阅读背景:

自定义输出文件名

来源:互联网 

<p>package selfname;</p>
	import java.io.IOException;

	import org.apache.hadoop.conf.Configuration;
	import org.apache.hadoop.fs.Path;
	import org.apache.hadoop.io.Text;
	//import org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat;
	//import org.apache.hadoop.mapreduce.lib.input.MultipleTextOutputFormat;
	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.output.FileOutputFormat;
	import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;

	public class Selfname {
	        public static class FileMap extends Mapper<Object,Text,Text,Text>{
	        	public void map(Object key,Text value,Context context) throws IOException, InterruptedException{
	        		String line = value.toString();
	        		if(line.length()>=93){
	        		String keys = line.substring(15, 19);
	        		String values = line.substring(87,93);
	        		context.write(new Text(keys), new Text(values));
	        		}
	        	}
	        }
	        public static class FileReduce extends Reducer<Text,Text,Text,Text>{
	        	<strong>private MultipleOutputs<Text, Text> multipleOutputs;
	        	protected void setup(Context context)throws IOException, InterruptedException {
	        		multipleOutputs = new MultipleOutputs<Text, Text>(context);
	        		}</strong>
	        	public void reduce(Text key,Iterable<Text>values,Context context) throws IOException, InterruptedException{
	        		String value = new String();
	        		for(Text val:values){
	        			value+=val.toString()+",";
	        		}
	        		<strong>multipleOutputs.write(key, new Text(value), key.toString());</strong>

	        	}
	        	<strong>protected void cleanup(Context context)throws IOException, InterruptedException {
	        		multipleOutputs.close();
	        		}</strong>
	        }
	        public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
	        	Configuration conf = new Configuration();
	        	Job job = new Job(conf,"myfile");
	        	job.setJarByClass(Selfname.class);
	        	job.setMapperClass(FileMap.class);
	        	job.setReducerClass(FileReduce.class);
	        	job.setOutputKeyClass(Text.class);
	        	job.setOutputValueClass(Text.class);
	        	job.setNumReduceTasks(1);
	        	FileInputFormat.addInputPath(job, new Path(args[0]));
	        	FileOutputFormat.setOutputPath(job, new Path(args[1]));
	        	System.exit(job.waitForCompletion(true)?0:1);
	        	
	        }
	}
<p>package selfname;</p>
	import java.io.IOExcepti




你的当前访问异常,请进行认证后继续阅读剩余内容。

分享到: