Java开发的mapreduce如何在hadoop中运行

最近在学习hadoop，安装的版本是hadoop2.7.3。

思考着如何把编写好的mapreduce内容部署到hadoop中并运行这个程序，下面记录了这部分实践内容。上面代码打包 hadoop-test.jar，打包方式任选。

package com.ksy.hadoop;

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.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;

/**
 * 该例子为网上经典例子统计单词出现次数
 *
 */
public class WordCount {
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        /**
         * key 偏移量包括了回车所占的字符数(Windows和Linux环境会不同)
         * value 一行数据
         * context存储新Map的对象
         */
        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, IntWritable> {
        private IntWritable result = new IntWritable();

        /**
         * key 为Map中的key，hadoop会把相同key的内容合并为一个list，该list就为values。
         * context为存放结果的对象
         */
        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();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }
        Job job = new Job(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(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

 

1. 上传包到部署有hadoop的机器上，本例子上传到/home/hadoop目录。
2. 用工具putty/SecureCRT登录到系统，进入hadoop/bin目录下。
3. 运行命令./hadoop jar ~/hadoop-test.jar com.ksy.hadoop.WordCount /user/hadoopfile output，这样就把该例子运行了，通过./hdfs dfs -ls /user/hadoop/output/可以查看到运行后生成了两个文件

   hadoop@ubuntu-114:/usr/local/hadoop/bin$ ./hdfs dfs -ls /user/hadoop/output/
   Found 2 items
   -rw-r--r--   1 hadoop supergroup          0 2017-07-25 19:00 /user/hadoop/output/_SUCCESS
   -rw-r--r--   1 hadoop supergroup      57649 2017-07-25 19:00 /user/hadoop/output/part-r-00000

    其中/user/hadoopfile是需要分析的hdfs文件，该文件可以通过shell命令上传到hdfs中，output是输出目录。