Java開發的mapreduce如何在hadoop中運行

最近在學習hadoop，安裝的版本是hadoop2.7.3。

思考着如何把編寫好的mapreduce內容部署到hadoop中並運行這個程序，下面記錄了這部分實踐內容。上面代碼打包 hadoop-test.jar，打包方式任選。

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;

/**
 * 該例子為網上經典例子統計單詞出現次數
 *
 */
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 偏移量包括了回車所占的字符數(Windows和Linux環境會不同)
         * value 一行數據
         * context存儲新Map的對象
         */
        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 為Map中的key，hadoop會把相同key的內容合並為一個list，該list就為values。
         * context為存放結果的對象
         */
        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. 上傳包到部署有hadoop的機器上，本例子上傳到/home/hadoop目錄。
2. 用工具putty/SecureCRT登錄到系統，進入hadoop/bin目錄下。
3. 運行命令./hadoop jar ~/hadoop-test.jar com.ksy.hadoop.WordCount /user/hadoopfile output，這樣就把該例子運行了，通過./hdfs dfs -ls /user/hadoop/output/可以查看到運行后生成了兩個文件

   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，該文件可以通過shell命令上傳到hdfs中，output是輸出目錄。