如何为MongoDB接收器构建用于Spark Structured Streaming应用程序的超级jar

Question

I am unable to build a fat jar for my Kafka-SparkStructuredStreaming-MongoDB pipeline.

I have built StructuredStreamingProgram: receives streaming data from Kafka Topics and apply some parsing and then my intention is to save the structured streaming data into a MongoDB collection.

I have followed this article to build my pipeline https://learningfromdata.blog/2017/04/16/real-time-data-ingestion-with-apache-spark-structured-streaming-implementation/

I have created Helpers.scala and MongoDBForeachWriter.scala as suggested in the article for my streaming pipeline and save it under src/main/scala/example

When i do sbt assembly to build a fat jar i face this errors;

"[error] C:\spark_streaming\src\main\scala\example\structuredStreamApp.scala:63: class MongoDBForeachWriter is abstract; cannot be instantiated

[error]     val structuredStreamForeachWriter: MongoDBForeachWriter = new MongoDBForeachWriter(mongodb_uri,mdb_name,mdb_collection,CountAccum)"

I need guidance in making this pipeline work.

Any help will be appreciated

package example
import java.util.Calendar
import org.apache.spark.util.LongAccumulator
import org.apache.spark.sql.Row
import org.apache.spark.sql.ForeachWriter
import org.mongodb.scala._
import org.mongodb.scala.bson.collection.mutable.Document
import org.mongodb.scala.bson._
import example.Helpers._


abstract class MongoDBForeachWriter(p_uri: String,
                           p_dbName: String,
                           p_collectionName: String,
                           p_messageCountAccum: LongAccumulator) extends ForeachWriter[Row] {

  val mongodbURI = p_uri
  val dbName = p_dbName
  val collectionName = p_collectionName
  val messageCountAccum = p_messageCountAccum

  var mongoClient: MongoClient = null
  var db: MongoDatabase = null
  var collection: MongoCollection[Document] = null

  def ensureMongoDBConnection(): Unit = {
    if (mongoClient == null) {
      mongoClient = MongoClient(mongodbURI)
      db = mongoClient.getDatabase(dbName)
      collection = db.getCollection(collectionName)
    }
  }

  override def open(partitionId: Long, version: Long): Boolean = {
    true
  }

  override def process(record: Row): Unit = {
    val valueStr = new String(record.getAs[Array[Byte]]("value"))

    val doc: Document = Document(valueStr)
    doc += ("log_time" -> Calendar.getInstance().getTime())

    // lazy opening of MongoDB connection
    ensureMongoDBConnection()
    val result = collection.insertOne(doc).results()

    // tracks how many records I have processed
    if (messageCountAccum != null)
      messageCountAccum.add(1)
  }
}


package example

import java.util.concurrent.TimeUnit

import scala.concurrent.Await
import scala.concurrent.duration.Duration

import org.mongodb.scala._

object Helpers {

  implicit class DocumentObservable[C](val observable: Observable[Document]) extends ImplicitObservable[Document] {
    override val converter: (Document) => String = (doc) => doc.toJson
  }

  implicit class GenericObservable[C](val observable: Observable[C]) extends ImplicitObservable[C] {
    override val converter: (C) => String = (doc) => doc.toString
  }

  trait ImplicitObservable[C] {
    val observable: Observable[C]
    val converter: (C) => String

    def results(): Seq[C] = Await.result(observable.toFuture(), Duration(10, TimeUnit.SECONDS))
    def headResult() = Await.result(observable.head(), Duration(10, TimeUnit.SECONDS))
    def printResults(initial: String = ""): Unit = {
      if (initial.length > 0) print(initial)
      results().foreach(res => println(converter(res)))
    }
    def printHeadResult(initial: String = ""): Unit = println(s"${initial}${converter(headResult())}")
  }

}

package example

import org.apache.spark.sql.functions.{col, _}
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions._
import org.apache.spark.sql.streaming.Trigger
import org.apache.spark.util.LongAccumulator
import example.Helpers._
import java.util.Calendar

object StructuredStreamingProgram {

  def main(args: Array[String]): Unit = {

    val spark = SparkSession
      .builder()
      .appName("OSB_Streaming_Model")
      .getOrCreate()

    import spark.implicits._

    val df = spark
      .readStream
      .format("kafka")
      .option("kafka.bootstrap.servers", "10.160.172.45:9092, 10.160.172.46:9092, 10.160.172.100:9092")
      .option("subscribe", "TOPIC_WITH_COMP_P2_R2, TOPIC_WITH_COMP_P2_R2.DIT, TOPIC_WITHOUT_COMP_P2_R2.DIT")
      .load()

    val dfs = df.selectExpr("CAST(value AS STRING)").toDF()
    val data =dfs.withColumn("splitted", split($"SERVICE_NAME8", "/"))
      .select($"splitted".getItem(4).alias("region"),$"splitted".getItem(5).alias("service"),col("_raw"))
      .withColumn("service_type", regexp_extract($"service", """.*(Inbound|Outbound|Outound).*""",1))
      .withColumn("region_type", concat(
        when(col("region").isNotNull,col("region")).otherwise(lit("null")), lit(" "),
        when(col("service").isNotNull,col("service_type")).otherwise(lit("null"))))

    val extractedDF = data.filter(
      col("region").isNotNull &&
        col("service").isNotNull &&
        col("_raw").isNotNull &&
        col("service_type").isNotNull &&
        col("region_type").isNotNull)
      .filter("region != ''")
      .filter("service != ''")
      .filter("_raw != ''")
      .filter("service_type != ''")
      .filter("region_type != ''")

    // sends to MongoDB once every 20 seconds
    val mongodb_uri = "mongodb://dstk8sdev06.us.dell.com/?maxPoolSize=1"
    val mdb_name = "HANZO_MDB"
    val mdb_collection = "Testing_Spark"
    val CountAccum: LongAccumulator = spark.sparkContext.longAccumulator("mongostreamcount")

    val structuredStreamForeachWriter: MongoDBForeachWriter = new MongoDBForeachWriter(mongodb_uri,mdb_name,mdb_collection,CountAccum)
    val query = df.writeStream
      .foreach(structuredStreamForeachWriter)
      .trigger(Trigger.ProcessingTime("20 seconds"))
      .start()

    while (!spark.streams.awaitAnyTermination(60000)) {
      println(Calendar.getInstance().getTime()+" :: mongoEventsCount = "+CountAccum.value)
    }

  }
}

with the above by doing corrections i would need to be able to save the structured streaming data into mongodb

Answer 1

You can instantiate object for abstract class. To resolve this issue, implement close function in MongoDBForeachWriter class and make it as as concrete class.

class MongoDBForeachWriter(p_uri: String,
                                    p_dbName: String,
                                    p_collectionName: String,
                                    p_messageCountAccum: LongAccumulator) extends ForeachWriter[Row] {

  val mongodbURI = p_uri
  val dbName = p_dbName
  val collectionName = p_collectionName
  val messageCountAccum = p_messageCountAccum

  var mongoClient: MongoClient = null
  var db: MongoDatabase = null
  var collection: MongoCollection[Document] = null

  def ensureMongoDBConnection(): Unit = {
    if (mongoClient == null) {
      mongoClient = MongoClient(mongodbURI)
      db = mongoClient.getDatabase(dbName)
      collection = db.getCollection(collectionName)
    }
  }

  override def open(partitionId: Long, version: Long): Boolean = {
    true
  }

  override def process(record: Row): Unit = {
    val valueStr = new String(record.getAs[Array[Byte]]("value"))

    val doc: Document = Document(valueStr)
    doc += ("log_time" -> Calendar.getInstance().getTime())

    // lazy opening of MongoDB connection
    ensureMongoDBConnection()
    val result = collection.insertOne(doc)

    // tracks how many records I have processed
    if (messageCountAccum != null)
      messageCountAccum.add(1)
  }

  override def close(errorOrNull: Throwable): Unit = {
    if(mongoClient != null) {
      Try {
        mongoClient.close()
      }
    }
  }
}

Hope this helps.

Ravi