Join關聯聯絡案例

一、封裝類：

public class Bean implements Writable {
    private String orderId;
    private String userId;
    private String name;
    private String age;
    private String userName;
    private String firstName;

    public Bean() {
    }

    public Bean(String orderId, String userId, String name, String age, String userName, String firstName) {
        this.orderId = orderId;
        this.userId = userId;
        this.name = name;
        this.age = age;
        this.userName = userName;
        this.firstName = firstName;
    }

    public String getOrderId() {
        return orderId;
    }

    public void setOrderId(String orderId) {
        this.orderId = orderId;
    }

    public String getUserId() {
        return userId;
    }

    public void setUserId(String userId) {
        this.userId = userId;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public String getAge() {
        return age;
    }

    public void setAge(String age) {
        this.age = age;
    }

    public String getUserName() {
        return userName;
    }

    public void setUserName(String userName) {
        this.userName = userName;
    }

    public String getFirstName() {
        return firstName;
    }

    public void setFirstName(String firstName) {
        this.firstName = firstName;
    }

    @Override
    public String toString() {
        return "orderId='" + orderId + '\'' +
                ", userId='" + userId + '\'' +
                ", name='" + name + '\'' +
                ", age='" + age + '\'' +
                ", userName='" + userName + '\'' +
                ", firstName='" + firstName + '\'' ;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(this.orderId);
        dataOutput.writeUTF(this.userId);
        dataOutput.writeUTF(this.name);
        dataOutput.writeUTF(this.age);
        dataOutput.writeUTF(this.userName);
        dataOutput.writeUTF(this.firstName);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.orderId = dataInput.readUTF();
        this.userId = dataInput.readUTF();
        this.name = dataInput.readUTF();
        this.age = dataInput.readUTF();
        this.userName = dataInput.readUTF();
        this.firstName = dataInput.readUTF();
    }
}
複製程式碼

二、Mapper類：

public class GoodsMapper extends Mapper<LongWritable,Text,Text,JoinBean> {

    private String fileName;
    JoinBean joinBean = new JoinBean();
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
         FileSplit split = (FileSplit) context.getInputSplit();
         fileName = split.getPath().getName();
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        String[] lien = value.toString().split(",");
        if (fileName.startsWith("order")){
            joinBean.setOrderId(lien[0]);
            joinBean.setUserId(lien[1]);
            joinBean.setAge("NULL");
            joinBean.setName("NULL");
            joinBean.setUserName("NULL");
            joinBean.setFistName("order");
        }
        if (fileName.startsWith("user")){
            joinBean.setOrderId("NULL");
            joinBean.setUserId(lien[0]);
            joinBean.setAge(lien[2]);
            joinBean.setName(lien[1]);
            joinBean.setUserName(lien[3]);
            joinBean.setFistName("user");
        }
        
        //以使用者名稱為key ，把資料進行分檔案組合成javabean，然後放入context中，shuffle會自動分割槽，排序map階段的資料。
        context.write(new Text(joinBean.getUserId()),joinBean);
    }
}
複製程式碼

三、Reducer類：

1.注意for迴圈迭代器Values的括號（引發錯誤：重複K，null）！

2.注意將BeanUtils.寫在if比較語句的裡面！簡便了bean.setOrderId(value.getOrderId());

3.注意遍歷連結串列裡的Bean時，context輸出的K，V要寫在for括號的裡面！

4.注意複製檔案BeanUtils.copyProperties(joinBean1,value);

public class GoodsReducer extends Reducer<Text,JoinBean,JoinBean,NullWritable> {

    @Override
    protected void reduce(Text key, Iterable<JoinBean> values, Context context) throws IOException, InterruptedException {

        //user類集合
        List<JoinBean> joinBeans = new ArrayList<>();
        //儲存orderid的物件
        JoinBean joinBean = new JoinBean();
        //區分物件是order還是user
        for (JoinBean value : values) {
            if (value.getFistName().equals("order")){
                joinBean.setOrderId(value.getOrderId());
                joinBean.setUserId(value.getUserId());
            }
            if (value.getFistName().equals("user")){
                JoinBean joinBean1 = new JoinBean();
                try {
                    BeanUtils.copyProperties(joinBean1,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
                joinBeans.add(joinBean1);
            }
        }

        for (JoinBean bean : joinBeans) {
            bean.setOrderId(joinBean.getOrderId());
            context.write(bean,NullWritable.get());
        }
    }
}
複製程式碼

四、測試類：

1.建立Configuration環境

2.建立Job新增conf環境

3.設定整個job所用的那些類在哪個Jar包

4.設定job使用的mapper和reducer的類

5.設定mapper的輸出資料KV型別

6.指定reducer的輸出資料KV型別

7.指定要處理的輸入資料存放路徑

8.指定要處理的輸出資料存放路徑

9.將job提交給叢集執行