spark2.x deep into the end series six of the RDD Java API with Jdbcrdd read relational database

Before you learn any spark technology, be sure to understand spark correctly, as a guide: understanding spark correctly

Here is the use of the Spark RDD Java API to read data from a relational database using a derby local database, which can be a relational database such as MySQL or Oracle:

package com.twq.javaapi.java7;import org.apache.spark.api.java.javardd;import  Org.apache.spark.api.java.javasparkcontext;import org.apache.spark.api.java.function.function;import  org.apache.spark.rdd.jdbcrdd;import java.io.serializable;import java.sql.*;p Ublic class  javajdbcrddsuite implements serializable {    public static  void preparedata ()  throws ClassNotFoundException, SQLException {         //using local Database Derby, of course, you can use relational database such as MySQL          class.forname ("Org.apache.derby.jdbc.EmbeddedDriver");         Connection connection =                 drivermanager.getconnection ("Jdbc:derby:target/javajdbcrddsuitedb;create=true");         try&nbSp {            //Creates a table Foo,id is a self-increasing primary key, and data is an integer column             Statement create =  Connection.createstatement ();             Create.execute (                      "Create table foo ("  +                               "id integer not null generated always as identity  ( start with 1, increment by 1), " +                               "Data integer)");             create.close ();             //Inserting Data              preparedstatement insert = connection.preparestatement ("insert  Into foo (DATA)  values (?) ");             for  (int i = 1;  i <= 5; i++)  {                 insert.setint (1, i * 2);                 insert.executeupdate ();             }             insert.close ();        } catch  (SQLExceptIon e)  {            // If  TABLE&NBSP;DOESN ' T exist...            if   (E.getsqlstate () compareTo ("X0y32")  != 0)  {                 throw e;             }        } finally {             connection.close ();         }    }    public static void  SHUTDOWNDB ()  throws sqlexception {        try {             drivermanager.getconnection ("JDBC: Derby:target/javajdbcrddsuitedb;shutdOwn=true ");        } catch  (SQLException e)  {             // Throw if not  normal single database shutdown             // https://db.apache.org/derby/docs/10.2/ref/rrefexcept71493.html             if  (E.getsqlstate () compareTo ("08006")  != 0)  {                throw  e;            }         }    }    public static void  Main (String[] args)  throws Exception {         javasparkcontext sc = new&nbsp Javasparkcontext ("local",  "Javaapisuite");         //preparing data          preparedata ();         // Build jdbcrdd        javardd<integer> rdd =  Jdbcrdd.create (                 sc,                new  jdbcrdd.connectionfactory ()  {                      @Override                      public Connection  Getconnection ()  throws SQLException {                 &nbSp;       return drivermanager.getconnection ("jdbc:derby:target/ Javajdbcrddsuitedb ");                     }                 },                  "select data from foo where ? <= id and id  <= ? ",                 1, 5, 1,                 new Function<ResultSet, Integer> ()  {                      @Override                      public integer call (ResultSet &NBSP;R)  throws Exception {                         return r.getint (1);                      }                }         );         //results:  [2,  4, 6, 8, 10]        system.out.println ( Rdd.collect ());         shutdowndb ();         sc.stop ();     }}

For more information about the RDD API, you can refer to the following: Spark core RDD API Rationale

spark2.x deep into the end series six of the RDD Java API with Jdbcrdd read relational database