mapreduce join操作

利用mapreduce做join操作：

在mapreduce中我们经常用到两张表合成一张的情况，这样的话就要用到join。
比如现在有两个表：
orders.txt：
1001,20170710,p0001,1
1002,20170710,p0001,3
1003,20170710,p0001,3
1004,20170710,p0002,1

products.txt：
p0001,xiaomi,001
p0002,chuizi,001

要利用字段p0001,p002将两张表合起来。形成最终的结果
p0001 xiaomi 7
p0002 chuizi 1

然后代码是：

package com.lmz;

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

import org.apache.commons.io.FileUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.v2.app.webapp.App;
import org.apache.hadoop.util.GenericOptionsParser;

public class Mymap {
    public static class joinMapper extends Mapper<LongWritable, Text, Text, Text> {

        private Text outKey = new Text();
        private Text outValue = new Text();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] split = line.split(",");
            FileSplit inputSplit = (FileSplit) context.getInputSplit();
            String name = inputSplit.getPath().getName();
            //System.out.println(name);
            //两个文件 在一个 mapper 中处理
            //通过文件名判断是那种数据
            if (name.contains("products")) {
                //取商品ID 作为 输出key 和 商品名称 作为 输出value，即 第0、1 的数据
                outKey.set(split[0]);
                outValue.set("product#" + split[1]);
                context.write(outKey, outValue);
            } else {
                //取商品ID 作为 输出key 和 购买数量 作为 输出value，即 第2、3 的数据
                outKey.set(split[2]);
                outValue.set("order#" + split[3]);
                context.write(outKey, outValue);
            }
        }
    }

    public static class joinReducer extends Reducer<Text, Text, Text, Text> {
        private Text outValue = new Text();

        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            //用来存放：商品ID、商品名称
            List<String> productsList = new ArrayList<String>();
            //用来存放：商品ID、购买数量
            List<Integer> ordersList = new ArrayList<Integer>();
            for (Text text : values) {
                String value = text.toString();
                if (value.contains("product#")) {
                    productsList.add(value.split("#")[1]);

                } else if (value.contains("order#")) {
                    ordersList.add(Integer.parseInt(text.toString().split("#")[1].trim()));

                }
            }

            int to = 0;
            for (int i = 0; i < productsList.size(); i++) {
                //System.out.println(productsList.size());

                for (int j = 0; j < ordersList.size(); j++) {
                    //System.out.println(ordersList.size());
                    to += ordersList.get(j);
                    //System.out.println(to);
                }
                outValue.set(productsList.get(i) + "\t" + to);
                context.write(key,new Text(outValue));
                //最后的输出是：商品ID、商品名称、购买数量

            }
            //System.out.println(outValue);


        }

        //System.out.println(ordersList);
        //int totalOrders = 0;

    }


    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        //conf.set("fs.defaultFS", "file:///");
        File file1 = new File("E:\\data1\\out");
        //Path path = new Path("E:\\data1\\out");
        //FileSystem fileSystem = path.getFileSystem(conf);
        if (file1.exists()) {
            FileUtils.deleteDirectory(file1);
        }
        Job job = Job.getInstance(conf);
        //设置job的各种属性
        //作业名称
        job.setJarByClass(Mymap.class);                 //搜索类
        job.setInputFormatClass(TextInputFormat.class); //设置输入格式

        job.setMapperClass(joinMapper.class);
        job.setReducerClass(joinReducer.class);
        //添加输入路径
        FileInputFormat.setInputPaths(job, new Path("E:\\data1"));
        ;
        //设置输出路径
        FileOutputFormat.setOutputPath(job, new Path("E:\\data1\\out"));
        //map输出类型
        job.setOutputKeyClass(Text.class);           //
        job.setOutputValueClass(Text.class);        //
        job.waitForCompletion(true);
        Boolean b = job.waitForCompletion(true);
        System.out.println(b ? 0 : 1);
    }
}

这个 代码是最简单的join操作。希望可以帮到大家。