在java中使用Apache Spark Connector从Cassandra检索数据时出错

Question

10凯瑟琳

我在本地运行start-all.sh启动了Spark

然后我创建了这个类“SparkCassandraconnector”，它有一个连接spark和Cassandra的命令。

import org.apache.commons.lang.StringUtils;

import org.apache.spark.SparkConf;

import org.apache.spark.api.java.JavaRDD;

import org.apache.spark.api.java.JavaSparkContext;

import java.io.Serializable;

import static com.datastax.spark.connector.CassandraJavaUtil.javaFunctions;

public class SparkCassandraConnector  implements Serializable {
public static void main(String[] args) {

    SparkConf conf = new SparkConf().setAppName("Simple Application");

    conf.setMaster("spark://127.0.0.1:7077");
    conf.set("spark.cassandra.connection.host", "127.0.0.1");
    String[] jars = new String[10];
    jars[0] = "~/.m2/repository/com/datastax/spark/spark-cassandra-connector-java_2.10/1.1.0-alpha4/spark-cassandra-connector-java_2.10-1.1.0-alpha4.jar";
    jars[1] = "~/.m2/repository/com/datastax/cassandra/cassandra-driver-core/2.1.0/cassandra-driver-core-2.1.0.jar";
    jars[3] = "~/.m2/repository/com/datastax/spark/spark-cassandra-connector_2.10/1.1.0-alpha4/spark-cassandra-connector_2.10-1.1.0-alpha4.jar";
    jars[4] = "~/.m2/repository/com/datastax/cassandra/cassandra-driver-core/2.1.0/cassandra-driver-core-2.1.0.jar";
    jars[5] = "~/.m2/repository/org/apache/cassandra/cassandra-thrift/2.1.0/cassandra-thrift-2.1.0.jar";
    jars[6] = "~/.m2/repository/org/apache/cassandra/cassandra-clientutil/2.1.0/cassandra-clientutil-2.1.0.jar";
    conf = conf.setJars(jars);
    JavaSparkContext sc = new JavaSparkContext(conf);

    JavaRDD<String> rdd = javaFunctions(sc).cassandraTable("ks", "student", Student.class)
            .map(new org.apache.spark.api.java.function.Function<Student, String>() {
                @Override
                public String call(Student person) throws Exception {
                    return person.toString();
                }
            });
    System.out.println("Data as Person beans: \n" + StringUtils.join(rdd.collect(), "\n"));
}
public static class Student implements  Serializable{

    private Integer id;
    private String name;

    public Student(){

    }
    public Student(Integer id, String name) {
        this.id = id;
        this.name = name;
    }

    public Integer getId() {
        return id;
    }

    public void setId(Integer id) {
        this.id = id;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }
}

<dependencies>


    <!--Spark-->

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>com.datastax.cassandra</groupId>
        <artifactId>cassandra-driver-core</artifactId>
        <version>2.1.0</version>
    </dependency>
    <dependency>
        <groupId>com.datastax.spark</groupId>
        <artifactId>spark-cassandra-connector_2.10</artifactId>
        <version>1.1.0-alpha4</version>
    </dependency>

    <dependency>
        <groupId>com.datastax.spark</groupId>
        <artifactId>spark-cassandra-connector-java_2.10</artifactId>
        <version>1.1.0-alpha4</version>
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-catalyst_2.10</artifactId>
        <version>1.0.0</version>
    </dependency>
</dependencies>

Answer 1

在提供的jar中，缺少包含作业的jar，因此缺少student.class。一个快速修复它的方法是在项目的./target文件夹中添加jar。

另一种选择是将您的工作和所有依赖项打包到一个“uber jar”中，并将该uber jar作为仅声明的jar使用。查看maven shade插件。

还可以通过命令行使用spark-submit--jars选项提供JAR。