Hadoop自定义类型处理手机上网日志

job提交源码分析

在eclipse中的写的代码如何提交作业到JobTracker中的哪？
(1)在eclipse中调用的job.waitForCompletion(true)实际上执行如下方法
　　connect();
　　info = jobClient.submitJobInternal(conf);
(2)在connect()方法中，实际上创建了一个JobClient对象。
　　在调用该对象的构造方法时，获得了JobTracker的客户端代理对象JobSubmissionProtocol。
　　JobSubmissionProtocol的实现类是JobTracker。
(3)在jobClient.submitJobInternal(conf)方法中，调用了
　　JobSubmissionProtocol.submitJob(...),
　　即执行的是JobTracker.submitJob(...)。

Hadoop数据类型

1.Hadoop的数据类型要求必须实现Writable接口。
2.java基本类型与Hadoop常见基本类型的对照
　　　　Long 　　　　LongWritable
　　　　Integer 　　  IntWritable
　　　　Boolean 　　 BooleanWritable
　　　　String 　　　 Text

java类型如何转化为hadoop基本类型？
　　　　调用hadoop类型的构造方法，或者调用set()方法。
　　　　　　new LongWritable(123L);

hadoop基本类型如何转化为java类型？
　　　　对于Text，需要调用toString()方法，其他类型调用get()方法。

使用Hadoop自定义类型处理手机上网日志

1、首先，将手机上网日志文件HTTP_20130313143750.dat通过WinSCP工具复制到/usr/local目录下

2、将日志文件上传到hdfs://chaoren:9000/wlan文件夹下

日志文件：

日志文件中各字段含义：

3、编写Java代码将日志文件中想要的数据统计出来。

 package mapreduce;

 import java.io.DataInput;
 import java.io.DataOutput;
 import java.io.IOException;

 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
 import org.apache.hadoop.io.LongWritable;
 import org.apache.hadoop.io.Text;
 import org.apache.hadoop.io.Writable;
 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.input.TextInputFormat;
 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
 import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

 public class KpiApp {
     static final String INPUT_PATH = "hdfs://chaoren:9000/wlan";//wlan是个文件夹，日志文件放在/wlan目录下
     static final String OUT_PATH = "hdfs://chaoren:9000/out";

     public static void main(String[] args) throws Exception {
         final Job job = new Job(new Configuration(),
                 KpiApp.class.getSimpleName());
         // 1.1 指定输入文件路径
         FileInputFormat.setInputPaths(job, INPUT_PATH);
         // 指定哪个类用来格式化输入文件
         job.setInputFormatClass(TextInputFormat.class);

         // 1.2指定自定义的Mapper类
         job.setMapperClass(MyMapper.class);
         // 指定输出<k2,v2>的类型
         job.setMapOutputKeyClass(Text.class);
         job.setMapOutputValueClass(KpiWritable.class);

         // 1.3 指定分区类
         job.setPartitionerClass(HashPartitioner.class);
         job.setNumReduceTasks(1);

         // 1.4 TODO 排序、分区

         // 1.5 TODO （可选）归约

         // 2.2 指定自定义的reduce类
         job.setReducerClass(MyReducer.class);
         // 指定输出<k3,v3>的类型
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(KpiWritable.class);

         // 2.3 指定输出到哪里
         FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
         // 设定输出文件的格式化类
         job.setOutputFormatClass(TextOutputFormat.class);

         // 把代码提交给JobTracker执行
         job.waitForCompletion(true);
     }

     static class MyMapper extends Mapper<LongWritable, Text, Text, KpiWritable> {
         protected void map(
                 LongWritable key,
                 Text value,
                 org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, KpiWritable>.Context context)
                 throws IOException, InterruptedException {
             final String[] splited = value.toString().split("\t");
             final String msisdn = splited[1];
             final Text k2 = new Text(msisdn);
             final KpiWritable v2 = new KpiWritable(splited[6], splited[7],
                     splited[8], splited[9]);
             context.write(k2, v2);
         };
     }

     static class MyReducer extends
             Reducer<Text, KpiWritable, Text, KpiWritable> {
         /**
          * @param k2
          *            表示整个文件中不同的手机号码
          * @param v2s
          *            表示该手机号在不同时段的流量的集合
          */
         protected void reduce(
                 Text k2,
                 java.lang.Iterable<KpiWritable> v2s,
                 org.apache.hadoop.mapreduce.Reducer<Text, KpiWritable, Text, KpiWritable>.Context context)
                 throws IOException, InterruptedException {
             long upPackNum = 0L;
             long downPackNum = 0L;
             long upPayLoad = 0L;
             long downPayLoad = 0L;

             for (KpiWritable kpiWritable : v2s) {
                 upPackNum += kpiWritable.upPackNum;
                 downPackNum += kpiWritable.downPackNum;
                 upPayLoad += kpiWritable.upPayLoad;
                 downPayLoad += kpiWritable.downPayLoad;
             }

             final KpiWritable v3 = new KpiWritable(upPackNum + "", downPackNum
                     + "", upPayLoad + "", downPayLoad + "");
             context.write(k2, v3);
         };
     }
 }

 class KpiWritable implements Writable {
     long upPackNum;
     long downPackNum;
     long upPayLoad;
     long downPayLoad;

     public KpiWritable() {
     }

     public KpiWritable(String upPackNum, String downPackNum, String upPayLoad,
             String downPayLoad) {
         this.upPackNum = Long.parseLong(upPackNum);
         this.downPackNum = Long.parseLong(downPackNum);
         this.upPayLoad = Long.parseLong(upPayLoad);
         this.downPayLoad = Long.parseLong(downPayLoad);
     }

     public void readFields(DataInput in) throws IOException {
         this.upPackNum = in.readLong();
         this.downPackNum = in.readLong();
         this.upPayLoad = in.readLong();
         this.downPayLoad = in.readLong();
     }

     public void write(DataOutput out) throws IOException {
         out.writeLong(upPackNum);
         out.writeLong(downPackNum);
         out.writeLong(upPayLoad);
         out.writeLong(downPayLoad);
     }

     @Override
     public String toString() {
         return upPackNum + "\t" + downPackNum + "\t" + upPayLoad + "\t"
                 + downPayLoad;
     }
 }

4、运行结果