Spark load and join CSV files

spark-load-and-join-csv-files.java

package com.test;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;

import java.util.List;
import java.util.regex.Pattern;

public class SparkHello {
    private static final Pattern SPACE = Pattern.compile(" ");
    public static void main(String[] args) {
        // Define a configuration to use to interact with Spark
        SparkConf conf = new SparkConf().setMaster("local").setAppName("Work Count App");
        // Create a Java version of the Spark Context from the configuration
        JavaSparkContext sc = new JavaSparkContext(conf);


        SparkSession sparkSession = SparkSession.builder().appName("test").getOrCreate();
        Dataset<Row> left = sparkSession.read().option("header", true).csv("/tmp/side.left");
        Dataset<Row> right = sparkSession.read().option("header", true).csv("/tmp/side.right");

        Dataset<Row> j = left.join(right, "id");

        List<Row> l = j.collectAsList();

        for (Row row : l) {
            System.out.println(row.mkString());
        }

        sc.stop();
    }
}

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.2.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.2.1</version>
        </dependency>