数据
https://www.jianshu.com/p/cb1914c1aaf5
通过将关联条件作为map输出的key，将两表满足join条件的数据并携带数据所来源的文件信息，发往同一个reduce task，在reduce中进行数据的串联。
1、创建商品和订合并后的bean类
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
public class TableBean implements Writable {
private String order_id; // 订单id
private String p_id; // 产品id
private int amount; // 产品数量
private String pname; // 产品名称
private String flag;// 表的标记
public TableBean() {
super();
}
public TableBean(String order_id, String p_id, int amount, String pname, String flag) {
super();
this.order_id = order_id;
this.p_id = p_id;
this.amount = amount;
this.pname = pname;
this.flag = flag;
}
public String getFlag() {
return flag;
}
public void setFlag(String flag) {
this.flag = flag;
}
public String getOrder_id() {
return order_id;
}
public void setOrder_id(String order_id) {
this.order_id = order_id;
}
public String getP_id() {
return p_id;
}
public void setP_id(String p_id) {
this.p_id = p_id;
}
public int getAmount() {
return amount;
}
public void setAmount(int amount) {
this.amount = amount;
}
public String getPname() {
return pname;
}
public void setPname(String pname) {
this.pname = pname;
}
@Override
public void write(DataOutput out) throws IOException {
out.writeUTF(order_id);
out.writeUTF(p_id);
out.writeInt(amount);
out.writeUTF(pname);
out.writeUTF(flag);
}
@Override
public void readFields(DataInput in) throws IOException {
this.order_id = in.readUTF();
this.p_id = in.readUTF();
this.amount = in.readInt();
this.pname = in.readUTF();
this.flag = in.readUTF();
}
@Override
public String toString() {
return order_id + "\t" + pname + "\t" + amount + "\t" ;
}
}
2、编写TableMapper程序
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
public class TableMapper extends Mapper{
TableBean bean = new TableBean();
Text k = new Text();
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
// 1 获取输入文件类型
FileSplit split = (FileSplit) context.getInputSplit();
String name = split.getPath().getName();
// 2 获取输入数据
String line = value.toString();
// 3 不同文件分别处理
if (name.startsWith("order")) {// 订单表处理
// 3.1 切割
String[] fields = line.split(",");
// 3.2 封装bean对象
bean.setOrder_id(fields[0]);
bean.setP_id(fields[1]);
bean.setAmount(Integer.parseInt(fields[2]));
bean.setPname("");
bean.setFlag("0");
k.set(fields[1]);
}else {// 产品表处理
// 3.3 切割
String[] fields = line.split(",");
// 3.4 封装bean对象
bean.setP_id(fields[0]);
bean.setPname(fields[1]);
bean.setFlag("1");
bean.setAmount(0);
bean.setOrder_id("");
k.set(fields[0]);
}
// 4 写出
context.write(k, bean);
}
}
3、编写TableReducer程序
import java.io.IOException;
import java.util.ArrayList;
import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class TableReducer extends Reducer {
@Override
protected void reduce(Text key, Iterable values, Context context)
throws IOException, InterruptedException {
// 1准备存储订单的集合
ArrayList orderBeans = new ArrayList<>();
// 2 准备bean对象
TableBean pdBean = new TableBean();
for (TableBean bean : values) {
if ("0".equals(bean.getFlag())) {// 订单表
// 拷贝传递过来的每条订单数据到集合中
TableBean orderBean = new TableBean();`
try {
BeanUtils.copyProperties(orderBean, bean);
} catch (Exception e) {
e.printStackTrace();
}
orderBeans.add(orderBean);
} else {// 产品表
try {
// 拷贝传递过来的产品表到内存中
BeanUtils.copyProperties(pdBean, bean);
} catch (Exception e) {
e.printStackTrace();
}
}
}
// 3 表的拼接
for(TableBean bean:orderBeans){
bean.getPname(pdBean.getPname());
// 4 数据写出去
context.write(bean, NullWritable.get());
}
}
}
4、编写TableDriver程序
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class TableDriver {
public static void main(String[] args) throws Exception {
// 1 获取配置信息，或者job对象实例
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 2 指定本程序的jar包所在的本地路径
job.setJarByClass(TableDriver.class);
// 3 指定本业务job要使用的mapper/Reducer业务类
job.setMapperClass(TableMapper.class);
job.setReducerClass(TableReducer.class);
// 4 指定mapper输出数据的kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(TableBean.class);
// 5 指定最终输出的数据的kv类型
job.setOutputKeyClass(TableBean.class);
job.setOutputValueClass(NullWritable.class);
// 6 指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
5、运行程序查看结果
1001 小米 1
1001 小米 1
1002 华为 2
1002 华为 2
1003 格力 3
1003 格力 3
缺点：这种方式中，合并的操作是在reduce阶段完成，reduce端的处理压力太大，map节点的运算负载则很低，资源利用率不高，且在reduce阶段极易产生数据倾斜
解决方案： map端实现数据合并
6、Code -> GitHub
https://github.com/liufengji/hadoop_mapreduce.git