MapReduce之Job工具類開發

[toc]

---

MapReduce之Job工具類開發

在MapReduce程序寫Mapper和Reducer的驅動程序時，有不少代碼都是重複性代碼，所以能夠將其提取出來寫成一個工具類，後面再寫MapReduce程序時都會使用這個工具類。

Job工具類開發

程序代碼以下：

package com.uplooking.bigdata.common.utils;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class MapReduceJobUtil {
    public static Job buildJob(Configuration conf,
                               Class<?> jobClazz,
                               String inputpath,
                               Class<? extends InputFormat> inputFormat,
                               Class<? extends Mapper> mapperClass,
                               Class<?> mapKeyClass,
                               Class<?> mapValueClass,
                               Path outputpath,
                               Class<? extends OutputFormat> outputFormat,
                               Class<? extends Reducer> reducerClass,
                               Class<?> outkeyClass,
                               Class<?> outvalueClass) throws IOException {

        String jobName = jobClazz.getSimpleName();
        Job job = Job.getInstance(conf, jobName);
        //設置job運行的jar
        job.setJarByClass(jobClazz);
        //設置整個程序的輸入
        FileInputFormat.setInputPaths(job, inputpath);
        job.setInputFormatClass(inputFormat);//就是設置如何將輸入文件解析成一行一行內容的解析類
        //設置mapper
        job.setMapperClass(mapperClass);
        job.setMapOutputKeyClass(mapKeyClass);
        job.setMapOutputValueClass(mapValueClass);
        //設置整個程序的輸出
        outputpath.getFileSystem(conf).delete(outputpath, true);//若是當前輸出目錄存在，刪除之，以免.FileAlreadyExistsException
        FileOutputFormat.setOutputPath(job, outputpath);
        job.setOutputFormatClass(outputFormat);
        //設置reducer，若是有才設置，沒有的話就不用設置
        if (null != reducerClass) {
            job.setReducerClass(reducerClass);
            job.setOutputKeyClass(outkeyClass);
            job.setOutputValueClass(outvalueClass);
        }
        return job;
    }
}