MapReduce 两个表关联

package sitesh;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;


import java.io.IOException;
import java.util.ArrayList;

public class TwoJoin {
    public static class TowJoinMap extends Mapper<Object, Text, Text, Text> {
        @Override
        protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            if (line.contains("name") == true || line.contains("id") == true) {
                return;
            }
            String words[] = line.split(",");
            String flag = new String();
            if (words[0].length() == 1) {
                flag = "2";
                context.write(new Text(words[0]), new Text(flag + "|" + words[1]));
            } else if (words[0].length() > 1) {
                flag = "1";
                context.write(new Text(words[1]), new Text(flag + "|" + words[0]));
            }

        }
    }

    public static class TwoJoinReduce extends Reducer<Text, Text, Text, Text> {
        private int time = 0;

        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            if (0 == time) {
                context.write(new Text("name"), new Text("id"));
                time++;
            }
           /*int namenum = 0;
            String[] name = new String[10];
            int addresnum = 0;
            String[] addres = new String[10];

            for (Text value : values) {
                String[] str2 = value.toString().split("\\+");
                if (str2[0].compareTo("1") == 0) {
                    name[namenum] = str2[1];
                    namenum++;
                }
                if (str2[0].compareTo("2") == 0) {
                    addres[addresnum] = str2[1];
                    addresnum++;
                }

            }
            if (0 != namenum && 0 != addresnum) {
                for (int m = 0; m < namenum; m++) {
                    for (int n = 0; n < addresnum; n++) {
                        // 输出结果
                        context.write(new Text(name[m]), new Text(addres[n]));
                    }

                }

            }*/
//reduce两种形式
            ArrayList<String> left=new ArrayList<String>();
            ArrayList<String> right=new ArrayList<String>();
            for(Text v:values){
                if(v.toString().contains("1")){
                    left.add(v.toString().split("|")[1]);//city名
                }else{
                    right.add(v.toString().split("|")[1]);//工厂名
                }
            }
            for(int i=0;i<left.size();i++){//left 城市名
                for(int j=0;j<right.size();j++){  //right 工厂名
                    context.write(new Text(right.get(j)), new Text(left.get(i)));
                }     //工厂名+ city
            }
        }
    }


    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        //设置压缩格式
        conf.set("mapreduce.output.fileoutputformat.compress", "false");
       //设置内存
        conf.set("mapreduce.map.memory.mb", "2048");
        Job job = Job.getInstance(conf);
        job.setJarByClass(TwoJoin.class);

        job.setMapperClass(TowJoinMap.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        //
        job.setReducerClass(TwoJoinReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //
        Path inPath = new Path(args[0]);

        FileInputFormat.addInputPath(job, inPath);

        Path outPath = new Path(args[1]);
        FileSystem fs = FileSystem.get(conf);
        if (fs.exists(outPath)) {
            fs.delete(outPath, true);
        }
        FileOutputFormat.setOutputPath(job, outPath);
        job.waitForCompletion(true);
    }

}