基于MapReduce的词频统计程序WordCountApp(一)

词频统计案例分析：
wordcount: 统计文件中每个单词出现的次数

需求：求wc

1. 文件内容小：shell(wc_shell.sh)
   

使用IDEA+Maven开发wc：
1）开发
2）编译：mvn clean package -DskipTests

3）上传到服务器：scp target/HDFS_Test-1.0-SNAPSHOT.jar zq@zq:~/lib
4）运行
hadoop jar /home/zq/lib/HDFS_Test-1.0-SNAPSHOT.jar MapReduce.WordCountApp hdfs://zq:8020/hello.txt hdfs://zq:8020/output/wc




可见，程序准确无误

代码如下：
WordCountApp.java

package MapReduce;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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;

/**
 * 使用MapReduce开发WordCount应用程序
 */
public class WordCountApp {

    /**
     * Map：读取输入的文件
     */
    public static class MyMapper extends Mapper {

        LongWritable one = new LongWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            // 接收到的每一行数据
            String line = value.toString();

            //按照指定分隔符进行拆分
            String[] words = line.split(" ");

            for (String word : words) {
                // 通过上下文把map的处理结果输出
                context.write(new Text(word), one);
            }

        }
    }

    /**
     * Reduce：归并操作
     */
    public static class MyReducer extends Reducer {

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

            long sum = 0;
            for (LongWritable value : values) {
                // 求key出现的次数总和
                sum += value.get();
            }

            // 最终统计结果的输出
            context.write(key, new LongWritable(sum));
        }
    }

    /**
     * 定义Driver：封装了MapReduce作业的所有信息
     */
    public static void main(String[] args) throws Exception {

        //创建Configuration
        Configuration configuration = new Configuration();

        //创建Job
        Job job = Job.getInstance(configuration, "wordcount");

        //设置job的处理类
        job.setJarByClass(WordCountApp.class);

        //设置作业处理的输入路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));

        //设置map相关参数
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //设置reduce相关参数
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //设置作业处理的输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

如果有不懂的，可以先阅读我的前面关于HDFS和YARN的几篇博客，再看这篇应该好懂一些
有问题欢迎留言！

更多代码以及详细信息见我的github相关项目
https://github.com/29DCH/Hadoop-MapReduce-Examples