Java版本
代码语言：javascript复制Map<String, String> options = new HashMap<String, String>();
options.put("url", "jdbc:mysql://spark1:3306/testdb");
options.put("dbtable", "students");
DataFrame jdbcDF = sqlContext.read().format("jdbc").options(options).load();Scala版本
代码语言：javascript复制val jdbcDF = sqlContext.read.format("jdbc").options(Map("url" -> "jdbc:mysql://spark1:3306/testdb", "dbtable" -> "students")).load()案例：查询分数大于80分的学生信息
首先创建mysql
代码语言：javascript复制grant all on testdb.* to ''@'spark1' with grant option;
grant all privileges on testdb.* to 'test'@'%' identified by 'test';
grant all privileges on testdb.* to 'test'@'localhost' identified by 'test';
grant all privileges on testdb.* to 'test'@'spark1' identified by 'test';
flush privileges;
create database if not exists hive_metadata;
grant all privileges on hive_metadata.* to 'hive'@'%' identified by 'hive';
grant all privileges on hive_metadata.* to 'hive'@'localhost' identified by 'hive';
grant all privileges on hive_metadata.* to 'hive'@'spark1' identified by 'hive';
flush privileges;
create database testdb;
Use testdb;
create table student_infos(name varchar(20),age integer)
create table student_scores(name varchar(20), scores integer)
insert into student_infos values('leo',18),('marry',17),('jack',19);
insert into student_scores values('leo',88),('marry',97),('jack',59);
create table good_student_infos(name varchar(20), age integer ,scores integer)
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.Statement;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
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.api.java.function.PairFunction;
import org.apache.spark.api.java.function.VoidFunction;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SQLContext;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import scala.Tuple2;
/**
* JDBC数据源
* @author Administrator
*
*/
public class JDBCDataSource {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("JDBCDataSource");
JavaSparkContext sc = new JavaSparkContext(conf);
SQLContext sqlContext = new SQLContext(sc);
// 总结一下
// jdbc数据源
// 首先，是通过SQLContext的read系列方法，将mysql中的数据加载为DataFrame
// 然后可以将DataFrame转换为RDD，使用Spark Core提供的各种算子进行操作
// 最后可以将得到的数据结果，通过foreach()算子，写入mysql、hbase、redis等等db / cache中
// 分别将mysql中两张表的数据加载为DataFrame
Map<String, String> options = new HashMap<String, String>();
options.put("url", "jdbc:mysql://spark1:3306/testdb");
options.put("dbtable", "student_infos");
DataFrame studentInfosDF = sqlContext.read().format("jdbc").options(options).load();
options.put("dbtable", "student_scores");
DataFrame studentScoresDF = sqlContext.read().format("jdbc").options(options).load();
// 将两个DataFrame转换为JavaPairRDD，执行join操作
JavaPairRDD<String, Tuple2<Integer, Integer>> studentsRDD = studentInfosDF.javaRDD().mapToPair(
new PairFunction<Row, String, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Tuple2<String, Integer> call(Row row) throws Exception {
return new Tuple2<String, Integer>(row.getString(0),
Integer.valueOf(String.valueOf(row.get(1))));
}
}).join(studentScoresDF.javaRDD().mapToPair(
new PairFunction<Row, String, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Tuple2<String, Integer> call(Row row) throws Exception {
return new Tuple2<String, Integer>(String.valueOf(row.get(0)),
Integer.valueOf(String.valueOf(row.get(1))));
}
}));
// 将JavaPairRDD转换为JavaRDD<Row>
JavaRDD<Row> studentRowsRDD = studentsRDD.map(
new Function<Tuple2<String,Tuple2<Integer,Integer>>, Row>() {
private static final long serialVersionUID = 1L;
@Override
public Row call(
Tuple2<String, Tuple2<Integer, Integer>> tuple) throws Exception {
return RowFactory.create(tuple._1, tuple._2._1, tuple._2._2);
}
});
// 过滤出分数大于80分的数据
JavaRDD<Row> filteredStudentRowsRDD = studentRowsRDD.filter(
new Function<Row, Boolean>() {
private static final long serialVersionUID = 1L;
@Override
public Boolean call(Row row) throws Exception {
if(row.getInt(2) > 80) {
return true;
}
return false;
}
});
// 转换为DataFrame
List<StructField> structFields = new ArrayList<StructField>();
structFields.add(DataTypes.createStructField("name", DataTypes.StringType, true));
structFields.add(DataTypes.createStructField("age", DataTypes.IntegerType, true));
structFields.add(DataTypes.createStructField("score", DataTypes.IntegerType, true));
StructType structType = DataTypes.createStructType(structFields);
DataFrame studentsDF = sqlContext.createDataFrame(filteredStudentRowsRDD, structType);
Row[] rows = studentsDF.collect();
for(Row row : rows) {
System.out.println(row);
}
// 将DataFrame中的数据保存到mysql表中
// 这种方式是在企业里很常用的，有可能是插入mysql、有可能是插入hbase，还有可能是插入redis缓
studentsDF.javaRDD().foreach(new VoidFunction<Row>() {
private static final long serialVersionUID = 1L;
@Override
public void call(Row row) throws Exception {
String sql = "insert into good_student_infos values(" "'" String.valueOf(row.getString(0)) "'," Integer.valueOf(String.valueOf(row.get(1))) "," Integer.valueOf(String.valueOf(row.get(2))) ")";
Class.forName("com.mysql.jdbc.Driver");
Connection conn = null;
Statement stmt = null;
try {
conn = DriverManager.getConnection(
"jdbc:mysql://spark1:3306/testdb", "", "");
stmt = conn.createStatement();
stmt.executeUpdate(sql);
} catch (Exception e) {
e.printStackTrace();
} finally {
if(stmt != null) {
stmt.close();
}
if(conn != null) {
conn.close();
}
}
}
});
sc.close();
}
}测试： Use testdb； Show tables; Select * from good_student_infos;
