flink消费kafka数据,按照指定时间开始消费

kafka中根据时间戳开始消费数据

java 复制代码
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.connector.kafka.source.enumerator.initializer.OffsetsInitializer;
import org.apache.flink.kafka.shaded.org.apache.kafka.clients.consumer.OffsetResetStrategy;
import org.apache.flink.kafka.shaded.org.apache.kafka.common.TopicPartition;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.yaml.snakeyaml.nodes.CollectionNode;

import java.util.Collection;
import java.util.Date;
import java.util.HashMap;
import java.util.Map;

/**
 * 支持按topic指定开始消费时间戳
 *
 * @author 
 */
public class KafkaOffsetsInitializer implements OffsetsInitializer  {

    private Logger logger = LoggerFactory.getLogger(KafkaOffsetsInitializer.class);


    private static final long serialVersionUID = 1L;
    /**
     * key:topic,value:开始消费时间戳
     */
    private Map<String, Long> topicStartingTimestamps;
    private ParameterTool parameters;

    /**
     * @param topicStartingTimestamps
     * @param parameters
     */
    public KafkaOffsetsInitializer(Map<String, Long> topicStartingTimestamps, ParameterTool parameters) {
        this.topicStartingTimestamps = topicStartingTimestamps;
        this.parameters = parameters;
    }

    @Override
    public Map<TopicPartition, Long> getPartitionOffsets(Collection<TopicPartition> partitions,
                                                         PartitionOffsetsRetriever partitionOffsetsRetriever) {
        //定义起始时间,初始offset
        Map<TopicPartition, Long> startingTimestamps = new HashMap<>();
        Map<TopicPartition, Long> initialOffsets = new HashMap<>();

        //commited offset
        Map<TopicPartition, Long> committedOffsets = partitionOffsetsRetriever.committedOffsets(partitions);

        //beginningOffsets the first offset for the given partitions.
        Map<TopicPartition, Long> beginningOffsets = partitionOffsetsRetriever.beginningOffsets(partitions);
        //endOffsets the for the given partitions.
        Map<TopicPartition, Long> endOffsets = partitionOffsetsRetriever.endOffsets(partitions);

        final long now = System.currentTimeMillis();
        partitions.forEach(tp -> {
            //起始时间赋值为从redis中获取到相对应topic的时间
            Long startingTimestamp = topicStartingTimestamps.get(tp.topic());
            if (startingTimestamp == null) {
                //redis里没有取到消费开始时间从启动时间消费
                startingTimestamp = now;
                logger.info("从redis没有取到时间戳,topic:{},partition:{},使用当前时间:{},{}", tp.topic(), tp.partition(), now, new Date(now));
            }
            logger.info("读取时间戳,topic:{},partition:{},时间戳:{},{}", tp.topic(), tp.partition(), now, new Date(now));
            startingTimestamps.put(tp, startingTimestamp);
        });
        partitionOffsetsRetriever.offsetsForTimes(startingTimestamps).forEach((tp, offsetMetadata) -> {
            long offsetForTime = beginningOffsets.get(tp);
            long offsetForCommit = beginningOffsets.get(tp);
            if (offsetMetadata != null) {
                offsetForTime = offsetMetadata.offset();
                logger.info("根据时间戳取到offset,topic:{},partition:{},offset:{}", tp.topic(), tp.partition(), offsetForTime);
            }

            Long commitedOffset = committedOffsets.get(tp);
            if (commitedOffset != null) {
                offsetForCommit = commitedOffset.longValue();
                logger.info("根据已提交offset取到offset,topic:{},partition:{},offset:{}", tp.topic(), tp.partition(), offsetForCommit);
            }
            logger.info("设置读取offset,topic:{},partition:{},offset:{},endOffset:{}", tp.topic(), tp.partition(), Math.max(offsetForTime, offsetForCommit), endOffsets.get(tp));
            //对比时间戳对应的offset和checkpoint保存的offset,取较大值
            //initialOffsets.put(tp, Math.max(offsetForTime, offsetForCommit));
            initialOffsets.put(tp, offsetForCommit);
        });
        return initialOffsets;
    }

    @Override
    public OffsetResetStrategy getAutoOffsetResetStrategy() {
        return OffsetResetStrategy.NONE;
    }
}
相关推荐
禾吾6 小时前
Kafka基础-安装、基础命令等
kafka
cpolar技术支持9 小时前
Kafka Streams 窗口统计怎么验收:本地跑订单流聚合,用 cpolar 给同事看只读结果页
java·docker·kafka·cpolar·kafka streams
MZA66611 小时前
Spring Boot 实战:基于自定义注解 + AOP 实现 Kafka 消息无侵入异步上送
java·spring boot·kafka
重庆小透明12 小时前
Kafka 完全指南:从基础组件到核心原理(包含面试题)
java·分布式·微服务·架构·kafka
一本正经的不务正业13 小时前
kafka与RocketMQ的不同
分布式·kafka·rocketmq
johnrui13 小时前
kafka4.x单机版安装部署(单节点 KRaft 模式)
kafka
starzy199016 小时前
Flink基础之Session-Cluster原理详解:共享集群的利与弊
大数据·flink
starzy199016 小时前
Flink基础之Per-Job-Cluster原理详解:被 Application 取代的模式
java·大数据·flink
面向Google编程1 天前
Kafka 成了 Agent 的「共享内存」,Flink 成了它的「大脑」
flink·kafka·agent
用户3610588626121 天前
Flink基础之Flink批流数据读取处理案例剖析:从文件到 Kafka 的完整代码
大数据·flink