Kafka：指定时间消费

需求：

在生产环境中，会遇到最近消费的几个小时数据异常，想重新按照时间消费。例如要求按照时间消费前一天的数据，怎么处理？

import org.apache.kafka.clients.consumer.*;
import org.apache.kafka.common.TopicPartition;
import org.apache.kafka.common.serialization.StringDeserializer;

import java.time.Duration;
import java.util.*;

public class CustomConsumerSeekTime {

    public static void main(String[] args) {

        // 0 配置信息
        Properties properties = new Properties();

        // 连接
        properties.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG,"192.168.25.129:9092,192.168.25.129:9092");

        // 反序列化
        properties.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        properties.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());

        // 组id
        properties.put(ConsumerConfig.GROUP_ID_CONFIG,"test3");

        // 1 创建消费者
        // KafkaConsumer<K, V> 
        // 由于消息形式是 key value 为 "", "hello"
        // 所以泛型K为key为String类型 泛型V为传递消息的类型，此处发送字符串用String类型
        KafkaConsumer<String, String> kafkaConsumer = new KafkaConsumer<>(properties);

        // 2 订阅主题
        ArrayList<String> topics = new ArrayList<>();
        topics.add("test");
        kafkaConsumer.subscribe(topics);

        // ===================================此处==============================================

        // 指定位置进行消费
        Set<TopicPartition> assignment = kafkaConsumer.assignment();

        //  保证分区分配方案已经制定完毕
        // 因为消费者初始化与broker通信进行分区分配需要一定的时间
        while (assignment.size() == 0){
            kafkaConsumer.poll(Duration.ofSeconds(1));

            assignment = kafkaConsumer.assignment();
        }

        // 希望把时间转换为对应的offset
        HashMap<TopicPartition, Long> topicPartitionLongHashMap = new HashMap<>();

        // 封装对应集合
        for (TopicPartition topicPartition : assignment) {
            // 每个分区对应一天前的数据，从此刻一天前
            topicPartitionLongHashMap.put(topicPartition,System.currentTimeMillis() - 1 * 24 * 3600 * 1000);
        }

        Map<TopicPartition, OffsetAndTimestamp> topicPartitionOffsetAndTimestampMap = kafkaConsumer.offsetsForTimes(topicPartitionLongHashMap);

        // 遍历每个分区，对每个分区设置消费时间。指定消费的offset
        for (TopicPartition topicPartition : assignment) {

            OffsetAndTimestamp offsetAndTimestamp = topicPartitionOffsetAndTimestampMap.get(topicPartition);
            
            if (offsetAndTimestamp != null) {
                // 将时间转成offset去消费
                kafkaConsumer.seek(topicPartition, offsetAndTimestamp.offset());
            }

        }

        // ==============================止此======================================

        // 3  消费数据
        while (true){

            ConsumerRecords<String, String> consumerRecords = kafkaConsumer.poll(Duration.ofSeconds(1));

            for (ConsumerRecord<String, String> consumerRecord : consumerRecords) {

                System.out.println(consumerRecord);
            }
        }
    }
}