運行代碼：
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCountRunner {
public static void main(String[] args) throws Exception {
// 創建本次mr程序的job實例
Configuration conf = new Configuration();
conf.set(“hadoop.tmp.dir”,“E:\tmp\hadoop-abc”);
// conf.set(“mapreduce.framework.name”, “local”);
Job job = Job.getInstance(conf);
// 指定本次job運行的主類
job.setJarByClass(WordCountRunner.class);
// 指定本次job的具體mapper reducer實現類
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
// 指定本次job map階段的輸出數據類型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
// 指定本次job reduce階段的輸出數據類型 也就是整個mr任務的最終輸出類型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
// 指定本次job待處理數據的目錄 和程序執行完輸出結果存放的目錄
long startTime=System.currentTimeMillis(); //獲取開始時間
//FileInputFormat.setMaxInputSplitSize(job, 128);
//FileInputFormat.setMinInputSplitSize(job, 128);
FileInputFormat.setInputPaths(job,“E:\wordcount\input\words.txt”);
FileOutputFormat.setOutputPath(job, new Path(“E:\wordcount\output”));
// 提交本次job
boolean b = job.waitForCompletion(true);
long endTime=System.currentTimeMillis(); //獲取結束時間
System.out.println("程序運行時間： "+(endTime-startTime)+“ms”);
System.exit(b ? 0 : 1);
}
}