MapJoin 案例缓存文件处理| 学习笔记

import java.net.URI;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.NullWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class DistributedCacheDriver {

public static void main(String[] args) throws Exception, IOException {

//0根据自己电脑路径重新配置args = new string[ ] { "e:/input/inputtable2",

"e :/output1"};

// 1 获取job信息

Configuration configuration = new Configuration();

Job job = Job.getInstance(configuration);

// 2 设置加载jar包路径

job.setJarByClass(DistributedCacheDriver.class);

// 3 关联map

job.setMapperClass(DistributedCacheMapper.class);

// 4 设置最终输出数据类型

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(NullWritable.class);

// 5 设置输入输出路径

FileInputFormat.setInputPaths(job, new Path(args[0]));

FileOutputFormat.setOutputPath(job, new Path(args[1]));

// 6 加载缓存数据

job.addCacheFile(new URI("file:///e:/input/inputcache/pd.txt"));

// 7 Map端Join的逻辑不需要Reduce阶段，设置reduceTask数量为0

job.setNumReduceTasks(0);

// 8 提交

boolean result = job.waitForCompletion(true);

System.exit(result ? 0 : 1);

}

}

 import java.io.BufferedReader;

import java.io.FileInputStream;

import java.io.IOException;

import java.io.InputStreamReader;

import java.net.URI;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.NullWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

public class DistributedCacheMapper extends Mapper<LongWritable, Text, Text, NullWritable> {

@Override

protected void setup(Mapper<LongWritable, Text, Text, NullWritable>.Context context)

throws IOException, InterruptedException {

// 缓存小表

URI[] cacheFiles = context.getCacheFiles();

String path = cacheFiles[0].getPath().toString();

BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(path), "UTF-8"));

String line;

while (StringUtils.isNotEmpty(line = reader.readLine())) {

// 切割

String[] fileds = line.split("\t");

pdMap.put(fileds[0], fileds[1]);

}

// 关闭资源

IOUtils.closeStream(reader);

}

@Override

protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

// 获取一行

String line = value.toString();

// 切割

String[] fileds = line.split("\t");

// 获取pid

String pid = fileds[1];

// 获取pname

String pname = pdMap.get(pid);

System.out.println(pdMap.get("01"));

// 拼接

line = line + "\t" + pname;

k.set(line);

// 写出

context.write(k, NullWritable.get());

}

}