maxtempmapper.java Klasse:Lauf MR-Programm mit separaten Mapper, Druckminderer und Treiberklassen
package com.hadoop.gskCodeBase.maxTemp;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class MaxTempMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
private static final int MISSING=9999;
@Override
public void map(LongWritable kay,Text value,Context context) throws IOException,InterruptedException {
String line = value.toString();
String year = line.substring(15,19);
int airTemperature;
if(line.charAt(87)== '+'){
airTemperature=Integer.parseInt(line.substring(88, 92));
}else{
airTemperature=Integer.parseInt(line.substring(87, 92));
}
String quality=line.substring(92,93);
if(airTemperature !=MISSING && quality.matches("[01459]")){
context.write(new Text(year), new IntWritable(airTemperature));
}
}
}
maxtempreducer.java Klasse:
package com.hadoop.gskCodeBase.maxTemp;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class MaxTempReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
@Override
public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException {
int maxValue = Integer.MIN_VALUE;
for(IntWritable value : values){
maxValue=Math.max(maxValue, value.get());
}
context.write(key, new IntWritable(maxValue));
}
}
maxtempdriver.java Klasse:
package com.hadoop.gskCodeBase.maxTemp;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class MaxTempDriver extends Configured implements Tool{
public int run(String[] args) throws Exception{
if(args.length !=2){
System.err.println("UsageTemperatureDriver <input path> <outputpath>");
System.exit(-1);
}
Job job = Job.getInstance();
job.setJarByClass(MaxTempDriver.class);
job.setJobName("Max Temperature");
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
job.setMapperClass(MaxTempMapper.class);
job.setReducerClass(MaxTempReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
System.exit(job.waitForCompletion(true) ? 0:1);
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;
}
public static void main(String[] args) throws Exception {
MaxTempDriver driver = new MaxTempDriver();
int exitCode = ToolRunner.run(driver, args);
System.exit(exitCode);
}
}
Ich muss die oben genannten drei Klassen auf einzelnen Knoten Hadoop Cluster auf Windows mit der Eingabeaufforderungausführenkann mir bitte jemand helfen, wie man diese drei Klassen an der Eingabeaufforderung (Windows) ausführt?
Also welchen Klassennamen sollte ich in der job.setJarByClass() angeben? Kannst du auch erklären, wie ich alle Java Mapper, Reducer und Treiber in einem Jar mit eclipse archiviere? @mfmz –
Ich habe die Antwort aktualisiert. – mfmz