码迷,mamicode.com
首页 > 其他好文 > 详细

hadoop相关

时间:2018-05-24 23:07:58      阅读:80      评论:0      收藏:0      [点我收藏+]

标签:epo   row   map   jar   NPU   tab   参考   sed   word   

执行wordcount

代码

技术分享图片
package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;

public class WordCount {

    public static class Map extends MapReduceBase implements
            Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                output.collect(word, one);
            }
        }
    }

    public static class Reduce extends MapReduceBase implements
            Reducer<Text, IntWritable, Text, IntWritable> {
        public void reduce(Text key, Iterator<IntWritable> values,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        JobConf conf = new JobConf(WordCount.class);
        conf.setJobName("wordcount");

        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(Map.class);
        conf.setCombinerClass(Reduce.class);
        conf.setReducerClass(Reduce.class);

        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);

        FileInputFormat.setInputPaths(conf, new Path(args[0]));
        FileOutputFormat.setOutputPath(conf, new Path(args[1]));

        JobClient.runJob(conf);
    }
}
View Code

首先进行编译:

技术分享图片
javac -classpath ./share/hadoop/common/hadoop-common-2.7.6.jar:./share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.7.6.jar -d WordCount ./WordCount/WordCount.java
View Code

 然后压包

技术分享图片
jar -cvf wordcount.jar org/*
View Code

在复制到hadoop的工作目录下

参考:

http://cardyn.iteye.com/blog/1356361

https://blog.csdn.net/qichangleixin/article/details/43376587

hadoop相关

标签:epo   row   map   jar   NPU   tab   参考   sed   word   

原文地址:https://www.cnblogs.com/vactor/p/9085467.html

(0)
(0)
   
举报
评论 一句话评论(0
0条  
登录后才能评论!
© 2014 mamicode.com 版权所有 京ICP备13008772号-2
迷上了代码!