1.原始日志数据:
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200
1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 视频网站 15 12 1527 2106 200
1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 信息安全 20 20 3156 2936 200
1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200
1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站点统计 24 9 6960 690 200
1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200
1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站点统计 3 3 1938 180 200
1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200
1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 综合门户 15 12 1938 2910 200
1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200
1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 综合门户 57 102 7335 110349 200
1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200
1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200
1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 2 2 120 120 200
1363157985066 13726238888 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157993055 13560436666 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
日志格式:
2.DataBean
public class DataBean implements Writable{
private String telNO;
private long upPlayLoad;
private long downPlayLoad;
private long totalPayLoad;
public DataBean(){
}
public DataBean(String telNO, long upPlayLoad, long downPlayLoad) {
this.telNO = telNO;
this.upPlayLoad = upPlayLoad;
this.downPlayLoad = downPlayLoad;
this.totalPayLoad=this.upPlayLoad+this.downPlayLoad;
}
//一定要注意下面两个方法的顺序、类型匹配
//反序列化
public void readFields(DataInput arg0) throws IOException {
this.telNO = arg0.readUTF();
this.upPlayLoad = arg0.readLong();
this.downPlayLoad = arg0.readLong();
this.totalPayLoad = arg0.readLong();
}
// 序列化
public void write(DataOutput arg0) throws IOException {
arg0.writeUTF(telNO);
arg0.writeLong(upPlayLoad);
arg0.writeLong(downPlayLoad);
arg0.writeLong(totalPayLoad);
}
public String getTelNO() {
return telNO;
}
public void setTelNO(String telNO) {
this.telNO = telNO;
}
public long getUpPlayLoad() {
return upPlayLoad;
}
public void setUpPlayLoad(long upPlayLoad) {
this.upPlayLoad = upPlayLoad;
}
public long getDownPlayLoad() {
return downPlayLoad;
}
public void setDownPlayLoad(long downPlayLoad) {
this.downPlayLoad = downPlayLoad;
}
public long getTotalPayLoad() {
return totalPayLoad;
}
public void setTotalPayLoad(long totalPayLoad) {
this.totalPayLoad = totalPayLoad;
}
//mapreduce自动调用
@Override
public String toString() {
return this.upPlayLoad+"\t"+this.downPlayLoad+"\t"+this.totalPayLoad;
}
3.DataCount处理实现
public class DataCount {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf=new Configuration();
// 对conf配置,否则会读取全局的mapred-site.xml的配置
Job job=Job.getInstance(conf);
job.setJarByClass(DataCount.class);
job.setMapperClass(DCMapper.class);
//当k2,v2和k3,v3类型一一对应时下面可以省略
//job.setOutputKeyClass(DataBean.class);
//job.setOutputValueClass(DataBean.class);
//job.setMapOutputKeyClass(Text.class);
//job.setMapOutputValueClass(DataBean.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
job.setReducerClass(DCReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(DataBean.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 设置分区实现类
job.setPartitionerClass(ProviderPartitioner.class);
//设置ruducer数量,即分区数,默认为1
job.setNumReduceTasks(Integer.parseInt(args[2]));
job.waitForCompletion(true);
}
//在map执行完成、reducer执行前执行<k2, v2>
public static class ProviderPartitioner extends Partitioner<Text, DataBean>{
private static Map<String, Integer> map= new HashMap<String, Integer>();
//运行命令时输入的分区参数只可以大于等于4
static{
map.put("150", 2);
map.put("159", 2);
map.put("134", 1);
map.put("135", 1);
map.put("136", 1);
map.put("137", 1);
map.put("138", 1);
map.put("139", 1);
map.put("183", 3);
map.put("182", 3);
}
//参数分别是k2,V2,分区数
//返回值:分区号
@Override
public int getPartition(Text key, DataBean value, int numPartitions) {
String account=key.toString();
String sunAcc=account.substring(0, 3);
Integer p=map.get(sunAcc);
if (p==null) {
p=0;
}
return p;
}
}
public static class DCMapper extends Mapper<LongWritable, Text, Text, DataBean> {
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, DataBean>.Context context)
throws IOException, InterruptedException {
//取数据、按制表副分割
String line=value.toString();
String[]fileds=line.split("\t");
String telNO=fileds[1];
Long up=Long.parseLong(fileds[8]);
Long down=Long.parseLong(fileds[9]);
//输出
context.write(new Text(telNO), new DataBean(telNO, up, down));
}
}
public static class DCReducer extends Reducer<Text, DataBean, Text, DataBean>{
@Override
protected void reduce(Text key, Iterable<DataBean> v2s,
Reducer<Text, DataBean, Text, DataBean>.Context context)
throws IOException, InterruptedException {
long upSum=0;
long downSum=0;
long totalSum=0;
for (DataBean dataBean : v2s) {
upSum+=dataBean.getUpPlayLoad();
downSum+=dataBean.getDownPlayLoad();
}
context.write(key, new DataBean(key.toString(), upSum, downSum));
}
}
}
4.执行结果
命令:
(记住:第三个参数只可以大于等于4)
hadoop jar rsort.jar cn.zx.hadoop.mr.dc.DataCount /test/HTTP_20130313143750.dat /test/tinfo **4**
结果:
hdfs dfs -cat /test/tinfo/part-r-00002