KeyValueTextInputFormat实例

package inputformat;

import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
 * hello	you	hello	you
 * hello	me
 *
 */
public class MyKeyValueTextInputFormatApp {
	private static final String INPUT_PATH = "hdfs://chaoren1:9000/hello";
	private static final String OUT_PATH = "hdfs://chaoren1:9000/out";

	public static void main(String[] args) throws Exception{
		Configuration conf = new Configuration();
                //使用特定的分割符分开
		conf.set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR, "\t");
		
		final FileSystem filesystem = FileSystem.get(new URI(OUT_PATH), conf);
		filesystem.delete(new Path(OUT_PATH), true);
		
		final Job job = new Job(conf , MyKeyValueTextInputFormatApp.class.getSimpleName());
		job.setJarByClass(MyKeyValueTextInputFormatApp.class);
		
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		job.setInputFormatClass(KeyValueTextInputFormat.class);
		job.setMapperClass(MyMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(LongWritable.class);
		job.setNumReduceTasks(0);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(LongWritable.class);
		FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
		
		job.waitForCompletion(true);
	}
	
	public static class MyMapper extends Mapper<Text, Text, Text, LongWritable>{
		protected void map(Text key, Text value, org.apache.hadoop.mapreduce.Mapper<Text,Text,Text,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
				context.write(key, new LongWritable(1));
				context.write(value, new LongWritable(1));
		};
	}
}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

波哥的技术积累

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值