Spark 连接mysql 及MongoDB

import java.io.Serializable;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SQLContext;

public class Main implements Serializable {

    private static final org.apache.log4j.Logger LOGGER = org.apache.log4j.Logger.getLogger(Main.class);

    private static final String MYSQL_DRIVER = "com.mysql.jdbc.Driver";
    private static final String MYSQL_USERNAME = "expertuser";
    private static final String MYSQL_PWD = "expertuser123";
    private static final String MYSQL_CONNECTION_URL =
            "jdbc:mysql://localhost:3306/employees?user=" + MYSQL_USERNAME + "&password=" + MYSQL_PWD;

    private static final JavaSparkContext sc =
            new JavaSparkContext(new SparkConf().setAppName("SparkJdbcDs").setMaster("local[*]"));

    private static final SQLContext sqlContext = new SQLContext(sc);

    public static void main(String[] args) {
        //Data source options
        Map<String, String> options = new HashMap<>();
        options.put("driver", MYSQL_DRIVER);
        options.put("url", MYSQL_CONNECTION_URL); //getConnection 返回一个已经打开的结构化数据库连接，JdbcRDD会自动维护关闭。
        options.put("dbtable",
                    "(select emp_no, concat_ws(‘ ‘, first_name, last_name) as full_name from employees) as employees_name");
//　　　　 sql 是查询语句，此查询语句必须包含两处占位符?来作为分割数据库ResulSet的参数，例如："select title, author from books where ? < = id and id <= ?"
        options.put("partitionColumn", "emp_no");//进行分区的表字段
        options.put("lowerBound", "10001");
//　　　　 owerBound, upperBound, numPartitions 分别为第一、第二占位符，partition的个数。例如，给出lowebound 1，upperbound 20， numpartitions 2，则查询分别为(1, 10)与(11, 20)
        options.put("upperBound", "499999");
        options.put("numPartitions", "10");

        //Load MySQL query result as DataFrame
        DataFrame jdbcDF = sqlContext.load("jdbc", options);
        JavaRDD<Row> rows = jdbcDF.toJavaRDD(); 

        List<Row> employeeFullNameRows = jdbcDF.collectAsList();

        for (Row employeeFullNameRow : employeeFullNameRows) {
            LOGGER.info(employeeFullNameRow);
        }
    }
}