Hadoop自定义类型处理手机上网日志

  1 package mapreduce;
  2 
  3 import java.io.DataInput;
  4 import java.io.DataOutput;
  5 import java.io.IOException;
  6 
  7 import org.apache.hadoop.conf.Configuration;
  8 import org.apache.hadoop.fs.Path;
  9 import org.apache.hadoop.io.LongWritable;
 10 import org.apache.hadoop.io.Text;
 11 import org.apache.hadoop.io.Writable;
 12 import org.apache.hadoop.mapreduce.Job;
 13 import org.apache.hadoop.mapreduce.Mapper;
 14 import org.apache.hadoop.mapreduce.Reducer;
 15 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
 16 import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
 17 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 18 import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
 19 import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
 20 
 21 public class KpiApp {
 22     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
 23     static final String OUT_PATH = "hdfs://chaoren:9000/out";
 24 
 25     public static void main(String[] args) throws Exception {
 26         final Job job = new Job(new Configuration(),
 27                 KpiApp.class.getSimpleName());
 28         // 1.1 指定输入文件路径
 29         FileInputFormat.setInputPaths(job, INPUT_PATH);
 30         // 指定哪个类用来格式化输入文件
 31         job.setInputFormatClass(TextInputFormat.class);
 32 
 33         // 1.2指定自定义的Mapper类
 34         job.setMapperClass(MyMapper.class);
 35         // 指定输出的类型
 36         job.setMapOutputKeyClass(Text.class);
 37         job.setMapOutputValueClass(KpiWritable.class);
 38 
 39         // 1.3 指定分区类
 40         job.setPartitionerClass(HashPartitioner.class);
 41         job.setNumReduceTasks(1);
 42 
 43         // 1.4 TODO 排序、分区
 44 
 45         // 1.5 TODO （可选）归约
 46 
 47         // 2.2 指定自定义的reduce类
 48         job.setReducerClass(MyReducer.class);
 49         // 指定输出的类型
 50         job.setOutputKeyClass(Text.class);
 51         job.setOutputValueClass(KpiWritable.class);
 52 
 53         // 2.3 指定输出到哪里
 54         FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
 55         // 设定输出文件的格式化类
 56         job.setOutputFormatClass(TextOutputFormat.class);
 57 
 58         // 把代码提交给JobTracker执行
 59         job.waitForCompletion(true);
 60     }
 61 
 62     static class MyMapper extends Mapper {
 63         protected void map(
 64                 LongWritable key,
 65                 Text value,
 66                 org.apache.hadoop.mapreduce.Mapper.Context context)
 67                 throws IOException, InterruptedException {
 68             final String[] splited = value.toString().split("\t");
 69             final String msisdn = splited[1];
 70             final Text k2 = new Text(msisdn);
 71             final KpiWritable v2 = new KpiWritable(splited[6], splited[7],
 72                     splited[8], splited[9]);
 73             context.write(k2, v2);
 74         };
 75     }
 76 
 77     static class MyReducer extends
 78             Reducer {
 79         /**
 80          * @param k2
 81          *            表示整个文件中不同的手机号码
 82          * @param v2s
 83          *            表示该手机号在不同时段的流量的集合
 84          */
 85         protected void reduce(
 86                 Text k2,
 87                 java.lang.Iterable v2s,
 88                 org.apache.hadoop.mapreduce.Reducer.Context context)
 89                 throws IOException, InterruptedException {
 90             long upPackNum = 0L;
 91             long downPackNum = 0L;
 92             long upPayLoad = 0L;
 93             long downPayLoad = 0L;
 94 
 95             for (KpiWritable kpiWritable : v2s) {
 96                 upPackNum += kpiWritable.upPackNum;
 97                 downPackNum += kpiWritable.downPackNum;
 98                 upPayLoad += kpiWritable.upPayLoad;
 99                 downPayLoad += kpiWritable.downPayLoad;
100             }
101 
102             final KpiWritable v3 = new KpiWritable(upPackNum + "", downPackNum
103                     + "", upPayLoad + "", downPayLoad + "");
104             context.write(k2, v3);
105         };
106     }
107 }
108 
109 class KpiWritable implements Writable {
110     long upPackNum;
111     long downPackNum;
112     long upPayLoad;
113     long downPayLoad;
114 
115     public KpiWritable() {
116     }
117 
118     public KpiWritable(String upPackNum, String downPackNum, String upPayLoad,
119             String downPayLoad) {
120         this.upPackNum = Long.parseLong(upPackNum);
121         this.downPackNum = Long.parseLong(downPackNum);
122         this.upPayLoad = Long.parseLong(upPayLoad);
123         this.downPayLoad = Long.parseLong(downPayLoad);
124     }
125 
126     public void readFields(DataInput in) throws IOException {
127         this.upPackNum = in.readLong();
128         this.downPackNum = in.readLong();
129         this.upPayLoad = in.readLong();
130         this.downPayLoad = in.readLong();
131     }
132 
133     public void write(DataOutput out) throws IOException {
134         out.writeLong(upPackNum);
135         out.writeLong(downPackNum);
136         out.writeLong(upPayLoad);
137         out.writeLong(downPayLoad);
138     }
139 
140     @Override
141     public String toString() {
142         return upPackNum + "\t" + downPackNum + "\t" + upPayLoad + "\t"
143                 + downPayLoad;
144     }
145 }