hadoop 单词出现次数统计实例 java 代码WorldCount

WorldCount.class

package com.hadoop.test;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WorldCount {
    public static void main(String[] args) {
        //加载配置
        Configuration conf = new Configuration();
        try {
            FileSystem fs = FileSystem.get(conf);
            //创建任务
            Job job =Job.getInstance();
            job.setJarByClass(WorldCount.class);
            job.setJobName("WorldCount");
            //Mapper和Reducer类
            job.setMapperClass(WorldCountMapper.class);
            job.setReducerClass(WorldCountReducer.class);
            //Mapper的输出类型
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
            //输入输出路径
            FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/user/bob/wordcount/input"));
            Path out = new Path("hdfs://localhost:9000/user/bob/wordcount/output/wc");
            if(fs.exists(out)) {
                fs.delete(out, true);
            }
            FileOutputFormat.setOutputPath(job, out);
            boolean f = job.waitForCompletion(true);
            if(f){
                System.out.println("任务已经执行完成了");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}

WorldCountMapper.class

package com.hadoop.test;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;
/**
 * Created by bob on 17-6-29.
 */
public class WorldCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    /**
     * 该方法循环调用，从文件的split中没读取一行调用一次，
     * 把该行的所在的下表为key, 内容为value
     *
     * mapper的输出经过洗牌， 分组， 输出到reducer
     * 本例中， 洗牌和分组是默认的
     * 所以暂时不用考虑
     */
    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] words = StringUtils.split(value.toString(), ' ');
        for (String w : words) {
            context.write(new Text(w), new IntWritable(1));
        }
    }
}

WorldCountReducer.class

package com.hadoop.test;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
/**
 * Created by bob on 17-6-29.
 */
public class WorldCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
    /**
     * mapper之后的数据，经过洗牌分组， 输出到reducer
     * 该方法每处理一组调用一次
     *
     */
    protected void reduce(Text key, Iterable<IntWritable> vals,
                          Context context)
            throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable iw : vals) {
            sum += iw.get();
        }
        context.write(key, new IntWritable(sum));
    }
}

wc.text

hello Hadoop
hello word
this is my first hadoop program

1.引入hadoop中的所有jar,通过IDE工具把项目打成jar包
2.进入　/opt/hadoop-2.6.1/sbin

cd /opt/hadoop-2.6.1/sbin

sudo ./start-all.sh

hadoop fs -mkdir wordcount/input/ 

hadoop fs -put /home/bob/test/wc.txt 
wordcount/input

3. 执行jar

hadoop jar /home/bob/test/hadoopTest.jar com.hadoop.test.WorldCount

4.查看执行结果

hadoop fs -ls /user/bob/wordcount/output/wc/

hadoop fs -cat /user/bob/wordcount/output/wc/part-r-00000