MapReduce初试

Posted 2022-06-07 mitsuhide1992

面试中问到mapreduce，所以装了单机版mapreduce，hadoop2，尝试一下。

工具

idea，maven，jdk8

Maven配置

<?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/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>mitsuhide</groupId>
    <artifactId>javaAIA</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <hadoop.version>2.7.2</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>$hadoop.version</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>$hadoop.version</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>$hadoop.version</version>
        </dependency>
   </dependencies>
   <repositories>
       <repository>
            <id>apache</id>
            <url>http://maven.apache.org</url>
       </repository>
   </repositories>
</project>

注意hadoop2和hadoop1不一样，hadoop1是hadoop-core，这里用不到了。

配置输入输出

在web路径下，配置了input文件夹，output文件夹是mapreduce自动生成的，不用配置。
程序会读取input文件夹下所有文件，按行读取。

配置运行参数

就是在参数上加上input和output：

wordcount

package cn.bigdata.hadoop.mapreduce;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;

/**
 * Created by baidu on 16/9/29.
 */
public class WordCount 
    public static class TokenizerMapper
            extends Mapper<Object, Text, Text, IntWritable> 

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context
        ) throws IOException, InterruptedException 
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) 
                word.set(itr.nextToken());
                context.write(word, one);
            
        
    

    public static class IntSumReducer
            extends Reducer<Text, IntWritable, Text, IntWritable> 
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values,
                           Context context
        ) throws IOException, InterruptedException 
            int sum = 0;
            for (IntWritable val : values) 
                sum += val.get();
            
            result.set(sum);
            context.write(key, result);
        
    

    public static void main(String[] args) throws Exception 
        Configuration conf = new Configuration();
        System.out.println(conf.getStrings("mapreduce.framework.name"));
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    

运行

见output下的文本输出：

"Be 2
"Don't  1
16, 1
20. 1
20; 1
24  1
60  2
80. 1
All 1
But 3
...

运行完成！