MapReduce实例 - WordCount

用IntelliJ IDEA 2021编辑，实际运行在Ubuntu18.04的虚拟机上。
Hadoop版本3.0.0。

导入方法：Project Structure -> Project Settings -> Modules -> Dependencies -> "+"

{HADOOP_HOME}/share/hadoop/common/hadoop-common-3.0.0.jar
{HADOOP_HOME}/share/hadoop/common/haoop-nfs-3.0.0.jar
{HADOOP_HOME}/share/hadoop/common/lib/*
{HADOOP_HOME}/share/hadoop/hdfs/haoop-hdfs-3.0.0.jar
{HADOOP_HOME}/share/hadoop/hdfs/hdfs-nfs-3.0.0.jar
{HADOOP_HOME}/share/hadoop/hdfs/lib/*
{HADOOP_HOME}/share/hadoop/mapreduce/*

官网代码：https://hadoop.apache.org/docs/r1.0.4/cn/mapred_tutorial.html

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.*;

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

public class WordCount {

    public static class Map extends MapReducebase implements Mapper {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, OutputCollector output, Reporter reporter) throws IOException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                output.collect(word, one);
            }
        }
    }
    public static class Reduce extends MapReducebase implements Reducer {
        public void reduce(Text key, Iterator values, OutputCollector output, Reporter reporter) throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        JobConf conf = new JobConf(WordCount.class);
        conf.setJobName("wordcount");

        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(Map.class);
        conf.setCombinerClass(Reduce.class);
        conf.setReducerClass(Reduce.class);

        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);

        FileInputFormat.setInputPaths(conf, new Path(args[0]));
        FileOutputFormat.setOutputPath(conf, new Path(args[1]));

        JobClient.runJob(conf);
    }
}

javac WordCount.java
jar -cvf WordCount.jar ./WordCount*.class

查看一下有关wordcount的HDFS的目录：

hadoop fs -ls /wordcount/

input里面存放的是输入的文件。sampleoutput是输出文件夹。
每次运行代码的时候都要把输出文件夹删除掉，否则会报org.apache.hadoop.mapred.FileAlreadyExistsException。

hadoop fs -rm -r /wordcount/sampleoutput

然后运行MapReduce程序：

hadoop jar WordCount.jar WordCount /wordcount/input/ /wordcount/sampleoutput

第一个参数WordCount是类名，如有程序中有包装在package中，要把类名写完整（包名+类名）。
第二个参数是输入路径，第三个参数是输出路径。
跑成功大概可以看到这一句：

INFO mapreduce.Job: Job job_local1565413150_0001 completed successfully

hadoop fs -cat /wordcount/sampleoutput/* | head -n 5

shuchu1

[1]一起学Hadoop——第一个MapReduce程序
[2] 使用命令行编译打包运行自己的MapReduce程序 Hadoop2.6.0