林子雨编著《大数据基础编程、实验和案例教程（第2版）》教材第7章的代码

public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text(); 
        public TokenizerMapper() {
        }
        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString()); 
            while(itr.hasMoreTokens()) {
                this.word.set(itr.nextToken());
                context.write(this.word, one);
            }
        }
    }

public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable(); 
        public IntSumReducer() {
        }
        public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            int sum = 0; 
            IntWritable val;
            for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = (IntWritable)i$.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }

public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
        if(otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");        //设置环境参数
        job.setJarByClass(WordCount.class);                //设置整个程序的类名
        job.setMapperClass(WordCount.TokenizerMapper.class); //添加Mapper类
        job.setReducerClass(WordCount.IntSumReducer.class);  //添加Reducer类
        job.setOutputKeyClass(Text.class);                  //设置输出类型
        job.setOutputValueClass(IntWritable.class);             //设置输出类型 
        for(int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));  //设置输入文件
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));//设置输出文件
        System.exit(job.waitForCompletion(true)?0:1);
    }

import java.io.IOException;
import java.util.Iterator;
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;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
    public WordCount() {
    }
     public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
        if(otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCount.TokenizerMapper.class);
        job.setCombinerClass(WordCount.IntSumReducer.class);
        job.setReducerClass(WordCount.IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class); 
        for(int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public TokenizerMapper() {
        }
        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString()); 
            while(itr.hasMoreTokens()) {
                this.word.set(itr.nextToken());
                context.write(this.word, one);
            }
        }
    }
public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
        public IntSumReducer() {
        }
        public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            int sum = 0;
            IntWritable val;
            for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = (IntWritable)i$.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }
}

cd /usr/local/hadoop

javac WordCount.java

jar -cvf WordCount.jar *.class

./bin/hadoop jar WordCount.jar WordCount input output

./bin/hadoop fs -cat output/*

cd /usr/local/hadoop/myapp
ls

cd /usr/local/hadoop
./sbin/start-dfs.sh

cd /usr/local/hadoop
./bin/hdfs dfs -rm -r input
./bin/hdfs dfs -rm -r output

cd /usr/local/hadoop
./bin/hdfs dfs -mkdir input

cd /usr/local/hadoop
./bin/hdfs dfs -put ./wordfile1.txt input
./bin/hdfs dfs -put ./wordfile2.txt input

cd /usr/local/hadoop
./bin/hdfs dfs -rm -r /user/hadoop/output

cd /usr/local/hadoop
./bin/hadoop jar ./myapp/WordCount.jar input output

cd /usr/local/hadoop
./bin/hdfs dfs -cat output/*