• wordcount


    源代码如下

    package org.apache.hadoop.examples;

    import java.io.IOException;

    import java.util.StringTokenizer;

    import org.apache.hadoop.conf.Configuration;

    import org.apache.hadoop.fs.Path;

    import org.apache.hadoop.io.IntWritable;

    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 org.apache.hadoop.util.GenericOptionsParser;

    public class WordCount {

      public static class TokenizerMapper

          extends Mapper<Object, Text, Text, IntWritable>{

          private final static IntWritable one = new IntWritable(1);

          private Text word = new Text();

          public void map(Object key, Text value, Context context)

            throws IOException, InterruptedException {

            StringTokenizer itr = new StringTokenizer(value.toString());

            while (itr.hasMoreTokens()) {

            word.set(itr.nextToken());

            context.write(word, one);

          }

        }

      }

      public static class IntSumReducer

          extends Reducer<Text,IntWritable,Text,IntWritable> {

          private IntWritable result = new IntWritable();

          public void reduce(Text key, Iterable<IntWritable> values,Context context)

               throws IOException, InterruptedException {

            int sum = 0;

            for (IntWritable val : values) {

               sum += val.get();

            }

          result.set(sum);

          context.write(key, result);

        }

      }

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

        Configuration conf = new Configuration();

        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        if (otherArgs.length != 2) {

          System.err.println("Usage: wordcount <in> <out>");

          System.exit(2);

        }

        Job job = new Job(conf, "word count");

        job.setJarByClass(WordCount.class);

        job.setMapperClass(TokenizerMapper.class);

        job.setCombinerClass(IntSumReducer.class);

        job.setReducerClass(IntSumReducer.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

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

    }

    }

  • 相关阅读:
    让a标签点击后不发生跳转
    关于antlr.collections.AST.getLine()I错误及解决
    Python -pycharm光标变粗解决办法!!
    通过了博客园的申请,感觉自己有了归宿!
    作为甲方对软件公司的项目实施团队提的几点要求
    高性能MySql学习笔记-第五章:创建高性能的索引
    高性能MySql学习笔记-第四章:Schema 与数据类型优化
    高性能MySql学习笔记-第三章:服务器性能剖析
    npm publish报错403 Forbidden
    父子组件利用@Input和@Output传值时显示undefined
  • 原文地址:https://www.cnblogs.com/xry1125/p/5554076.html
Copyright © 2020-2023  润新知