这篇文章主要为大家展示了“hadoop中如何实现KeyValueTextInputFormat”,内容简而易懂,条理清晰,希望能够帮助大家解决疑惑,下面让小编带领大家一起研究并学习一下“hadoop中如何实现KeyValueTextInputFormat”这篇文章吧。
package com.test;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.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;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
* hello jim
* hello tim
*
* 最后输出
* hello 1
* jim 1
* hello 1
* tim 1
*/
public class WordCountKeyValue extends Configured implements Tool {
public static class Map extends Mapper<Text, Text, Text, IntWritable> {
/**
* key hello
* value jim
*/
public void map(Text key, Text value, Context context) throws IOException, InterruptedException {
context.write(key, new IntWritable(1));
context.write(value, new IntWritable(1));
}
}
public int run(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = this.getConf();
//指定KeyValueTextInputFormat分割符,默认分割符是\t
//conf.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", "\t");
conf.set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR, "\t");
Job job = new Job(conf);
job.setJobName(WordCountKeyValue.class.getSimpleName());
job.setJarByClass(WordCountKeyValue.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setNumReduceTasks(0);
job.setMapperClass(Map.class);
job.setInputFormatClass(KeyValueTextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.waitForCompletion(true);
return job.isSuccessful()?0:1;
}
public static void main(String[] args) throws Exception {
int exit = ToolRunner.run(new WordCount(), args);
System.exit(exit);
}
}
以上是“hadoop中如何实现KeyValueTextInputFormat”这篇文章的所有内容,感谢各位的阅读!相信大家都有了一定的了解,希望分享的内容对大家有所帮助,如果还想学习更多知识,欢迎关注亿速云行业资讯频道!
亿速云「云服务器」,即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘,价格低至29元/月。点击查看>>
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。
原文链接:https://my.oschina.net/sniperLi/blog/366259