<configuration>
<!--  resource,manager主节点所在机器 -->
<property>
<name>yarn.resourcemanager.hostname</name>
<value>doit001</value>
</property><!--  为mr程序提供shuffle服务 -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property><!--  一台NodeManager的总可用内存资源 -->
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>2048</value>
</property>
<!--  一台NodeManager的总可用（逻辑）cpu核数 -->
<property>
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>2</value>
</property><!--  是否检查容器的虚拟内存使用超标情况 -->
<property><name>yarn.nodemanager.vmem-check-enabled</name><value>false</value>
</property><!--  容器的虚拟内存使用上限：与物理内存的比率 -->
<property><name>yarn.nodemanager.vmem-pmem-ratio</name><value>2.1</value>
</property></configuration>

package cn.doit19.hadoop.review.join;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.*;/*** @author:tom* @Date:Created in 21:43 2020/11/17*/
@SuppressWarnings("all")
public class JoinApp {static class JoinMap extends Mapper<LongWritable, Text, Text, NullWritable> {String fileName = null;Text k = new Text();Map<String, String> map = null;@Overrideprotected void setup(Context context) throws IOException, InterruptedException {map = new HashMap<>();BufferedReader br = new BufferedReader(new FileReader("user.txt"));String line = null;while ((line = br.readLine()) != null) {String[] split = line.split(",");map.put(split[0], split[1] + "," + split[2] + "," + split[3] + "," + split[4]);}}@Overrideprotected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {String line = value.toString();//处理order.txtString[] split = line.split(",");String user = map.getOrDefault(split[1], "null,null,null,null");String s = split[0] + "," + user;k.set(s);context.write(k, NullWritable.get());}}public static void main(String[] args) throws Exception {//初始化配置对象Configuration conf = new Configuration();
// 设置程序默认启动方式   yarn  默认为本地conf.set("mapreduce.framework.name", "yarn");// yarn的resourcemanager的位置conf.set("yarn.resourcemanager.hostname", "linux01");//创建job对象Job job = Job.getInstance(conf,"joincase");//       将  HDFS 上的  user.txt 分布式缓存到执行maptask任务的机器上job.addCacheFile(new URI("/data/user.txt"));// 设置访问的集群的位置// conf.set("fs.defaultFS", "hdfs://doit01:9000");// 设置MapReduce程序运行在windows上的跨平台参数// conf.set("mapreduce.app-submission.cross-platform","true");//设置map task 类job.setMapperClass(JoinMap.class);//设置reduce 最终输出类型  kvjob.setOutputKeyClass(Text.class);job.setOutputValueClass(NullWritable.class);//设置jar包  通过类名找到位置job.setJarByClass(JoinApp.class);//设置输入路径FileInputFormat.setInputPaths(job, new Path("/mr/in"));//设置输出路径FileOutputFormat.setOutputPath(job, new Path("/mr/out"));//提交任务boolean s = job.waitForCompletion(true);}
}