Debian Hadoop 应用怎样开发

<code>sudo apt update
sudo apt install openjdk-11-jdk</code>

<code>java -version</code>

<code>wget https://downloads.apache.org/hadoop/common/hadoop-3.3.4/hadoop-3.3.4.tar.gz
tar -xzvf hadoop-3.3.4.tar.gz -C /usr/local/</code>

<code>export HADOOP_HOME=/usr/local/hadoop-3.3.4
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin</code>

<code>source ~/.bashrc</code>

<code>start-dfs.sh
start-yarn.sh</code>

<code>jps</code>

<code>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 java.io.IOException;
import java.util.StringTokenizer;

public class WordCount {

    public static class TokenizerMapper extends Mapper<object intwritable="" text=""> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object 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=""> {
        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();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.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);
    }
}
</intwritable></text></object></code>

<code>javac -cp $(hadoop classpath) WordCount.java
jar cf wordcount.jar WordCount*.class</code>

<code>hadoop jar wordcount.jar WordCount input output</code>