try{String[] lineSplit = line.split(" ");String newKey = lineSplit[0];String newValue = lineSplit[1];context.write(new Text(newKey), new Text(newValue));}catch(Exception e){ context.getCounter(Counter.LINESKIP).increment(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 result = "";for (Text value : values) {result += value.toString() + " # ";}context.write(key, new Text(result));}}public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {// TODO Auto-generated method stubJob job = new Job(new Configuration(), " 倒排索引 ");job.setJarByClass(daopaisuoyin.class);job.setNumReduceTasks(1);job.setOutputKeyClass(Text.class);job.setOutputValueClass(Text.class);job.setMapperClass(Map.class);job.setReducerClass(Reduce.class);FileInputFormat.addInputPath(job, new Path(args[0]));FileOutputFormat.setOutputPath(job, new Path(args[1]));//记录时间SimpleDateFormat  sdf = new SimpleDateFormat();    Date start = new Date();        //开始时间    int result = job.waitForCompletion(true)? 0 : 1;    //任务开始Date end = new Date();     //结束时间float time = (float)((end.getTime() - start.getTime()) / 60000.0);  //任务开始到结束经历的时间System.out.println("Job 开始的时间为：" + start);System.out.println("Job 结束的时间为：" + end);System.out.println("Job 经历的时间为：" + time + "分钟");System.out.println("Job 的名字：" + job.getJobName());System.out.println("Job 是否成功：" + job.isSuccessful() );System.out.println("Job 输入的行数：" + job.getCounters().findCounter("org.apache.hadoop.mapred.Task$Counter",  "MAP_INPUT_RECORDS").getValue());System.out.println("Job 输出的行数：" + job.getCounters().findCounter("org.apache.hadoop.mapred.Task$Counter",  "MAP_OUTPUT_RECORDS").getValue());System.exit(result); //判断是否结束}}</span>

结果显示：