下面给出一个child-parent的表格，要求挖掘其中的父子辈关系，给出祖孙辈关系的表格。

import java.io.IOException;

import java.util.ArrayList;

import java.util.List;

 

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.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

 

public class STJoin {

    public static int time = 0;

 

    public static class Map extends Mapper<Object, Text, Text, Text> {

        @Override

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

            String line = value.toString();

            String[] childAndParent = line.split(" ");

            List<String> list = new ArrayList<>(2);

            for (String childOrParent : childAndParent) {

                if (!"".equals(childOrParent)) {

                    list.add(childOrParent);

                }

            }

            if (!"child".equals(list.get(0))) {

                String childName = list.get(0);

                String parentName = list.get(1);

                String relationType = "1";

                context.write(new Text(parentName), new Text(relationType + "+"

                        + childName + "+" + parentName));

                relationType = "2";

                context.write(new Text(childName), new Text(relationType + "+"

                        + childName + "+" + parentName));

            }

        }

    }

 

    public static class Reduce extends Reducer<Text, Text, Text, Text> {

        @Override

        public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {

            if (time == 0) {

                context.write(new Text("grand_child"), new Text("grand_parent"));

                time++;

            }

            List<String> grandChild = new ArrayList<>();

            List<String> grandParent = new ArrayList<>();

            for (Text text : values) {

                String s = text.toString();

                String[] relation = s.split("\\+");

                String relationType = relation[0];

                String childName = relation[1];

                String parentName = relation[2];

                if ("1".equals(relationType)) {

                    grandChild.add(childName);

                } else {

                    grandParent.add(parentName);

                }

            }

            int grandParentNum = grandParent.size();

            int grandChildNum = grandChild.size();

            if (grandParentNum != 0 && grandChildNum != 0) {

                for (int m = 0; m < grandChildNum; m++) {

                    for (int n = 0; n < grandParentNum; n++) {

                        context.write(new Text(grandChild.get(m)), new Text(

                                grandParent.get(n)));

                    }

                }

            }

        }

    }

 

    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();

        conf.set("fs.defaultFS", "hdfs://localhost:9000");

        String[] otherArgs = new String[]{"input3", "output3"};

        if (otherArgs.length != 2) {

            System.err.println("Usage: Single Table Join <in> <out>");

            System.exit(2);

        }

        Job job = Job.getInstance(conf, "Single table Join ");

        job.setJarByClass(STJoin.class);

        job.setMapperClass(Map.class);

        job.setReducerClass(Reduce.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(Text.class);

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);

 

    }

 

}