Streaming ETL from MySQL and Postgres to Elasticsearch（中文）

1. 下载 docker-compose.yml

version: '2.1'
services:
  postgres:
    image: debezium/example-postgres:1.1
    ports:
      - "5432:5432"
    environment:
      - POSTGRES_PASSWORD=1234
      - POSTGRES_DB=postgres
      - POSTGRES_USER=postgres
      - POSTGRES_PASSWORD=postgres
  mysql:
    image: debezium/example-mysql:1.1
    ports:
      - "3306:3306"
    environment:
      - MYSQL_ROOT_PASSWORD=123456
      - MYSQL_USER=mysqluser
      - MYSQL_PASSWORD=mysqlpw
  elasticsearch:
    image: elastic/elasticsearch:7.6.0
    environment:
      - cluster.name=docker-cluster
      - bootstrap.memory_lock=true
      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
      - discovery.type=single-node
    ports:
      - "9200:9200"
      - "9300:9300"
    ulimits:
      memlock:
        soft: -1
        hard: -1
      nofile:
        soft: 65536
        hard: 65536
  kibana:
    image: elastic/kibana:7.6.0
    ports:
      - "5601:5601"
  zookeeper:
    image: wurstmeister/zookeeper:3.4.6
    ports:
      - "2181:2181"
  kafka:
    image: wurstmeister/kafka:2.12-2.2.1
    ports:
      - "9092:9092"
      - "9094:9094"
    depends_on:
      - zookeeper
    environment:
      - KAFKA_ADVERTISED_LISTENERS=INSIDE://:9094,OUTSIDE://localhost:9092
      - KAFKA_LISTENERS=INSIDE://:9094,OUTSIDE://:9092
      - KAFKA_LISTENER_SECURITY_PROTOCOL_MAP=INSIDE:PLAINTEXT,OUTSIDE:PLAINTEXT
      - KAFKA_INTER_BROKER_LISTENER_NAME=INSIDE
      - KAFKA_ZOOKEEPER_CONNECT=zookeeper:2181
      - KAFKA_CREATE_TOPICS="user_behavior:1:1"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock

1. 进入 mysql 容器，初始化数据：

docker-compose exec mysql mysql -uroot -p123456

-- MySQL
CREATE DATABASE mydb;
USE mydb;
CREATE TABLE products (
  id INTEGER NOT NULL AUTO_INCREMENT PRIMARY KEY,
  name VARCHAR(255) NOT NULL,
  description VARCHAR(512)
);
ALTER TABLE products AUTO_INCREMENT = 101;

INSERT INTO products
VALUES (default,"scooter","Small 2-wheel scooter"),
       (default,"car battery","12V car battery"),
       (default,"12-pack drill bits","12-pack of drill bits with sizes ranging from #40 to #3"),
       (default,"hammer","12oz carpenter's hammer"),
       (default,"hammer","14oz carpenter's hammer"),
       (default,"hammer","16oz carpenter's hammer"),
       (default,"rocks","box of assorted rocks"),
       (default,"jacket","water resistent black wind breaker"),
       (default,"spare tire","24 inch spare tire");

CREATE TABLE orders (
  order_id INTEGER NOT NULL AUTO_INCREMENT PRIMARY KEY,
  order_date DATETIME NOT NULL,
  customer_name VARCHAR(255) NOT NULL,
  price DECIMAL(10, 5) NOT NULL,
  product_id INTEGER NOT NULL,
  order_status BOOLEAN NOT NULL -- 是否下单
) AUTO_INCREMENT = 10001;

INSERT INTO orders
VALUES (default, '2020-07-30 10:08:22', 'Jark', 50.50, 102, false),
       (default, '2020-07-30 10:11:09', 'Sally', 15.00, 105, false),
       (default, '2020-07-30 12:00:30', 'Edward', 25.25, 106, false);

1. 进入postgres 容器，初始化数据：

docker-compose exec postgres psql -h localhost -U postgres

-- PG
CREATE TABLE shipments (
  shipment_id SERIAL NOT NULL PRIMARY KEY,
  order_id SERIAL NOT NULL,
  origin VARCHAR(255) NOT NULL,
  destination VARCHAR(255) NOT NULL,
  is_arrived BOOLEAN NOT NULL
);
ALTER SEQUENCE public.shipments_shipment_id_seq RESTART WITH 1001;
ALTER TABLE public.shipments REPLICA IDENTITY FULL;

INSERT INTO shipments
VALUES (default,10001,'Beijing','Shanghai',false),
       (default,10002,'Hangzhou','Shanghai',false),
       (default,10003,'Shanghai','Hangzhou',false);

1. 下载以下 jar 包到 <FLINK_HOME>/lib/:

• flink-sql-connector-elasticsearch7_2.11-1.13.2.jar

• flink-sql-connector-mysql-cdc-2.0.2.jar

• flink-sql-connector-postgres-cdc-2.0.2.jar

1. 然后启动 Flink 集群，再启动 SQL CLI.

--Flink SQL
-- 设置 checkpoint 间隔为 3 秒                     
Flink SQL> SET execution.checkpointing.interval = 3s;
Flink SQL> CREATE TABLE products (
   id INT,
   name STRING,
   description STRING,
   PRIMARY KEY (id) NOT ENFORCED
 ) WITH (
   'connector' = 'mysql-cdc',
   'hostname' = 'localhost',
   'port' = '3306',
   'username' = 'root',
   'password' = '123456',
   'database-name' = 'mydb',
   'table-name' = 'products'
 );

Flink SQL> CREATE TABLE orders (
   order_id INT,
   order_date TIMESTAMP(0),
   customer_name STRING,
   price DECIMAL(10, 5),
   product_id INT,
   order_status BOOLEAN,
   PRIMARY KEY (order_id) NOT ENFORCED
 ) WITH (
   'connector' = 'mysql-cdc',
   'hostname' = 'localhost',
   'port' = '3306',
   'username' = 'root',
   'password' = '123456',
   'database-name' = 'mydb',
   'table-name' = 'orders'
 );

Flink SQL> CREATE TABLE shipments (
   shipment_id INT,
   order_id INT,
   origin STRING,
   destination STRING,
   is_arrived BOOLEAN,
   PRIMARY KEY (shipment_id) NOT ENFORCED
 ) WITH (
   'connector' = 'postgres-cdc',
   'hostname' = 'localhost',
   'port' = '5432',
   'username' = 'postgres',
   'password' = 'postgres',
   'database-name' = 'postgres',
   'schema-name' = 'public',
   'table-name' = 'shipments'
 );

Flink SQL> CREATE TABLE enriched_orders (
   order_id INT,
   order_date TIMESTAMP(0),
   customer_name STRING,
   price DECIMAL(10, 5),
   product_id INT,
   order_status BOOLEAN,
   product_name STRING,
   product_description STRING,
   shipment_id INT,
   origin STRING,
   destination STRING,
   is_arrived BOOLEAN,
   PRIMARY KEY (order_id) NOT ENFORCED
 ) WITH (
     'connector' = 'elasticsearch-7',
     'hosts' = 'http://localhost:9200',
     'index' = 'enriched_orders'
 );

Flink SQL> INSERT INTO enriched_orders
 SELECT o.*, p.name, p.description, s.shipment_id, s.origin, s.destination, s.is_arrived
 FROM orders AS o
 LEFT JOIN products AS p ON o.product_id = p.id
 LEFT JOIN shipments AS s ON o.order_id = s.order_id;

1. 修改 mysql 和 postgres 里面的数据，观察 elasticsearch 里的结果。

--MySQL
INSERT INTO orders
VALUES (default, '2020-07-30 15:22:00', 'Jark', 29.71, 104, false);

--PG
INSERT INTO shipments
VALUES (default,10004,'Shanghai','Beijing',false);

--MySQL
UPDATE orders SET order_status = true WHERE order_id = 10004;

--PG
UPDATE shipments SET is_arrived = true WHERE shipment_id = 1004;

--MySQL
DELETE FROM orders WHERE order_id = 10004;

1. Kafka changelog json format

在 SQL CLI 中：

--Flink SQL
Flink SQL> CREATE TABLE kafka_gmv (
   day_str STRING,
   gmv DECIMAL(10, 5)
 ) WITH (
     'connector' = 'kafka',
     'topic' = 'kafka_gmv',
     'scan.startup.mode' = 'earliest-offset',
     'properties.bootstrap.servers' = 'localhost:9092',
     'format' = 'changelog-json'
 );

Flink SQL> INSERT INTO kafka_gmv
 SELECT DATE_FORMAT(order_date, 'yyyy-MM-dd') as day_str, SUM(price) as gmv
 FROM orders
 WHERE order_status = true
 GROUP BY DATE_FORMAT(order_date, 'yyyy-MM-dd');

-- 读取 Kafka 的 changelog 数据，观察 materialize 后的结果
Flink SQL> SELECT * FROM kafka_gmv;

观察 kafka 的输出：

docker-compose exec kafka bash -c 'kafka-console-consumer.sh --topic kafka_gmv --bootstrap-server kafka:9094 --from-beginning'

更新 orders 数据，观察SQL CLI 和 kafka console 的输出

-- MySQL
UPDATE orders SET order_status = true WHERE order_id = 10001;
UPDATE orders SET order_status = true WHERE order_id = 10002;
UPDATE orders SET order_status = true WHERE order_id = 10003;

INSERT INTO orders
VALUES (default, '2020-07-30 17:33:00', 'Timo', 50.00, 104, true);

UPDATE orders SET price = 40.00 WHERE order_id = 10005;

DELETE FROM orders WHERE order_id = 10005;