大数据的MapReduce-WordCount案例

大数据的MapReduce-WordCount案例

代码实现

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.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 java.io.IOException;

public class WordCount {

    public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
        Text k = new Text();
        IntWritable v = new IntWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] split = value.toString().split(" ");

            for (String s : split) {
                k.set(s);
                context.write(k, v);
            }
        }
    }

    public static class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
        IntWritable v = new IntWritable();
        int sum = 0;

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException,
                InterruptedException {

            for (IntWritable value : values) {
                sum += value.get();
            }
            v.set(sum);
            context.write(key, v);
        }
    }

    public static void main(String[] args) throws Exception {

        args = new String[]{"e:/input", "e:/output"};
        // 1 获取配置信息以及封装任务
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 2 设置jar加载路径
        job.setJarByClass(WordCount.class);

        // 3 设置map和reduce类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReduce.class);

        // 4 设置map输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 设置输入和输出路径
        Path output = new Path(args[1]);
        FileSystem fs = FileSystem.get(configuration);
        if (fs.exists(output)) {
            fs.delete(output, true);
        }

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, output);

        // 7 提交
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);
    }
}