sparksql鏈接mysql

一、方法1：分別將兩張表中的數據加載爲DataFrame

 /* * 方法1：分別將兩張表中的數據加載爲DataFrame * */ /*
　　　　　Map<String,String> options = new HashMap<String,String>(); options.put("url","jdbc:mysql://localhost:3306/tset"); options.put("driver","com.mysql.jdbc.Driver"); options.put("user","root"); options.put("password","admin"); options.put("dbtable","information"); Dataset myinfromation = sqlContext.read().format("jdbc").options(options).load(); //若是須要多張表，則須要再put一遍  options.put("dbtable","score"); Dataset scores = sqlContext.read().format("jdbc").options(options).load();*/

二、方法2：分別將mysql中兩張表的數據加載爲DataFrame

 //方法2：分別將mysql中兩張表的數據加載爲DataFrame DataFrameReader reader = sqlContext.read().format("jdbc"); reader.option("url","jdbc:mysql://127.0.0.1:3306/test?serverTimezone=GMT"); reader.option("driver","com.mysql.cj.jdbc.Driver"); reader.option("user","root"); reader.option("password","admin"); reader.option("dbtable","information"); Dataset myinformation = reader.load(); reader.option("dbtable","score"); Dataset scores = reader.load();

三、問題：

在程序運行過程報錯

（1）

解決：

在idea中加入jar包

（2）運行報錯

The server time zone value 'Öйú±ê׼ʱ¼ä' is unrecognized or represents .....

解決：添加信息。

dbc:mysql://127.0.0.1:3306/test?serverTimezone=GMT

四、成功運行

附：程序源碼：

 

package sparkSQl; import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.sql.DataFrameReader; import org.apache.spark.sql.Dataset; import org.apache.spark.sql.SQLContext; import java.util.HashMap; import java.util.Map; public class mysqlToDataFrame { public static void main(String[] args) { //首先新建一個sparkconf定義參數
        SparkConf conf = new SparkConf().setMaster("local").setAppName("JDBCDataSource"); //建立sparkContext，是通往spark集羣的惟一通道
        JavaSparkContext sc = new JavaSparkContext(conf); //新建一個sparksql
        SQLContext sqlContext = new SQLContext(sc); //sparksql鏈接mysql
        /* * 方法1：分別將兩張表中的數據加載爲DataFrame * */
        /*Map<String,String> options = new HashMap<String,String>(); options.put("url","jdbc:mysql://localhost:3306/tset"); options.put("driver","com.mysql.jdbc.Driver"); options.put("user","root"); options.put("password","admin"); options.put("dbtable","information"); Dataset myinfromation = sqlContext.read().format("jdbc").options(options).load(); //若是須要多張表，則須要再put一遍 options.put("dbtable","score"); Dataset scores = sqlContext.read().format("jdbc").options(options).load();*/

        //方法2：分別將mysql中兩張表的數據加載爲DataFrame
        DataFrameReader reader = sqlContext.read().format("jdbc"); reader.option("url","jdbc:mysql://127.0.0.1:3306/test?serverTimezone=GMT"); reader.option("driver","com.mysql.cj.jdbc.Driver"); reader.option("user","root"); reader.option("password","admin"); reader.option("dbtable","information"); Dataset myinformation = reader.load(); reader.option("dbtable","score"); Dataset scores = reader.load(); //將兩個DataFrame轉換爲javapairrdd，執行join操做
        myinformation.registerTempTable("info"); scores.registerTempTable("score"); //定義sql語句
        String sql = "select info.name,age"
                +" from info join score"
                +" on(info.name=score.name)"
                +" where score.score>90"; Dataset sql2 = sqlContext.sql(sql); sql2.show(); } }