版权声明:www.hsboy.cn [email protected] https://blog.csdn.net/oHongShu1/article/details/88930581
import java.io.IOException;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordcountDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// 1 获取配置信息以及封装任务
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 2 设置jar加载路径
job.setJarByClass(WordcountDriver.class);
// 3 设置map和reduce类
job.setMapperClass(WordcountMapper.class);
job.setReducerClass(WordcountReducer.class);
// 4 设置map输出
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// 5 设置最终输出kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//job.setInputFormatClass(KeyValueTextInputFormat.class);
// 6 设置输入和输出路径
FileInputFormat.setInputPaths(job, 输入路径);
FileOutputFormat.setOutputPath(job, 输出路径);//提前不能存在
// 7 提交
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}