Hadoop练习

将这两个文件中的内容进行合并整合，输出格式：
1001 date=20170710 name=apple num=2 price=5999 sum=59992
1002 date=20170710 name=xiaomi num=100 price=2999 sum=2999100
文件1：order.txt
1001 20170710 4 2
1002 20170710 3 100
1003 20170710 2 40
1004 20170711 2 23
1005 20170823 4 55
1006 20170824 3 20
1007 20170825 2 3
1008 20170826 4 23
1009 20170912 2 10
1010 20170913 2 2
1011 20170914 3 14
1012 20170915 3 18
文件二： product.txt
1 chuizi 3999
2 huawei 3999
3 xiaomi 2999
4 apple 5999

// Writable --- 序列化，反序列化
public class Item implements Writable{
	
	private int id;
	private String date = "";//String类型默认为null 在序列化时不能有null 所以给个空字符串
	private String pid = "";
	private String name = "";
	private int price;
	private int num;
	
	
	@Override
	public String toString() {
		return "Item [id=" + id + ", date=" + date + ", pid=" + pid + ", name=" + name + ", price=" + price + ", num="
				+ num + "]";
	}
	public int getId() {
		return id;
	}
	public void setId(int id) {
		this.id = id;
	}
	public String getDate() {
		return date;
	}
	public void setDate(String date) {
		this.date = date;
	}
	public String getPid() {
		return pid;
	}
	public void setPid(String pid) {
		this.pid = pid;
	}
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
	public int getPrice() {
		return price;
	}
	public void setPrice(int price) {
		this.price = price;
	}
	public int getNum() {
		return num;
	}
	public void setNum(int num) {
		this.num = num;
	}
	@Override
	public void readFields(DataInput in) throws IOException {
		this.id = in.readInt();
		this.date = in.readUTF();
		this.pid = in.readUTF();
		this.name = in.readUTF();
		this.price = in.readInt();
		this.num = in.readInt();		
	}
	@Override
	public void write(DataOutput out) throws IOException {
		out.writeInt(id);
		out.writeUTF(date);
		out.writeUTF(pid);
		out.writeUTF(name);
		out.writeInt(price);
		out.writeInt(num);		
	}
}

Map

public class JoinMapper extends Mapper<LongWritable, Text, Text, Item> {

	public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

		String line = value.toString();		
		String[] arr = line.split(" ");	
		Item it = new Item();		
		FileSplit fs = (FileSplit) context.getInputSplit();
		String fileName = fs.getPath().getName();
		
		if (fileName.startsWith("order")) {
			it.setId(Integer.parseInt(arr[0]));
			it.setDate(arr[1]);
			it.setPid(arr[2]);
			it.setNum(Integer.parseInt(arr[3]));
		} else {
			it.setPid(arr[0]);
			it.setName(arr[1]);
			it.setPrice(Integer.parseInt(arr[2]));
		}	
		context.write(new Text(it.getPid()), it);		
	}
}

Reduce

public class JoinReducer extends Reducer<Text, Item, Item, NullWritable> {

	public void reduce(Text _key, Iterable<Item> values, Context context) throws IOException, InterruptedException {
		//找到这个包含名字和价格的这个对象
		Item product = new Item();
		List<Item> its = new ArrayList<>();
		
		for (Item val : values) {
			if (val.getPrice() != 0) {
				product.setPid(val.getPid());
				product.setName(val.getName());
				product.setPrice(val.getPrice());
			} else {
				Item it = new Item();
				it.setId(val.getId());
				it.setDate(val.getDate());
				it.setPid(val.getPid());
				it.setNum(val.getNum());
				its.add(it);
			}
		}
		for (int i = 0; i < its.size(); i++) {
			Item it = its.get(i);
			it.setName(product.getName());
			it.setPrice(product.getPrice());	
			context.write(it, NullWritable.get());
		}
	}
}

Driver

public class JoinDriver {

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf, "JobName");
		job.setJarByClass(cn.tedu.join.JoinDriver.class);
		
		job.setMapperClass(JoinMapper.class);
		job.setReducerClass(JoinReducer.class);

		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Item.class);
		
		job.setOutputKeyClass(Item.class);
		job.setOutputValueClass(NullWritable.class);

		FileInputFormat.setInputPaths(job, new Path("hdfs://10.42.87.122:9000/mr"));
		FileOutputFormat.setOutputPath(job, new Path("hdfs://10.42.87.122:9000/joinresult"));

		if (!job.waitForCompletion(true))
			return;
	}
}