linux要求挖掘父子辈关系,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。...

package org.apache.hadoop.examples;

import java.util.HashMap;

import java.io.IOException;

import java.util.ArrayList;

import java.util.Iterator;

import java.util.List;

import java.util.Map;

import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

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.output.FileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

public class C_findParents {

public static Integer numsum = new Integer(0);

public static Map> levelmap=new HashMap>();

public C_findParents() {

}

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

Configuration conf = new Configuration();

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

String[] otherArgs = new String[]{"input","output"};

if(otherArgs.length < 2) {

System.err.println("Usage: wordcount [...] ");

System.exit(2);

}

Job job = Job.getInstance(conf, "sort");

job.setJarByClass(C_findParents.class);

job.setMapperClass(C_findParents.TokenizerMapper.class);

job.setMapOutputKeyClass(Text.class);

job.setMapOutputValueClass(Text.class);

job.setReducerClass(C_findParents.IntSumReducer.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(Text.class);

for(int i = 0; i < otherArgs.length - 1; ++i) {

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

}

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

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

}

public static class IntSumReducer extends Reducer {

protected void reduce(Text key, Iterable values, Reducer.Context context)

throws IOException, InterruptedException {

List yeyelist = new ArrayList();

List children = new ArrayList();

for(Text val:values){

if(val.toString().endsWith("_1")){

yeyelist.add(val.toString());

}else if(val.toString().endsWith("_2")){

children.add(val.toString());

}

}

for(String child:children){

for(String yeye:yeyelist){

context.write(new Text(child.substring(0, child.length()-2)), new Text(yeye.substring(0, yeye.length()-2)));

}

}

}

}

public static class TokenizerMapper extends Mapper {

public TokenizerMapper() {

}

protected void map(LongWritable key, Text value, Mapper.Context context)

throws IOException, InterruptedException {

String line = value.toString();

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

context.write(new Text(values[0]), new Text(values[1]+"_1"));

context.write(new Text(values[1]), new Text(values[0]+"_2"));

}

}

}