WordCount运行测试

在hadoop目录下创建wordcount文件夹

mkdir wordcount

cd wordcount

创建输入文件夹input和两个输入文件file0、file1，在这里将wordcount源码作为file0内容。

创建WordCount.java文件，源码附在下方

vim WordCount.java

编译java文件

javac WordCount.java

将编译后的.class文件打成jar包

jar -cvf WordCount.jar *.class 

上传测试文件到hdfs

hadoop fs -put input/* input

查看上传

hadoop fs -ls input/

运行Wordcount

hadoop jar WordCount.jar WordCount input output

如果hdfs中已有output存在则删除后再运行

hadoop fs -rmr output

WordCount.java

import java.io.IOException;
import java.util.*;
        
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
        
public class WordCount {
        
 public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
        
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        StringTokenizer tokenizer = new StringTokenizer(line,"\t\n\r\f\b, . :;?![]()<>{}\"=+-'");
        while (tokenizer.hasMoreTokens()) {
            word.set(tokenizer.nextToken());
            context.write(word, one);
        }
    }
 } 
        
 public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {

    public void reduce(Text key, Iterable<IntWritable> values, Context context) 
      throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values) {
            sum += val.get();
        }
        context.write(key, new IntWritable(sum));
    }
 }
        
 public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
        
    Job job = new Job(conf, "wordcount");
    
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
        
    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);
        
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
        
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
    job.waitForCompletion(true);
 }
        
}