使用FlinkSql实现热门商品TOP N

使用FlinkSql实现热门商品TOP N

目前仅 Blink 计划器支持 Top-N 。

Flink 使用OVER 窗口条件和过滤条件相结合以进行 Top-N 查询。利用 OVER 窗口的 PARTITION BY 子句的功能，Flink 还支持逐组 Top-N 。 例如，每个类别中实时销量最高的前五种产品。批处理表和流处理表都支持基于SQL的 Top-N 查询。

流处理模式需注意: TopN 查询的结果会带有更新。 Flink SQL 会根据排序键对输入的流进行排序；若 top N 的记录发生了变化，变化的部分会以撤销、更新记录的形式发送到下游。 推荐使用一个支持更新的存储作为 Top-N 查询的 sink。另外，若 top N 记录需要存储到外部存储，则结果表需要拥有与 Top-N 查询相同的唯一键。

1. 需求描述

每隔10min 统计最近 1hour的热门商品 top3, 并把统计的结果写入到mysql中

思路:

1. 统计每个商品的点击量, 开窗
2. 分组窗口分组,
3. over窗口

2. 在mysql中创建表

CREATE DATABASE flink_sql;
USE flink_sql;
DROP TABLE IF EXISTS `hot_item`;
CREATE TABLE `hot_item` (
  `w_end` timestamp NOT NULL,
  `item_id` bigint(20) NOT NULL,
  `item_count` bigint(20) NOT NULL,
  `rk` bigint(20) NOT NULL,
  PRIMARY KEY (`w_end`,`rk`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

3. 导入JDBC Connector依赖

 <properties>
        <flink.version>1.12.0</flink.version>
        <scala.binary.version>2.11</scala.binary.version>
        <slf4j.version>1.7.30</slf4j.version>
 </properties>

<dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
            <!--在idea下运行的时候, 依赖会参与, 打包的不会达到依赖中-->
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.49</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner-blink_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-csv</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-json</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-jdbc_2.11</artifactId>
            <version>1.12.0</version>
        </dependency>
    </dependencies>

4. 具体实现代码

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;

public class Flink01_HotItem_TopN {
    public static void main(String[] args) {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(2);
        StreamTableEnvironment tenv = StreamTableEnvironment.create(env);


        // 使用sql从文件读取数据
        tenv.executeSql(
            "create table user_behavior(" +
                "   user_id bigint, " +
                "   item_id bigint, " +
                "   category_id int, " +
                "   behavior string, " +
                "   ts bigint, " +
                "   event_time as to_timestamp(from_unixtime(ts, 'yyyy-MM-dd HH:mm:ss')), " +
                "   watermark for event_time as  event_time - interval '5' second " +
                ")with(" +
                "   'connector'='filesystem', " +
                "   'path'='input/UserBehavior.csv', " +
                "   'format'='csv')"
        );

        // 每隔 10m 统计一次最近 1h 的热门商品 top

        // 1. 计算每每个窗口内每个商品的点击量
        Table t1 = tenv
            .sqlQuery(
                "select " +
                    "   item_id, " +
                    "   hop_end(event_time, interval '10' minute, interval '1' hour) w_end," +
                    "   count(*) item_count " +
                    "from user_behavior " +
                    "where behavior='pv' " +
                    "group by hop(event_time, interval '10' minute, interval '1' hour), item_id"
            );
        tenv.createTemporaryView("t1", t1);
        // 2. 按照窗口开窗, 对商品点击量进行排名
        Table t2 = tenv.sqlQuery(
            "select " +
                "   *," +
                "   row_number() over(partition by w_end order by item_count desc) rk " +
                "from t1"
        );
        tenv.createTemporaryView("t2", t2);

        // 3. 取 top3
        Table t3 = tenv.sqlQuery(
            "select " +
                "   item_id, w_end, item_count, rk " +
                "from t2 " +
                "where rk<=3"
        );

        // 4. 数据写入到mysql
        // 4.1 创建输出表
        tenv.executeSql("create table hot_item(" +
                            "   item_id bigint, " +
                            "   w_end timestamp(3), " +
                            "   item_count bigint, " +
                            "   rk bigint, " +
                            "   PRIMARY KEY (w_end, rk) NOT ENFORCED)" +
                            "with(" +
                            "   'connector' = 'jdbc', " +
                            "   'url' = 'jdbc:mysql://hadoop162:3306/flink_sql?useSSL=false', " +
                            "   'table-name' = 'hot_item', " +
                            "   'username' = 'root', " +
                            "   'password' = 'aaaaaa' " +
                            ")");
        // 4.2 写入到输出表
        t3.executeInsert("hot_item");
    }
}