Hadoop之HelloWorld

2019独角兽企业重金招聘Python工程师标准>>>

Hadoop之HelloWorld实例：

• 目的:将输入文件的中的Hello,World输出到文件为World Hello.
• 输入文件内容：

• 代码实例：

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
 * HelloWorld Job
 * 将输入文件中的Hello,World， 以World Hello输出到文件
 */
public class HelloWorld {

	/**
	 * 映射器
	 * 用于将我们的数据进行预处理
	 */
	private static class MyMapper extends Mapper<LongWritable, Text, Text, Text>{
		@Override
		protected void map(LongWritable key, Text value, Context context)
				throws IOException, InterruptedException {
			System.out.println("mapper running...");
			System.out.println("key=" + key.get());
			System.out.println("value=" + value.toString());
			String[] strValue = value.toString().split(",");
			context.write(new Text(strValue[1]), new Text(strValue[0]));
		}
	}
	
	/**
	 * 处理器
	 * 用于将mapper预处理的数据记录进行业务计算，然后输出
	 */
	private static class MyReducer extends Reducer<Text, Text, Text, Text>{
		@Override
		protected void reduce(Text key, Iterable<Text> values,
				Context context)
				throws IOException, InterruptedException {
			System.out.println("reducer running...");
			System.out.println("key=" + key.toString());
			String val = values.iterator().next().toString();
			System.out.println("value=" + val);
			context.write(key, new Text(val));
		}
	}
	
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		Configuration configuration = new Configuration();
		Job job = new Job(configuration, "helloworld_job");
		job.setJarByClass(HelloWorld.class);
		job.setMapperClass(MyMapper.class);
		job.setReducerClass(MyReducer.class);
		
		job.setInputFormatClass(TextInputFormat.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.addInputPath(job, new Path("hdfs://hadoopmaster:9000/in/helloworld.txt"));
		String outFileExt = "_" + new SimpleDateFormat("yyyyMMddHHmmss").format(new Date());
		FileOutputFormat.setOutputPath(job, new Path("hdfs://hadoopmaster:9000/out/helloworld"+outFileExt));
		System.out.println(job.waitForCompletion(true));
		
	}
}

• 将代码打包, 拷贝到hadoopmaster上：

• 执行jar包：

hadoop jar helloworld.jar

• 得到输出文件：

• 收工。

转载于:https://my.oschina.net/indestiny/blog/196254