读取kafka的偏移量的工具类

65 阅读 0 评论 43 点赞

我是靠谱客的博主小巧高山，最近开发中收集的这篇文章主要介绍读取kafka的偏移量的工具类，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

读取kafka的偏移量的工具类

// An highlighted block
import java.util.Properties

import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}

object MyKafkaUtil {
  private val properties: Properties = MyPropertiesUtil.load("config.properties")
  val broker_list = properties.getProperty("kafka.broker.list")

  // kafka消费者配置
  var kafkaParam = collection.mutable.Map(
    "bootstrap.servers" -> broker_list,//用于初始化链接到集群的地址
    "key.deserializer" -> classOf[StringDeserializer],
    "value.deserializer" -> classOf[StringDeserializer],
    //用于标识这个消费者属于哪个消费团体
    "group.id" -> "gmall0523_group",
    //latest自动重置偏移量为最新的偏移量
    "auto.offset.reset" -> "latest",
    //如果是true，则这个消费者的偏移量会在后台自动提交,但是kafka宕机容易丢失数据
    //如果是false，会需要手动维护kafka偏移量
    "enable.auto.commit" -> (false: java.lang.Boolean)
  )


  // 创建DStream，返回接收到的输入数据   使用默认的消费者组
  def getKafkaStream(topic: String,ssc:StreamingContext ): InputDStream[ConsumerRecord[String,String]]={
    val dStream = KafkaUtils.createDirectStream[String,String](
      ssc,
      LocationStrategies.PreferConsistent,
      ConsumerStrategies.Subscribe[String,String](Array(topic), kafkaParam )
    )
    dStream
  }

  //在对Kafka数据进行消费的时候，指定消费者组
  def getKafkaStream(topic: String,ssc:StreamingContext,groupId:String): InputDStream[ConsumerRecord[String,String]]={
    kafkaParam("group.id")=groupId
    val dStream = KafkaUtils.createDirectStream[String,String](
      ssc,
      LocationStrategies.PreferConsistent,
      ConsumerStrategies.Subscribe[String,String](Array(topic),kafkaParam ))
    dStream
  }

  //从指定的偏移量位置读取数据 offsets 是一个map 集合key 是new TopicPartition(topic, partition.toInt),value 是 offset.toLong
  def getKafkaStream(topic: String,ssc:StreamingContext,offsets:Map[TopicPartition,Long],groupId:String)
  : InputDStream[ConsumerRecord[String,String]]={
    kafkaParam("group.id")=groupId
    val dStream = KafkaUtils.createDirectStream[String,String](
      ssc,
      LocationStrategies.PreferConsistent,
      ConsumerStrategies.Subscribe[String,String](Array(topic),kafkaParam,offsets))
    dStream
  }

}