MapReduce的Mapper端JOIN

package com.mengyao.hadoop.mapreduce;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Vector;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Counter;
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.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class MapJoinApp extends Configured implements Tool {

    static class MapJoinMapper extends Mapper<LongWritable, Text, Text, Text> {
        
        private Text k;
        private Text v;
        
        @Override
        protected void setup(
                Mapper<LongWritable, Text, Text, Text>.Context context)
                        throws IOException, InterruptedException {
            k = new Text();
            v = new Text();        
        }

        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            Counter errorLineCounter = context.getCounter("ErrorTotal", "errorLine");
            Counter notFindCounter = context.getCounter("ErrorTotal", "notFind");
            FileSplit inputSplit = (FileSplit) context.getInputSplit();
            String fileName = inputSplit.getPath().getName();
            String userAddressTable = "userAddressTable.txt";
            String userTable = "userTable.txt";
            if (fileName != null && !fileName.isEmpty()) {
                if (fileName.equals(userAddressTable)) {
                    String[] fields = value.toString().split("\t");
                    String addressId = fields[0];
                    String address = fields[1];
                    k.set(addressId);
                    v.set("ua@"+address);
                    context.write(k, v);
                    System.err.println(k.toString()+"\t"+v.toString());
                } else if(fileName.equals(userTable)) {
                    String[] fields = value.toString().split("\t");
                    String id = fields[0];
                    String name = fields[1];
                    String addressId = fields[2];
                    k.set(addressId);
                    v.set("u@"+id+"\t"+name);
                    System.err.println(k.toString()+"\t"+v.toString());
                    context.write(k, v);
                } else {
                    notFindCounter.increment(1L);
                }
            } else {
                errorLineCounter.increment(1L);
            }
        }
    }
    
    static class MapJoinReducer extends Reducer<Text, Text, NullWritable, Text> {
        @Override
        protected void reduce(Text key, Iterable<Text> value, Context context)
                throws IOException, InterruptedException {
            Vector<String> uArr = new Vector<String>();
            Vector<String> uaArr = new Vector<String>();
            for (Text text : value) {
                String item = text.toString();
                if (item.contains("ua@")) {
                    uaArr.add(item.split("ua@")[1]);
                }
                if (item.contains("u@")) {
                    uArr.add(item.split("u@")[1]);
                }
            }
            int i;
            for (i = 0; i < uArr.size(); i++) {
                for (String uaItem : uaArr) {
                    context.write(NullWritable.get(), new Text(uArr.get(i) +"\t"+ uaItem));
                }
            }
            
        }
    }

    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = getConf();
        
        conf.set("mapreduce.job.jvm.numtasks", "-1");        
        conf.set("mapreduce.map.speculative", "false");        
        conf.set("mapreduce.reduce.speculative", "false");    
        conf.set("mapreduce.map.maxattempts", "4");            
        conf.set("mapreduce.reduce.maxattempts", "4");        
        conf.set("mapreduce.map.skip.maxrecords", "0");    
        Job job = Job.getInstance(conf, MapJoinApp.class.getSimpleName());
        job.setJarByClass(MapJoinApp.class);
        
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        job.setMapperClass(MapJoinMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        
//        job.setCombinerClass(JoinReducer.class);
        
        job.setReducerClass(MapJoinReducer.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Text.class);
        
        return job.waitForCompletion(true)?0:1;
    }
    
    public static int createJob(String[] params){
        Configuration conf = new Configuration();
        int status = 1;
        try {
            status = ToolRunner.run(conf, new MapJoinApp(), params);
        } catch (Exception e) {
            e.printStackTrace();
            throw new RuntimeException(e);
        }
        
        return status;
    }
    
    public static void main(String[] args) {
        args = new String[2];
        args[0] = "/testdata/user*";
        args[1] = "/job/mapreduce/"+MapJoinApp.class.getSimpleName()+"_"+new SimpleDateFormat("yyyyMMddhhMMss").format(new Date());
        if (args.length != 2) {
            System.out.println("Usage: "+MapJoinApp.class.getSimpleName()+" <in> <out>");
            System.exit(2);
        } else {
            int status = createJob(args);
            System.exit(status);
        }
    }


}