十一:Partitioner例子实现
例子内容将同一手机号断分在同一个Reduce中若没有指定手机号段分区的则在同一个没有设置号段的分区
import java.util.HashMap;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
import cn.com.bigdata.mr.flowcount.FlowBean;
/**
* 定义自己的从map到reduce之间的数据（分组）分发规则 按照手机号所属的省份来分发（分组）ProvincePartitioner
* 默认的分组组件是HashPartitioner
*
* @author
*
*/
public class ProvincePartitioner extends Partitioner<Text, FlowBean> {
static HashMap<String, Integer> provinceMap = new HashMap<String, Integer>();
static {
provinceMap.put("135", 0);
provinceMap.put("136", 1);
provinceMap.put("137", 2);
provinceMap.put("138", 3);
provinceMap.put("139", 4);
}
@Override
public int getPartition(Text key, FlowBean value, int numPartitions) {
Integer code = provinceMap.get(key.toString().substring(0, 3));
return code == null ? 5 : code;
}
}
import java.io.IOException;
import org.apache.commons.lang.StringUtils;
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.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 cn.com.bigdata.mr.flowcount.FlowBean;
public class FlowCountProvince {
static class FlowCountProvinceMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 将传进来的这一行数据转为string
String line = value.toString();
// 切分这一行，拿到各个字段
String[] fields = StringUtils.split(line, "\t");
// 拿到手机号
String phone = fields[1];
long upflow = Long.parseLong(fields[fields.length - 3]);
long dflow = Long.parseLong(fields[fields.length - 2]);
FlowBean bean = new FlowBean(upflow, dflow);
context.write(new Text(phone), bean);
}
}
static class FlowCountProvinceReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
@Override
protected void reduce(Text key, Iterable<FlowBean> beans, Context context) throws IOException, InterruptedException {
// 先定义两个计数器
long upAmount = 0;
long dAmount = 0;
// 遍历该用户所有的流量bean，进行累加求和
for (FlowBean bean : beans) {
upAmount += bean.getUpflow();
dAmount += bean.getDflow();
}
// 构造一个用于输出最终结果的flowbean
FlowBean countBean = new FlowBean(upAmount, dAmount);
// 输出结果
context.write(key, countBean);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(FlowCountProvince.class);
job.setMapperClass(FlowCountProvinceMapper.class);
job.setReducerClass(FlowCountProvinceReducer.class);
/**
* 如果map和reduce的输出kv类型一致，则不用专门设置map的输出kv类型
*/
/*
* job.setMapOutputKeyClass(Text.class);
* job.setMapOutputValueClass(FlowBean.class);
*/
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
/**
* hadoop中默认的输入输出组件就是TextInputformat和textoutputformat，所以，这两句代码也可以省略
*/
/*
* job.setInputFormatClass(TextInputFormat.class);
* job.setOutputFormatClass(TextOutputFormat.class);
*/
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
/**
* 告诉job，使用我们自定义的数据分组组件ProvincePartitioner
*/
job.setPartitionerClass(ProvincePartitioner.class);
/**
* 为了配合自定义分组策略中分组数，需要设置相应的reduce的并发数 如果“并发数”>分组数 ，就会出现空的结果文件
* 如果"并发数"<分组数，
* 就会报错：非法的分区号，但是如果并发数=1，则不会调用分组逻辑，所有的数据进入唯一的一个reduceTask，也就不会报错
*/
job.setNumReduceTasks(Integer.parseInt(args[2]));
boolean res = job.waitForCompletion(true);
System.exit(res ? 0 : 1);
}
}