需求:有如下文件,A的好友有B,C,D,F,E,O,查找出A和B的共同好友有哪些
A:B,C,D,F,E,O
B:A,C,E,K
C:F,A,D,I
D:A,E,F,L
E:B,C,D,M,L
F:A,B,C,D,E,O,M
G:A,C,D,E,F
H:A,C,D,E,O
I:A,O
J:B,O
K:A,C,D
L:D,E,F
M:E,F,G
O:A,H,I,J
1:定义Friends1Map类
package Friends;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class Friends1Map extends Mapper<LongWritable, Text, Text, Text> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] fields = line.split(":");
//person在前,friends在后,拿到person A:B,C,D,F,E,O
String person = fields[0];
//拿到friends
String[] friends = fields[1].split(",");
//重新拼接数据,friends在前,person在后
for(String friend : friends){
context.write(new Text(friend),new Text(person));
}
}
}
2:定义Friends1Reducer类
package Friends;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class Friends1Reducer extends Reducer<Text, Text, Text, Text>{
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
StringBuffer sb = new StringBuffer();
for (Text person : values){
sb.append(person).append(",");
}
context.write(key, new Text(sb.toString()));
}
}
3:定义了Friends1Driver类
package Friends;
import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;
public class Friends1Driver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
args = new String[]{"E:\\bigdata_code\\friends","E:\\bigdata_code\\friends\\out1"};
//1 获取job对象
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//2 指定jar包运行路径
job.setJarByClass(Friends1Driver.class);
//3 指定map类、map输出数据类型
job.setMapperClass(Friends1Map.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
//4 指定Reduce类、reduce输出数据类型
job.setReducerClass(Friends1Reducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
//5 指定job的输入输出目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//6 提交
boolean result = job.waitForCompletion(true);
System.exit(result ? 1:0);
}
}
输出结果:
--------------------------------------
4:定义Friends2Map 类
package Friends;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
import java.util.Arrays;
public class Friends2Map extends Mapper<LongWritable, Text, Text, Text> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] friend_persons = line.split("\t");
//拿到friend、person,A I,K,C,B,G,F,H,O,D,
String friend = friend_persons[0];
String[] persons = friend_persons[1].split(",");
Arrays.sort(persons);
for (int x = 0; x < persons.length -1; x++){
for(int y = x + 1; y < persons.length; y++){
context.write(new Text(persons[x] + "-" + persons[y]), new Text(friend));
}
}
}
}
5:定义了Friends2Reducer类
package Friends;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class Friends2Reducer extends Reducer< Text, Text, Text, Text> {
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
StringBuilder sb = new StringBuilder();
for (Text friend : values){
sb.append(friend).append(" ");
}
context.write(key, new Text(sb.toString()));
}
}
6:定义了Friends2Driver
package Friends;
import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;
public class Friends2Driver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
args = new String[]{"E:\\bigdata_code\\friends\\out1","E:\\bigdata_code\\friends\\out2"};
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(Friends2Driver.class);
job.setMapperClass(Friends2Map.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setReducerClass(Friends2Reducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job,new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
job.waitForCompletion(true);
}
}
输出结果:
package Friends;
import org.apache.hadoop.conf.Configuration;
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.jobcontrol.ControlledJob;
import org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class AllFriendsDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
args = new String[]{"E:\\bigdata_code\\friends",
"E:\\bigdata_code\\friends\\out1",
"E:\\bigdata_code\\friends\\out2"};
Configuration conf = new Configuration();
Job job1 = Job.getInstance(conf);
job1.setJarByClass(AllFriendsDriver.class);
job1.setMapperClass(Friends1Map.class);
job1.setMapOutputKeyClass(Text.class);
job1.setMapOutputValueClass(Text.class);
job1.setReducerClass(Friends1Reducer.class);
job1.setOutputKeyClass(Text.class);
job1.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job1, new Path(args[0]));
FileOutputFormat.setOutputPath(job1, new Path(args[1]));
Job job2 = Job.getInstance(conf);
job2.setMapperClass(Friends2Map.class);
job2.setMapOutputKeyClass(Text.class);
job2.setMapOutputValueClass(Text.class);
job2.setReducerClass(Friends2Reducer.class);
job2.setOutputKeyClass(Text.class);
job2.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job2, new Path(args[1]));
FileOutputFormat.setOutputPath(job2, new Path(args[2]));
JobControl control = new JobControl("zhang");
ControlledJob ajob = new ControlledJob(job1.getConfiguration());
ControlledJob bjob = new ControlledJob(job2.getConfiguration());
bjob.addDependingJob(ajob);
control.addJob(ajob);
control.addJob(bjob);
Thread thread = new Thread();
thread.start();
}
}
在将job1、job2串联起来时候,遇到问题,报了个警告就不往下走了,初步查找,觉得是环境问题,但是换了饱之后还是同样问题,暂时不知如何解决。希望有大神能帮助看看
2019-06-24 17:14:30,117 WARN [org.apache.hadoop.util.NativeCodeLoader] - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Process finished with exit code 0