Spark-Es-To-Es

<repositories>
        <repository>
            <id>central</id>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
        </repository>
    </repositories>


    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <spark.version>2.3.3</spark.version>
        <elasticsearch.version>5.6.9</elasticsearch.version>
    </properties>


    <dependencies>
        <dependency>
            <groupId>org.elasticsearch</groupId>
            <artifactId>elasticsearch-spark-20_2.11</artifactId>
            <version>${elasticsearch.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-yarn_2.11</artifactId>
            <version>${spark.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

    </dependencies>


    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.0</version>
                <configuration>
                    <encoding>utf-8</encoding><!-- 指定项目源文件编码 -->
                    <source>${maven.compiler.source}</source><!-- 指定项目源文件jdk版本 -->
                    <target>${maven.compiler.target}</target><!-- 指定项目生成目标文件的jdk版本 -->
                </configuration>
            </plugin>

        </plugins>
    </build>

Spark代码

import org.apache.log4j.Level;
import org.apache.log4j.Logger;
import org.apache.spark.SparkConf;
import org.apache.spark.sql.*;

import java.util.HashMap;
import java.util.Map;

public class SparkEsToEs{

    public static void main(String[] args) {

        Logger.getRootLogger().setLevel(Level.DEBUG);

        SparkConf sparkConf = new SparkConf().setMaster("local[1]").setAppName("SparkEsToEs");
        sparkConf.set("spark.sql.warehouse.dir","file:///D://test");

        SparkSession sparkSession = SparkSession.builder().config(sparkConf).getOrCreate();


        Dataset<Row> esDataset = sparkSession.read().format("es").options(initEsSourceOptions()).load("/goods_old_index/docs");

        //esDataset.show();
        Dataset<Row> esDatasetNew = esDataset.withColumn("new_data_key", functions.concat_ws("_",esDataset.col("goods_code"), esDataset.col("shop_code")));


        //写入es中，指定index/type
        esDatasetNew.write()
                .format("org.elasticsearch.spark.sql")
                .options(initEsDestOptions())
                .mode(SaveMode.Append)
                .save("/goods_new_index/docs");


    }

    private static Map<String, String> initEsSourceOptions() {
        Map<String, String> options = new HashMap<>(6);
        options.put("es.nodes", "127.0.0.1");
        options.put("es.port", "9200");

        options.put("es.mapping.id", "goods_code");

        /*options.put("es.write.operation", "upsert");
        options.put("es.index.auto.create", "true");
        options.put("es.nodes.wan.only", "true");*/
        return options;
    }

    private static Map<String, String> initEsDestOptions() {
        Map<String, String> options = new HashMap<>(6);
        options.put("es.nodes", "127.0.0.1");
        options.put("es.port", "9200");

        options.put("es.mapping.id", "new_data_key");

        /*options.put("es.write.operation", "upsert");
        options.put("es.index.auto.create", "true");*/
        return options;
    }
}