Flink SQL使用

Flink table API

需要用到的依赖：

<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-streaming-scala_${scala.binary.version}</artifactId>
    <version>${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>

代码实现：

流：

DataStreamSource<WaterSensor> waterSensorStream =
            env.fromElements(new WaterSensor("sensor_1", 1000L, 10),
                             new WaterSensor("sensor_1", 2000L, 20),
                             new WaterSensor("sensor_2", 3000L, 30),
                             new WaterSensor("sensor_1", 4000L, 40),
                             new WaterSensor("sensor_1", 5000L, 50),
                             new WaterSensor("sensor_2", 6000L, 60));

1.创建执行环境：

StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

2.把流转换为动态表

Table table = tableEnv.fromDataStream(waterSensorStream);
//打印查看一下
table.printScheam();

3.在表上执行连续查询

Table resultTable = table
            .where($("id").isEqual("sensor_1"))
            .select($("id"), $("ts"), $("vc"));

4.把动态表转换为流进行输出

  DataStream<Row> resultStream = tableEnv.toAppendStream(resultTable, Row.class);
  resultStream.print();
  env.execute();
     

完整案例：

import com.atguigu.flink.java.chapter_5.WaterSensor;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.apache.flink.types.Row;

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

public class Flink01_TableApi_BasicUse {
    public static void main(String[] args) {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        DataStreamSource<WaterSensor> waterSensorStream =
            env.fromElements(new WaterSensor("sensor_1", 1000L, 10),
                             new WaterSensor("sensor_1", 2000L, 20),
                             new WaterSensor("sensor_2", 3000L, 30),
                             new WaterSensor("sensor_1", 4000L, 40),
                             new WaterSensor("sensor_1", 5000L, 50),
                             new WaterSensor("sensor_2", 6000L, 60));

        // 1. 创建表的执行环境
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);
        // 2. 创建表: 将流转换成动态表. 表的字段名从pojo的属性名自动抽取
        Table table = tableEnv.fromDataStream(waterSensorStream);
        // 3. 对动态表进行查询
        Table resultTable = table
            .where($("id").isEqual("sensor_1"))
            .select($("id"), $("ts"), $("vc"));
        // 4. 把动态表转换成流
        DataStream<Row> resultStream = tableEnv.toAppendStream(resultTable, Row.class);
        resultStream.print();
        try {
            env.execute();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

补充：

import static 静态导入

/* 意思是导入这个类里的静态成员（静态方法、静态变量）在这个类中，就可以直接用方法名调用静态方法，而不必用“类名.方法名（）” 的方式来调用。
缺点：
1.静态导入可能会让代码更加难以阅读
2.如果同时导入的两个类中又有重命名的静态成员，会出现编译器错误。
*/
import static org.apache.flink.table.api.Expressions.$;

聚合操作

// 1. 对动态表进行查询
Table resultTable = table
    .where($("vc").isGreaterOrEqual(20))
    .groupBy($("id"))
    .aggregate($("vc").sum().as("vc_sum"))
    .select($("id"), $("vc_sum"));
// 2. 把动态表转换成流 如果涉及到数据的更新, 要用到撤回流. 多个了一个boolean标记
DataStream<Tuple2<Boolean, Row>> resultStream = tableEnv.toRetractStream(resultTable, Row.class);