期末大作业

大数据期末大作业

源文件

 package org.apache.hadoop.examples;
 
import java.io.IOException;
import java.util.Iterator;
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 WordCount() {
    }
 
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        //String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
        String[] otherArgs=new String[]{"input","output"};
        if(otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
 
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCount.TokenizerMapper.class);
        job.setCombinerClass(WordCount.IntSumReducer.class);
        job.setReducerClass(WordCount.IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
 
        for(int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
 
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }
 
    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
 
        public IntSumReducer() {
        }
 
        public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            int sum = 0;
 
            IntWritable val;
            for(Iterator<IntWritable> i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = i$.next();
            }
 
            this.result.set(sum);
            context.write(key, this.result);
        }
    }
 
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text();
 
        public TokenizerMapper() {
        }
 
        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
 
            while(itr.hasMoreTokens()) {
                this.word.set(itr.nextToken());
                context.write(this.word, one);
            }
 
        }
    }
}

过程:
启动Hadoop:将准备好的文档上传到hdfs;浏览器打开“http:localhost:50070”,依次点击’‘Utilities’’->’‘Browse the file system’’->选择你要上传的txt文档->’‘upload’’
在这里插入图片描述

通过eclipse运行项目查看单词个数
在这里插入图片描述
将结果导出本地
在这里插入图片描述

相关推荐
©️2020 CSDN 皮肤主题: 深蓝海洋 设计师:CSDN官方博客 返回首页