IDEA调试运行WordCount程序

IDEA调试运行WordCount程序

先给出WordCount代码

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();
        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 TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public TokenizerMapper() {
        }
        @Override
        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);
            }
        }
    }
    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
        public IntSumReducer() {
        }
        @Override
        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 i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = (IntWritable)i$.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }
}

我们创建项目后发现该代码中的很多需要的类没有，这时候就需要手工导入了

将hadoop根目录路径为hadoop/share/hadoop/common中的

hadoop-common-3.3.5.jar和haoop-nfs-3.3.5.jar

/hadoop/share/hadoop/common/lib目录下的所有JAR包

/hadoop/share/hadoop/mapreduce”目录下的所有JAR包

导入项目中，发现此时WordCount程序已经没有报错了，接下来试着运行

出现

Usage: wordcount <in> [<in>...] <out>

说明程序正常运行

接下来我们在idea中将我们的项目导出为jar包

然后回到hadoop环境，创建一个myapp目录

cd /opt/hadoop-2.7.4#
mkdir myapp

将我们的jar导入该文件夹，然后启动ssh

/usr/sbin/sshd

启动hdfs

/opt/hadoop-2.7.4/sbin/start-dfs.sh

创建input和output

hadoop fs -mkdir /input
hadoop fs -mkdir /output

创建两个文本文件，word1.txt和word2.txt 将其放到容器中

内容分别为：

I love java

I love python

和

I really like java

将其上传到input

hadoop dfs -put ../../myapp/hadoop_jar/word2.txt /input
hadoop dfs -put ../../myapp/hadoop_jar/word1.txt /input

然后执行程序:

 hadoop jar ../myapp/hadoop_jar/hadoop.jar /input /output

然后

hadoop dfs -cat output/*

就可以得到结果