package com.testMr;
import java.io.IOException;
import java.util.ArrayList;
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 JoinDemo {
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[] arr = value.toString().split(" ");
FileSplit file = (FileSplit) context.getInputSplit();
String path = file.getPath().toString();
String stuID;
if (path.contains("student.txt")) {
stuID = arr[2];
context.write(new Text(stuID), new Text(value.toString() + " " + "a"));
} else {
stuID = arr[1];
context.write(new Text(stuID), new Text(value.toString() + " " + "b"));
}
}
}
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 {
List<String> a = new ArrayList<String>();
List<String> b = new ArrayList<String>();
// String[] arr;
String arr[] = new String[] {};
for (Text t : arg1) {
arr = t.toString().split(" ");
// arg2.write(new Text(t.toString()), new Text(""));
if (arr[arr.length - 1].equals("a")) {
a.add(t.toString());
} else {
b.add(t.toString());
}
}
if (a.size() != 0 && b.size() != 0) {
int sum = 0;
String arr1[] = new String[] {};
// List<String> list = new ArrayList<String>();
for (String str_a : a) {
arr = str_a.split(" ");
for (String str_b : b) {
arr1 = str_b.split(" ");
int i = Integer.parseInt(arr1[3]);
if (i>75) {
int s = Integer.parseInt(arr1[3]);
sum = sum + s;
// list.add(arr[1] + " " + arr1[3]);
}
}
// for(String c :list){
// arg2.write(new Text(arr[2]),new Text( c+" "+sum));
// }
}
arg2.write(new Text(arr[2]), new Text(arr[1] + " " + sum));
}
}
}
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[2];
Job job = Job.getInstance();
job.setJobName("test");
job.setJarByClass(JoinDemo.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);
}
}
Inner join --案例
最新推荐文章于 2024-05-07 15:05:54 发布