spark中读取elasticsearch数据

在spark中读取es的数据

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>com.test</groupId>
     <artifactId>spark</artifactId>
     <version>0.0.1-SNAPSHOT</version>
     <packaging>jar</packaging>
  
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <scala.version>2.11.6</scala.version>
         <scala.maven.version>2.11.6</scala.maven.version>
     </properties>
  
     <dependencies>
         <dependency>
             <groupId>org.apache.spark</groupId>
             <artifactId>spark-core_2.10</artifactId>
             <version>1.3.1</version>
         </dependency>
         <!--<dependency>
             <groupId>org.apache.hadoop</groupId>
             <artifactId>hadoop-client</artifactId>
             <version>2.6.0</version>
         </dependency>-->
         <dependency>
             <groupId>org.elasticsearch</groupId>
             <artifactId>elasticsearch-spark_2.10</artifactId>
             <version>2.1.0.Beta4</version>
         </dependency>
     </dependencies>
  
     <build>
         <sourceDirectory>src/main/scala</sourceDirectory>
         <testSourceDirectory>src/test/scala</testSourceDirectory>
         <plugins>
             <plugin>
                 <groupId>org.scala-tools</groupId>
                 <artifactId>maven-scala-plugin</artifactId>
                 <version>2.15.2</version>
                 <executions>
                     <execution>
                         <goals>
                             <goal>compile</goal>
                             <!--<goal>testCompile</goal>-->
                         </goals>
                     </execution>
                 </executions>
                 <configuration>
                     <scalaVersion>${scala.version}</scalaVersion>
                 </configuration>
             </plugin>
             <plugin>
                 <artifactId>maven-assembly-plugin</artifactId>
                 <version>2.4</version>
                 <configuration>
                     <skipTests>true</skipTests>
                     <descriptorRefs>
                         <descriptorRef>jar-with-dependencies</descriptorRef>
                     </descriptorRefs>
                 </configuration>
                 <executions>
                     <execution>
                         <id>make-assembly</id>
                         <phase>package</phase>
                         <goals>
                             <goal>single</goal>
                         </goals>
                     </execution>
                 </executions>
             </plugin>
         </plugins>
     </build>
 </project>

esRDDTest.scala

package spark
  
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.elasticsearch.spark._
 
object esRDDTest {
    def main(args: Array[String]) {
        val conf = new SparkConf().setAppName("esRDDtest")
        conf.set("es.nodes", "127.0.0.1")
        conf.set("es.port", "8200")
        val sc = new SparkContext(conf)
        val resource = args(0)
        val query = args(1)
        val eslogs = sc.esRDD(resource, query)
        //……
    }
}