參考案例1的測試數據:
package com.testMr;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
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.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
public class LeftJoinDemo {
public static class LeftJoinMap extends Mapper<LongWritable, Text, Text, Text> {
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
String[] line = value.toString().split(" ");
String buyerName = line[0];
String receiverName = line[1];
String goods = line[2];
String price = line[3];
context.write(new Text(buyerName), new Text(buyerName + " " + receiverName + " " + goods + " " + price));
}
}
public static class LeftJoinReduce extends Reducer<Text, Text, Text, Text> {
@Override
protected void reduce(Text arg0, Iterable<Text> arg1, Reducer<Text, Text, Text, Text>.Context arg2)
throws IOException, InterruptedException {
Iterator it = arg1.iterator();
String[] arr;
int max = Integer.MIN_VALUE;
String maxGoodsName = "";
while (it.hasNext()) {
String line = it.next().toString();
arr = line.split(" ");
if (arr.length != 4) {
throw new RuntimeException("數組個數不是4個,這行的數據爲" + line.toString() + ", 大小爲:" + arr.length);
}
if (Integer.parseInt(arr[3]) > max) {
max = Integer.parseInt(arr[3]);
maxGoodsName = arr[2];
}
}
String m = Integer.toString(max);
arg2.write(new Text(arg0), new Text(m + " " + maxGoodsName));
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
System.out.println(args.length);
for (String str : args) {
System.out.println(str);
}
String input1 = args[0];
// String input2 = args[1];
String outputPath = args[1];
Job job = Job.getInstance();
job.setJobName("test");
job.setJarByClass(LeftJoinDemo.class);
FileInputFormat.addInputPath(job, new Path(input1));
// FileInputFormat.addInputPath(job, new Path(input2));
FileOutputFormat.setOutputPath(job, new Path(outputPath));
job.setMapperClass(LeftJoinMap.class);
job.setReducerClass(LeftJoinReduce.class);
job.setPartitionerClass(HashPartitioner.class);
job.setNumReduceTasks(1);
job.setOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}