Flink 系例 之 TableAPI ＆ SQL 与 MYSQL 数据查询

使用 Tbale&SQL 与 Flink JDBC 连接器从 MYSQL 数据库表中 SELECT 选取数据。

示例环境

java.version: 1.8.x
flink.version: 1.11.1
kafka：2.11

示例数据源 （项目码云下载）

Flink 系例 之 搭建开发环境与数据

示例模块 （pom.xml）

Flink 系例 之 TableAPI & SQL 与 示例模块

SelectToMysql.java

package com.flink.examples.mysql;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.EnvironmentSettings;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.apache.flink.types.Row;
import org.apache.flink.util.Collector;

import static org.apache.flink.table.api.Expressions.$;

/**
 * @Description 使用Tbale&SQL与Flink JDBC连接器从MYSQL数据库表中SELECT选取数据。
 */
public class SelectToMysql {
    /**
     官方参考：https://ci.apache.org/projects/flink/flink-docs-release-1.11/dev/table/connectors/jdbc.html

     分区扫描
     为了加速并行Source任务实例中的数据读取，Flink为JDBC表提供了分区扫描功能。
         scan.partition.column：用于对输入进行分区的列名。
         scan.partition.num：分区数。
         scan.partition.lower-bound：第一个分区的最小值。
         scan.partition.upper-bound：最后一个分区的最大值。
     */

    //flink-jdbc-1.11.1写法,所有属性名在JdbcTableSourceSinkFactory工厂类中定义
    static String table_sql =
            "CREATE TABLE my_users (\n" +
            "  id BIGINT,\n" +
            "  name STRING,\n" +
            "  age INT,\n" +
            "  status INT,\n" +
            "  PRIMARY KEY (id) NOT ENFORCED\n" +
            ") WITH (\n" +
            "  'connector.type' = 'jdbc',\n" +
            "  'connector.url' = 'jdbc:mysql://192.168.110.35:3306/flink?useUnicode=true&characterEncoding=utf-8', \n" +
            "  'connector.driver' = 'com.mysql.jdbc.Driver', \n" +
            "  'connector.table' = 'users', \n" +
            "  'connector.username' = 'root',\n" +
            "  'connector.password' = 'password', \n" +
            "  'connector.read.fetch-size' = '3' \n" +
            ")";
    public static void main(String[] args) throws Exception {
        //构建StreamExecutionEnvironment
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        //构建EnvironmentSettings 并指定Blink Planner
        EnvironmentSettings bsSettings = EnvironmentSettings.newInstance().useBlinkPlanner().inStreamingMode().build();
        //构建StreamTableEnvironment
        StreamTableEnvironment tEnv = StreamTableEnvironment.create(env, bsSettings);
        //注册mysql数据维表
        tEnv.executeSql(table_sql);

        String sql = "select id,name,age,status from my_users";
        //第一种：执行SQL
        //Table table = tEnv.sqlQuery(sql);

        //第二种：通过方法拼装执行语句
        Table table = tEnv.from("my_users").select($("id"), $("name"), $("age"), $("status")).where($("status").isEqual(0));

        //打印字段结构
        table.printSchema();

        //table 转成 dataStream 流
        DataStream<Row> behaviorStream = tEnv.toAppendStream(table, Row.class);
        behaviorStream.flatMap(new FlatMapFunction<Row, Object>() {
            @Override
            public void flatMap(Row value, Collector<Object> out) throws Exception {
                System.out.println(value.toString());
                Thread.sleep(1 * 1000);
            }
        }).print();
        env.execute();
    }
}

  打印结果

root
 |-- id: BIGINT NOT NULL
 |-- name: STRING
 |-- age: INT
 |-- status: INT

1,nike,16,0
2,nike,18,0