大数据学习——mapreduce案例join算法

需求：

用mapreduce实现
select order.orderid,order.pdtid,pdts.pdt_name,oder.amount
from order
join pdts
on order.pdtid=pdts.pdtid

数据：

orders.txt

Order_0000001,pd001,222.8
Order_0000001,pd005,25.8
Order_0000002,pd005,325.8
Order_0000002,pd003,522.8
Order_0000002,pd004,122.4
Order_0000003,pd001,222.8
Order_0000003,pd001,322.8

pdts.txt

pd001,apple
pd002,banana
pd003,orange
pd004,xiaomi
pd005,meizu

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">

    <modelVersion>4.0.0</modelVersion>

    <groupId>com.cyf</groupId>
    <artifactId>MapReduceCases</artifactId>
    <packaging>jar</packaging>
    <version>1.0</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.6.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.6.4</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.1.40</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.36</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <appendAssemblyId>false</appendAssemblyId>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                    <archive>
                        <manifest>
                            <mainClass>cn.itcast.mapreduce.CacheFile.MapJoinDistributedCacheFile</mainClass>
                        </manifest>
                    </archive>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>assembly</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

package cn.itcast.mapreduce.CacheFile;


import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.HashMap;

import org.apache.commons.lang.StringUtils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
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;

public class MapJoinDistributedCacheFile {
    private static final Log log = LogFactory.getLog(MapJoinDistributedCacheFile.class);

    public static class MapJoinDistributedCacheFileMapper extends Mapper<LongWritable, Text, Text, NullWritable> {

        FileReader in = null;
        BufferedReader reader = null;
        HashMap<String, String[]> b_tab = new HashMap<String, String[]>();

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            // 此处加载的是产品表的数据
            in = new FileReader("pdts.txt");
            reader = new BufferedReader(in);
            String line = null;
            while (StringUtils.isNotBlank((line = reader.readLine()))) {
                String[] split = line.split(",");
                String[] products = {split[0], split[1]};
                b_tab.put(split[0], products);
            }
            IOUtils.closeStream(reader);
            IOUtils.closeStream(in);
        }

        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();
            String[] orderFields = line.split(",");
            String pdt_id = orderFields[1];
            String[] pdtFields = b_tab.get(pdt_id);
            String ll = orderFields[0] + "	" + pdtFields[1] + "	" + orderFields[1] + "	" + orderFields[2];
            context.write(new Text(ll), NullWritable.get());
        }
    }


    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

//        job.setJarByClass(MapJoinDistributedCacheFile.class);
        //告诉框架，我们的程序所在jar包的位置
        job.setJar("/root/MapJoinDistributedCacheFile.jar");
        job.setMapperClass(MapJoinDistributedCacheFileMapper.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.setInputPaths(job, new Path("/mapjoin/input"));
        FileOutputFormat.setOutputPath(job, new Path("/mapjoin/output"));

        job.setNumReduceTasks(0);
        
//        job.addCacheFile(new URI("file:/D:/pdts.txt"));
        job.addCacheFile(new URI("hdfs://mini1:9000/cachefile/pdts.txt"));


        job.waitForCompletion(true);
    }
}

创建文件夹上传数据

 hadoop fs -mkdir -p /cachefile

 hadoop fs -put pdts.txt /cachefile

 hadoop fs -mkdir -p /mapjoin/input

 hadoop fs -put orders.txt /mapjoin/input

打包并运行

运行

hadoop jar MapJoinDistributedCacheFile.jar cn.itcast.mapreduce.CacheFile.MapJoinDistributedCacheFile    

运行结果