4、 用 Java 实现的 MapReduce 去重编程

以下是用 Java 实现的 MapReduce 去重编程示例：

Mapper 类：

import java.io.IOException;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;

public class DuplicateRemoverMapper extends Mapper<LongWritable, Text, Text, NullWritable> {

    private Text word = new Text();

    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString().trim();
        if (!line.equals("")) { // 过滤掉空行
            word.set(line);
            context.write(word, NullWritable.get());
        }
    }
}

Reducer 类：

import java.io.IOException;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;

public class DuplicateRemoverReducer extends Reducer<Text, NullWritable, Text, NullWritable> {

    public void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key, NullWritable.get());
    }
}

Driver 类：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.*;
import org.apache.hadoop.mapreduce.lib.output.*;

public class DuplicateRemover {

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Duplicate Remover");
        job.setJarByClass(DuplicateRemover.class);

        job.setMapperClass(DuplicateRemoverMapper.class);
        job.setReducerClass(DuplicateRemoverReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

以上代码实现了一个简单的去重 MapReduce 程序。Mapper 类将每行文本数据作为一个键，输出到 Reducer 类中进行处理。Reducer 类直接将输入键输出到结果中，这样就实现了对文本数据的去重。