用MapReduce写一个wordcount做词频统计

需求: 在一堆给定的文本文件中统计输出每一个单词出现的总次数

Step 1. 数据格式准备

1.创建一个新的文件

cd /export/servers
vim wordcount.txt

2. 向其中放入以下内容并保存

hello,world,hadoop
hive,sqoop,flume,hello
kitty,tom,jerry,world
hadoop

3. 上传到 HDFS

hdfs dfs -mkdir /wordcount/
hdfs dfs -put wordcount.txt /wordcount/

Step 2. Mapper

public class WordCountMapper extends
Mapper<LongWritable,Text,Text,LongWritable> {
    @Override
    public void map(LongWritable key, Text value, Context context) throws
IOException, InterruptedException {
        String line = value.toString();
        String[] split = line.split(",");
        for (String word : split) {
            context.write(new Text(word),new LongWritable(1));
       }
   }
}

Step 3. Reducer

public class WordCountReducer extends
Reducer<Text,LongWritable,Text,LongWritable> {
    /**
     * 自定义我们的reduce逻辑
     * 所有的key都是我们的单词，所有的values都是我们单词出现的次数
     * @param key
     * @param values
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values,
Context context) throws IOException, InterruptedException {
        long count = 0;
        for (LongWritable value : values) {
            count += value.get();
       }
        context.write(key,new LongWritable(count));
   }
}

Step 4. 定义主类, 描述 Job 并提交 Job

public class JobMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        Job job = Job.getInstance(super.getConf(),
JobMain.class.getSimpleName());
        //打包到集群上面运行时候，必须要添加以下配置，指定程序的main函数
        job.setJarByClass(JobMain.class);
        //第一步：读取输入文件解析成key，value对
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new
Path("hdfs://192.168.52.250:8020/wordcount"));
        //第二步：设置我们的mapper类
        job.setMapperClass(WordCountMapper.class);
        //设置我们map阶段完成之后的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        //第三步，第四步，第五步，第六步，省略
        //第七步：设置我们的reduce类
        job.setReducerClass(WordCountReducer.class);
        //设置我们reduce阶段完成之后的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        //第八步：设置输出类以及输出路径
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new
Path("hdfs://192.168.52.250:8020/wordcount_out"));
        boolean b = job.waitForCompletion(true);
        return b?0:1;
   }
    /**
     * 程序main函数的入口类
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        Tool tool  =  new JobMain();
        int run = ToolRunner.run(configuration, tool, args);
        System.exit(run);
   }
}