MapReduce编程基础WordCount

public class WordCountYARNApp {

    public static void main(String[] args) throws Exception {
        //1.获取job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        String input = args[0];
        String output = args[1];
        /**
         * 自定义写了一个工具类，递归删除指定目录
         */
        FileUtils.daleteTarget(output, configuration);

        //2.获取jar的相关信息
        job.setJarByClass(WordCountYARNApp.class);

        //3.设置自定义的Mapper和Reducer
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);

        //4.Mapper阶段输出的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //5.Reducer阶段输出的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6.设置输入输出路径

        FileInputFormat.setInputPaths(job, new Path(input));
        FileOutputFormat.setOutputPath(job, new Path(output));

        //7.提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }

    /**
     * KEYIN:    输入数据key的数据类型------每行数据的偏移量（一般没用）
     * KEYVALUE：输入数据value的数据类型----文本内容
     * KEYOUT：  输出数据key的数据类型------每个单词
     * VALUEOUT：输出数据value的数据类型----数量1
     */
    public static class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
        IntWritable ONE = new IntWritable(1);
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] splits = value.toString().split(",");
            for (String split : splits) {
                context.write(new Text(split), ONE);
            }
        }
    }

    public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        @Override
        protected void reduce(Text word, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int cnt = 0;
            for (IntWritable value : values) {
                cnt += value.get();
            }
            context.write(word, new IntWritable(cnt));
        }
    }
}

自定义的删除输出目录的工具类：

public class FileUtils {
    public static void daleteTarget(String output, Configuration configuration) throws IOException {
        FileSystem fileSystem = FileSystem.get(configuration);
        Path outPath = new Path(output);
        if (fileSystem.exists(outPath)) {
            fileSystem.delete(outPath, true);		//递归删除
        }
    }
}