Spark Scala noClassDefFounderRor：org/apache/Spark/logging

Question

import org.apache.spark._
import org.apache.spark.streaming._
import org.apache.spark.streaming.twitter._
import twitter4j.Status

object TrendingHashTags {
  def main(args: Array[String]): Unit = {
    if (args.length < 8) {
      System.err.println("Usage: TrendingHashTags <consumer key> <consumer secret> " +
                          "<access token> <access token secret> " +
                          "<language> <batch interval> <min-threshold> <show-count> " +
                          "[<filters>]")
      System.exit(1)
    }

    val Array(consumerKey, consumerSecret, accessToken, accessTokenSecret,
                              lang, batchInterval, minThreshold, showCount ) = args.take(8)
    val filters = args.takeRight(args.length - 8)

    System.setProperty("twitter4j.oauth.consumerKey", consumerKey)
    System.setProperty("twitter4j.oauth.consumerSecret", consumerSecret)
    System.setProperty("twitter4j.oauth.accessToken", accessToken)
    System.setProperty("twitter4j.oauth.accessTokenSecret", accessTokenSecret)

    val conf = new SparkConf().setMaster(("local[4]")).setAppName("TrendingHashTags")
    val ssc = new StreamingContext(conf, Seconds(batchInterval.toInt))
    ssc.checkpoint("checkpoint")
    val tweets = TwitterUtils.createStream(ssc, None, filters)
    val tweetsFilteredByLang = tweets.filter{tweet => tweet.getLang() == lang}
    val statuses = tweetsFilteredByLang.map{tweet => tweet.getText()}
    val words = statuses.flatMap{status => status.split("""\s+""")}
    val hashTags = words.filter{word => word.startsWith("#")}
    val hashTagPairs = hashTags.map{hashtag => (hashtag, 1)}
    val tagsWithCounts = hashTagPairs.updateStateByKey(
      (counts: Seq[Int], prevCount: Option[Int]) =>
        prevCount.map{c => c + counts.sum}.orElse{Some(counts.sum)}
    )
    val topHashTags = tagsWithCounts.filter { case (t, c) =>
      c > minThreshold.toInt
    }
    val sortedTopHashTags = topHashTags.transform{rdd =>
      rdd.sortBy({case(w, c) => c}, false)
    }
    sortedTopHashTags.print(showCount.toInt)
    ssc.start()
    ssc.awaitTermination()
  }
}

Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/spark/Logging
    at java.lang.ClassLoader.defineClass1(Native Method)
    at java.lang.ClassLoader.defineClass(ClassLoader.java:763)
    at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
    at java.net.URLClassLoader.defineClass(URLClassLoader.java:467)
    at java.net.URLClassLoader.access$100(URLClassLoader.java:73)
    at java.net.URLClassLoader$1.run(URLClassLoader.java:368)
    at java.net.URLClassLoader$1.run(URLClassLoader.java:362)
    at java.security.AccessController.doPrivileged(Native Method)
    at java.net.URLClassLoader.findClass(URLClassLoader.java:361)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:335)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
    at org.apache.spark.streaming.twitter.TwitterUtils$.createStream(TwitterUtils.scala:44)
    at TrendingHashTags$.main(TrendingHashTags.scala:28)
    at TrendingHashTags.main(TrendingHashTags.scala)
Caused by: java.lang.ClassNotFoundException: org.apache.spark.Logging
    at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:335)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)

以下是我的构建。SBT内容：

name := "sparkStreaming"

version := "0.1"

scalaVersion := "2.11.12"

libraryDependencies ++= Seq("org.apache.spark" %% "spark-core" % "2.4.5",
  "org.apache.spark" %% "spark-sql" % "2.4.5",
  "org.apache.spark" %% "spark-streaming" % "2.4.5" % "provided",
  "org.apache.spark" %% "spark-streaming-twitter" % "1.6.3")

Answer 1

清楚的迹象是，有些地方你在内部使用较低版本的Spark...（spark 1.5可能是）

sbt inspect tree clean

你可以用这个检查一下。对于maven用户MVN depdency:tree将给出所有使用的依赖项列表

还有一件事是你在使用

  "org.apache.spark" %% "spark-streaming" % "2.4.5" % "provided",