java - Spark 和 Cassandra Java 应用程序 : Exception in thread "main" java. lang.NoClassDefFoundError: org/apache/spark/sql/Dataset

Question

我得到了一个令人惊奇的 siplme java 应用程序，我几乎从这个例子中复制了它:http://markmail.org/download.xqy?id=zua6upabiylzeetp&number=2

我想做的就是读取表数据并显示在 Eclipse 控制台中。

我的pom.xml:

        <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>chat_connaction_test</groupId>
  <artifactId>ChatSparkConnectionTest</artifactId>
  <version>0.0.1-SNAPSHOT</version>
 <dependencies> 
    <dependency>
    <groupId>com.datastax.cassandra</groupId>
    <artifactId>cassandra-driver-core</artifactId>
    <version>3.1.0</version>
    </dependency>

    <dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-core_2.10</artifactId>
    <version>2.0.0</version>
    </dependency>

    <!-- https://mvnrepository.com/artifact/com.datastax.spark/spark-cassandra-connector_2.10 -->
    <dependency>
    <groupId>com.datastax.spark</groupId>
    <artifactId>spark-cassandra-connector_2.10</artifactId>
    <version>2.0.0-M3</version>
    </dependency>

    <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming_2.10 -->
    <dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming_2.10</artifactId>
    <version>2.0.0</version>
    </dependency>
    <!--
    <dependency> 
    <groupId>org.apache.spark</groupId> 
    <artifactId>spark-hive_2.10</artifactId> 
    <version>1.5.2</version> 
    </dependency>
    -->
  </dependencies>
</project>

还有我的java代码:

    package com.chatSparkConnactionTest;

import static com.datastax.spark.connector.japi.CassandraJavaUtil.javaFunctions;
import java.io.Serializable;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import com.datastax.spark.connector.japi.CassandraRow;

public class JavaDemo implements Serializable {
    private static final long serialVersionUID = 1L;
    public static void main(String[] args) {

        SparkConf conf = new SparkConf().
            setAppName("chat").
            setMaster("local").
            set("spark.executor.memory","1g").
            set("spark.cassandra.connection.host", "127.0.0.1");
        JavaSparkContext sc = new JavaSparkContext(conf);

        JavaRDD<String> cassandraRowsRDD = javaFunctions(sc).cassandraTable(
            "chat", "dictionary")

            .map(new Function<CassandraRow, String>() {
                @Override
                public String call(CassandraRow cassandraRow) throws Exception {
                    String tempResult = cassandraRow.toString();
                    System.out.println(tempResult);
                    return tempResult;
                    }
                }
            );
        System.out.println("Data as CassandraRows: \n" + 
        cassandraRowsRDD.collect().size()); // THIS IS A LINE WITH ERROR
    } 
}

这是我的错误:

16/10/05 20:49:18 INFO CassandraConnector: Connected to Cassandra cluster: Test Cluster Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/spark/sql/Dataset at java.lang.Class.getDeclaredMethods0(Native Method) at java.lang.Class.privateGetDeclaredMethods(Unknown Source) at java.lang.Class.getDeclaredMethod(Unknown Source) at java.io.ObjectStreamClass.getPrivateMethod(Unknown Source) at java.io.ObjectStreamClass.access$1700(Unknown Source) at java.io.ObjectStreamClass$2.run(Unknown Source) at java.io.ObjectStreamClass$2.run(Unknown Source) at java.security.AccessController.doPrivileged(Native Method) at java.io.ObjectStreamClass.(Unknown Source) at java.io.ObjectStreamClass.lookup(Unknown Source) at java.io.ObjectOutputStream.writeObject0(Unknown Source) at java.io.ObjectOutputStream.defaultWriteFields(Unknown Source) at java.io.ObjectOutputStream.writeSerialData(Unknown Source) at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source) at java.io.ObjectOutputStream.writeObject0(Unknown Source) at java.io.ObjectOutputStream.defaultWriteFields(Unknown Source) at java.io.ObjectOutputStream.writeSerialData(Unknown Source) at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source) at java.io.ObjectOutputStream.writeObject0(Unknown Source) at java.io.ObjectOutputStream.writeObject(Unknown Source) at scala.collection.immutable.$colon$colon.writeObject(List.scala:379) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source) at java.lang.reflect.Method.invoke(Unknown Source) at java.io.ObjectStreamClass.invokeWriteObject(Unknown Source) at java.io.ObjectOutputStream.writeSerialData(Unknown Source) at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source) at java.io.ObjectOutputStream.writeObject0(Unknown Source) at java.io.ObjectOutputStream.defaultWriteFields(Unknown Source) at java.io.ObjectOutputStream.writeSerialData(Unknown Source) at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source) at java.io.ObjectOutputStream.writeObject0(Unknown Source) at java.io.ObjectOutputStream.defaultWriteFields(Unknown Source) at java.io.ObjectOutputStream.writeSerialData(Unknown Source) at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source) at java.io.ObjectOutputStream.writeObject0(Unknown Source) at java.io.ObjectOutputStream.defaultWriteFields(Unknown Source) at java.io.ObjectOutputStream.writeSerialData(Unknown Source) at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source) at java.io.ObjectOutputStream.writeObject0(Unknown Source) at java.io.ObjectOutputStream.writeObject(Unknown Source) at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:43) at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100) at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:295) at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:288) at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:108) at org.apache.spark.SparkContext.clean(SparkContext.scala:2037) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1896) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1911) at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:893) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112) at org.apache.spark.rdd.RDD.withScope(RDD.scala:358) at org.apache.spark.rdd.RDD.collect(RDD.scala:892) at org.apache.spark.api.java.JavaRDDLike$class.collect(JavaRDDLike.scala:360) at org.apache.spark.api.java.AbstractJavaRDDLike.collect(JavaRDDLike.scala:45) at com.chatSparkConnactionTest.JavaDemo.main(JavaDemo.java:37) Caused by: java.lang.ClassNotFoundException: org.apache.spark.sql.Dataset at java.net.URLClassLoader.findClass(Unknown Source) at java.lang.ClassLoader.loadClass(Unknown Source) at sun.misc.Launcher$AppClassLoader.loadClass(Unknown Source) at java.lang.ClassLoader.loadClass(Unknown Source) ... 58 more

我更新了 pom.xml，但这并没有解决错误。有人可以帮我解决这个问题吗？

谢谢!

更新1:这是我的构建路径截图: Link to my screenshot

Answer 1

您收到“java.lang.NoClassDefFoundError: org/apache/spark/sql/Dataset”错误，因为您的 pom.xml 文件中缺少“spark-sql”依赖项。

如果您想使用 Spark 2.0.0 读取 Cassandra 表，那么您需要以下最小依赖项。

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-core_2.11</artifactId>
    <version>2.0.0</version>
</dependency>
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-sql_2.11</artifactId>
    <version>2.0.0</version>
</dependency>
<dependency>
    <groupId>com.datastax.spark</groupId>
    <artifactId>spark-cassandra-connector_2.11</artifactId>
    <version>2.0.0-M3</version>
</dependency>

Spark 2.0.0提供了SparkSession和Dataset API。下面是读取Cassandra表并打印记录的示例程序。

 public class SparkCassandraDatasetApplication {
 public static void main(String[] args) {
 SparkSession spark = SparkSession
          .builder()
          .appName("SparkCassandraDatasetApplication")
          .config("spark.sql.warehouse.dir", "/file:C:/temp")
          .config("spark.cassandra.connection.host", "127.0.0.1")
          .config("spark.cassandra.connection.port", "9042")
          .master("local[2]")
          .getOrCreate();

 //Read data
 Dataset<Row> dataset = spark.read().format("org.apache.spark.sql.cassandra")
        .options(new HashMap<String, String>() {
            {
                put("keyspace", "mykeyspace");
                put("table", "mytable");
            }
        }).load();

   //Print data
   dataset.show();       
   spark.stop();
   }        
}

如果您仍然想使用 RDD，请使用下面的示例程序。

public class SparkCassandraRDDApplication {
public static void main(String[] args) {
    SparkConf conf = new SparkConf()
            .setAppName("SparkCassandraRDDApplication")
            .setMaster("local[2]")
            .set("spark.cassandra.connection.host", "127.0.0.1")
            .set("spark.cassandra.connection.port", "9042");

    JavaSparkContext sc = new JavaSparkContext(conf);

    //Read
    JavaRDD<UserData> resultsRDD = javaFunctions(sc).cassandraTable("mykeyspace", "mytable",CassandraJavaUtil.mapRowTo(UserData.class));

    //Print
    resultsRDD.foreach(data -> {
        System.out.println(data.id);
        System.out.println(data.username);
    });

    sc.stop();
  }
}

上面程序中使用的Javabean(UserData)如下。

public class UserData implements Serializable{  
  String id;
  String username;     
  public String getId() {
      return id;
  }
  public void setId(String id) {
      this.id = id;
  }
  public String getUsername() {
     return username;
  }
  public void setUsername(String username) {
     this.username = username;
   }    
}