hadoop wordcount 的hello world

Hadoop WordCount是一个经典的MapReduce示例程序，用于计算给定文本文件中每个单词出现的次数。以下是Hadoop MapReduce中实现WordCount的一个简单"Hello World"级别的例子：

首先，你需要有一个Mapper类，它负责读取输入数据并分解成键值对（key-value pairs）。在这个例子中，我们将每个单词作为键，值设为1。

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper 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();
        for (String token : line.split("\\s+")) {
            word.set(token);
            context.write(word, one);
        }
    }
}

然后，你需要一个Reducer类，它接收Mapper阶段产生的键值对，并计算每个单词的实际计数。

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer 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);
    }
}

最后，在Driver类中设置Mapper和Reducer，以及配置Job运行。

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCountMapper.class);
        job.setCombinerClass(WordCountReducer.class);
        job.setReducerClass(WordCountReducer.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);
    }
}

运行这个程序时，需要提供两个参数：一个是包含文本数据的输入文件路径，另一个是期望生成结果的输出目录。例如，你可以像这样运行：

hadoop jar your-word-count-job.jar WordCount input.txt output-dir