tencent cloud

name := "Consumer Example"
version := "1.0"
scalaVersion := "2.11.8"
libraryDependencies += "org.apache.spark" %% "spark-core" % "2.1.0"
libraryDependencies += "org.apache.spark" %% "spark-streaming" % "2.1.0"
libraryDependencies += "org.apache.spark" %% "spark-streaming-kafka-0-10" % "2.1.0"


import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.kafka.common.TopicPartition
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.kafka010.OffsetRange
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import collection.JavaConversions._
import Array._
object Kafka {
    def main(args: Array[String]) {
        val kafkaParams = Map[String, Object](
            "bootstrap.servers" -> "172.16.16.12:9092",
            "key.deserializer" -> classOf[StringDeserializer],
            "value.deserializer" -> classOf[StringDeserializer],
            "group.id" -> "spark_stream_test1",
            "auto.offset.reset" -> "earliest",
            "enable.auto.commit" -> "false"
        )

        val sparkConf = new SparkConf()
        sparkConf.setMaster("local")
        sparkConf.setAppName("Kafka")
        val ssc = new StreamingContext(sparkConf, Seconds(5))
        val topics = Array("spark_test")

        val offsets : Map[TopicPartition, Long] = Map()

        for (i <- 0 until 3){
            val tp = new TopicPartition("spark_test", i)
            offsets.updated(tp , 0L)
        }
        val stream = KafkaUtils.createDirectStream[String, String](
            ssc,
            PreferConsistent,
            Subscribe[String, String](topics, kafkaParams)
        )
        println("directStream")
        stream.foreachRDD{ rdd=>
            // Output the obtained message
            rdd.foreach{iter =>
                val i = iter.value
                println(s"${i}")
            }
            // Get the offset
            val offsetRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
            rdd.foreachPartition { iter =>
                val o: OffsetRange = offsetRanges(TaskContext.get.partitionId)
                println(s"${o.topic} ${o.partition} ${o.fromOffset} ${o.untilOffset}")
            }
        }

        // Start the computation
        ssc.start()
        ssc.awaitTermination()
    }
}


import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.kafka010.OffsetRange
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import collection.JavaConversions._
import Array._
object Kafka {
    def main(args: Array[String]) {
        val kafkaParams = Map[String, Object](
            "bootstrap.servers" -> "172.16.16.12:9092",
            "key.deserializer" -> classOf[StringDeserializer],
            "value.deserializer" -> classOf[StringDeserializer],
            "group.id" -> "spark_stream",
            "auto.offset.reset" -> "earliest",
            "enable.auto.commit" -> (false: java.lang.Boolean)
        )
        val sc = new SparkContext("local", "Kafka", new SparkConf())
        val java_kafkaParams : java.util.Map[String, Object] = kafkaParams
        // Pull messages in the corresponding offset range from the partition in order. The request will be blocked if no messages can be pulled, until the specified waiting time elapses or the number of produced new messages reaches the number for messages to be pulled
        val offsetRanges = Array[OffsetRange](
            OffsetRange("spark_test", 0, 0, 5),
            OffsetRange("spark_test", 1, 0, 5),
            OffsetRange("spark_test", 2, 0, 5)
        )
        val range = KafkaUtils.createRDD[String, String](
            sc,
            java_kafkaParams,
            offsetRanges,
            PreferConsistent
        )
        range.foreach(rdd=>println(rdd.value))
        sc.stop()
    }
}