Hadoop中的MultipleOutput使用(45)

最新推荐文章于 2020-05-07 16:55:39 发布

weixin_33701564

最新推荐文章于 2020-05-07 16:55:39 发布

阅读量97

点赞数

文章标签：大数据 java python

原文链接：https://my.oschina.net/Xiao629/blog/300343

版权

2019独角兽企业重金招聘Python工程师标准>>>

原数据：

预想处理后的结果：

MyMapper.java

package com.xr.text;

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class MyMapper extends Mapper<LongWritable, Text, Text, Text> {

	protected void map(LongWritable key, Text value,Context context)
			throws IOException, InterruptedException {
		String[] split = value.toString().split(";");
		context.write(new Text(split[0]), new Text(split[1]));
	}
	
}

MyReducer.java

package com.xr.text;

import java.io.IOException;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;

public class MyReducer extends Reducer<Text, Text, Text, Text> {
	private MultipleOutputs mos;
	
	/**
	 * start before set MultipleOutputs;
	 */
	protected void setup(Context context) throws IOException,
			InterruptedException {
		mos = new MultipleOutputs(context);
	}

	protected void reduce(Text k1, Iterable<Text> value,Context context)
			throws IOException, InterruptedException {
		String key = k1.toString();
		for(Text t : value){
			if("中国".equals(key)){
				mos.write("china",new Text("中国"), t);
			}else if("美国".equals(key)){
				mos.write("usa",new Text("美国"),t);
			}else if("中国人".equals(key)){
				mos.write("cpeople",new Text("中国人"),t);
			}
		}
	}

	/**
	 * close MultipleOutputs;
	 */
	protected void cleanup(Context context)
			throws IOException, InterruptedException {
		mos.close();
	}
}

JobTest.java

package com.xr.text;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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;
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;




public class JobTest {
	
	public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
		String inputPath = "hdfs://192.168.75.100:9000/1.txt";
		String outputPath = "hdfs://192.168.75.100:9000/ceshi";
		Job job = new Job();
		job.setJarByClass(JobTest.class);
		job.setMapperClass(MyMapper.class);
		/**
		 * set MultipleOutput file name
		 */
		MultipleOutputs.addNamedOutput(job, "china", TextOutputFormat.class, Text.class, Text.class);
		MultipleOutputs.addNamedOutput(job, "usa", TextOutputFormat.class, Text.class, Text.class);
		MultipleOutputs.addNamedOutput(job, "cpeople", TextOutputFormat.class, Text.class, Text.class);
		
		job.setReducerClass(MyReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		
		FileInputFormat.setInputPaths(job, new Path(inputPath));
//		Configuration conf = new Configuration();
//		FileSystem fs = FileSystem.get(conf);
//		
//		if(fs.exists(new Path(outputPath))){
//			fs.delete(new Path(outputPath), true);
//		}
		FileOutputFormat.setOutputPath(job, new Path(outputPath));
		
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}

运行过程中报错：

14/08/12 12:44:02 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable

14/08/12 12:44:02 ERROR security.UserGroupInformation: PriviledgedActionException as:Xr cause:java.io.IOException: Failed to set permissions of path: \tmp\hadoop-Xr\mapred\staging\Xr-1514460710\.staging to 0700

Exception in thread "main" java.io.IOException: Failed to set permissions of path: \tmp\hadoop-Xr\mapred\staging\Xr-1514460710\.staging to 0700

at org.apache.hadoop.fs.FileUtil.checkReturnValue(FileUtil.java:689)

at org.apache.hadoop.fs.FileUtil.setPermission(FileUtil.java:662)

at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:509)

at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:344)

at org.apache.hadoop.fs.FilterFileSystem.mkdirs(FilterFileSystem.java:189)

at org.apache.hadoop.mapreduce.JobSubmissionFiles.getStagingDir(JobSubmissionFiles.java:116)

at org.apache.hadoop.mapred.JobClient$2.run(JobClient.java:918)

at org.apache.hadoop.mapred.JobClient$2.run(JobClient.java:912)

at java.security.AccessController.doPrivileged(Native Method)

at javax.security.auth.Subject.doAs(Subject.java:396)

at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1149)