[MapReduce编程案例4-join模型的mr实现]

1.问题：完成订单表和用户表之间的join

Map阶段map方法中的context参数保存了map负责的切片信息(哪个文件，多少偏移量，读取多长)，可通过context.getInputSplit()获取InputSplit类对象，InputSplit为 抽象类，需要强转。

2.设置一个joinBean类

public class JoinBean implements Writable{

	private String oid;
	private String uid;
	private String name;
	private int age;
	private String gender;
	private String friend;
	public JoinBean() {
		
	}
	public void set(String oid, String uid, String name, int age, String gender, String friend) {
		this.oid = oid;
		this.uid = uid;
		this.name = name;
		this.age = age;
		this.gender = gender;
		this.friend = friend;
	}
	public String getOid() {
		return oid;
	}
	public void setOid(String oid) {
		this.oid = oid;
	}
	public String getUid() {
		return uid;
	}
	public void setUid(String uid) {
		this.uid = uid;
	}
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
	public int getAge() {
		return age;
	}
	public void setAge(int age) {
		this.age = age;
	}
	public String getGender() {
		return gender;
	}
	public void setGender(String gender) {
		this.gender = gender;
	}
	public String getFriend() {
		return friend;
	}
	public void setFriend(String friend) {
		this.friend = friend;
	}
	@Override
	public String toString() {
		return "[oid=" + oid + ", uid=" + uid + ", name=" + name + ", age=" + age + ", gender=" + gender
				+ ", friend=" + friend + "]";
	}
	public void readFields(DataInput in) throws IOException {
		this.oid = in.readUTF();
		this.uid = in.readUTF();
		this.name = in.readUTF();
		this.age = in.readInt();
		this.gender = in.readUTF();
		this.friend = in.readUTF();
	}
	public void write(DataOutput out) throws IOException {
		out.writeUTF(oid);
		out.writeUTF(uid);
		out.writeUTF(name);
		out.writeInt(age);
		out.writeUTF(gender);
		out.writeUTF(friend);
	}
}

3.Mapper中如何获取文件信息

public static class JoinMapper extends Mapper<LongWritable, Text, Text, JoinBean>{
		protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,Text,JoinBean>.Context context) 
				throws java.io.IOException ,InterruptedException {
			//获取任务切片信息
			FileSplit inputSplit = (FileSplit) context.getInputSplit();
			//从任务切片信息中获取文件路径
			String fileName = inputSplit.getPath().getName();
			
			String[] split = value.toString().split(",");
			JoinBean joinBean = new JoinBean();
			
			//来自user.txt的数据,不存在的字段设置为"NULL"
			if(fileName.equals("user.txt")){
				joinBean.set("NULL", split[0], split[1], Integer.parseInt(split[2]), split[3], split[4]);
			}else{
				joinBean.set(split[0],split[1],"NULL",0,"NULL","NULL");
			}
			//key:uid
			context.write(new Text(joinBean.getUid()), joinBean);
		}
	}
	
	

4.Reducer类

public static class JoinReducer extends Reducer<Text, JoinBean, JoinBean, NullWritable>{
		@Override
		protected void reduce(Text key, Iterable<JoinBean> values,
				Reducer<Text, JoinBean, JoinBean, NullWritable>.Context context) throws IOException, InterruptedException {
			ArrayList<JoinBean> orderList = new ArrayList<JoinBean>();
			JoinBean userBean  = new JoinBean();
			
			for (JoinBean v : values) {
				//如果这条数据是user.txt
				if(v.getOid().equals("NULL")){
					try {
						BeanUtils.copyProperties(userBean, v);
					} catch (Exception e) {
						e.printStackTrace();
					}
				}else{
					//如果这条数据是订单数据
					JoinBean newBean = new JoinBean();
					try {
						BeanUtils.copyProperties(newBean, v);
						orderList.add(newBean);
					} catch (Exception e) {
						e.printStackTrace();
					}
				}
			}
			//拼接数据：
			for (JoinBean joinBean : orderList) {
				joinBean.setName(userBean.getName());
				joinBean.setAge(userBean.getAge());
				joinBean.setGender(userBean.getGender());
				joinBean.setFriend(userBean.getFriend());
				
				context.write(joinBean, NullWritable.get());
				//
			}
		}
	}