mac上eclipse上运行word count

1.打开eclipse之后，建立wordcount项目

package wordcount;

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.LongWritable;

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;

public class WordCount {

    public static class TokenizerMapper extends 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, 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();

        if (args.length != 2) {

            System.err.println("Usage: wordcount  ");

            System.exit(2);

        }

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

        job.setJarByClass(WordCount.class);

        job.setMapperClass(TokenizerMapper.class);

        job.setReducerClass(IntSumReducer.class);

        job.setMapOutputKeyClass(Text.class);

        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

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

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

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

    }

}

2.配置hadoop路径。

把需要运行的文件放进input文件夹，如何在eclipse上的run configuration上配置需要运行的文件路径和运行结果路径，中间用一个空格隔开，如何点击apply-run,开始跑。

mac上eclipse上运行word count

3.用终端查看结果

JIAS-MacBook-Pro:output jia$ cat part-r-00000

do    2

excuse    1

fine    1

hello    2

how    1

me    1

thank    2

you    3

秒客网

mac上eclipse上运行word count

相关文章