Flink Kafka 工具类（保证数据精准一致性）

KafkaUtil 

import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer;
import org.apache.flink.streaming.connectors.kafka.KafkaSerializationSchema;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.producer.ProducerConfig;
import org.apache.kafka.clients.producer.ProducerRecord;

import javax.annotation.Nullable;
import java.util.Properties;

/**
 * @author zyj
 * @Date 2022/1/6 15:29
 * 操作 kafka 的工具类
 */
public class MyKafkaUtil {
    private static final String KAFKA_SERVER = "hadoop101:9092,hadoop102:9092,hadoop103:9092";
    private static final String DEFAULT_TOPIC = "default_topic";

    // 获取kafka的消费者
    public static FlinkKafkaConsumer<String> getKafkaSource(String topic, String groupId) {
        Properties props = new Properties();
        props.setProperty(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, KAFKA_SERVER);
        props.setProperty(ConsumerConfig.GROUP_ID_CONFIG, groupId);

        return new FlinkKafkaConsumer<String>(topic, new SimpleStringSchema(), props);
    }

    // 获取kafka的生产者（String数据类型）
   /*
   注意：下面这中实现只能保证数据不丢，不能保证精准一次性
   public static FlinkKafkaProducer<String> getKafkaSink(String topic) {
        return new FlinkKafkaProducer<String>(
                KAFKA_SERVER,
                topic,
                new SimpleStringSchema()
        );
    }*/
    public static FlinkKafkaProducer<String> getKafkaSink(String topic) {
        Properties props = new Properties();
        // 指定kafka服务端ip地址
        props.setProperty(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, KAFKA_SERVER);
        // 设置生产超时时间
        props.setProperty(ProducerConfig.TRANSACTION_TIMEOUT_CONFIG, 1000 * 60 * 15 + "");

        // 创建kafka生产者，自定义序列化器 KafkaSerializationSchema<String> 这里是指定String类型
        return new FlinkKafkaProducer<String>(DEFAULT_TOPIC, new KafkaSerializationSchema<String>() {
            @Override
            public ProducerRecord<byte[], byte[]> serialize(String str, @Nullable Long timestamp) {
                return new ProducerRecord<byte[], byte[]>(topic, str.getBytes());
            }
        }, props, FlinkKafkaProducer.Semantic.EXACTLY_ONCE);
    }

    // 获取kafka的生产者（通用数据类型）
    public static <T> FlinkKafkaProducer<T> getKafkaSinkSchema(KafkaSerializationSchema<T> kafkaSerializationSchema) {
        Properties props = new Properties();
        // 指定kafka服务端ip地址
        props.setProperty(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, KAFKA_SERVER);
        // 设置生产超时时间
        props.setProperty(ProducerConfig.TRANSACTION_TIMEOUT_CONFIG, 1000 * 60 * 15 + "");

        return new FlinkKafkaProducer<T>(DEFAULT_TOPIC, kafkaSerializationSchema, props, FlinkKafkaProducer.Semantic.EXACTLY_ONCE);
    }
}