SpringBoot整合Apache Spark实现一个简单的数据分析功能

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-sql_2.12</artifactId>
    <version>3.4.2</version>
</dependency>

@Configuration
public class SparkConfig {
    @Bean
    public SparkSession sparkSession() {
        return SparkSession.builder()
                .appName("SpringBootSparkIntegration")
                .master("local[*]") // 在本地模式下运行
                .getOrCreate();
    }
}

@RestController
@RequestMapping("/test")
public class TestController {


    @Autowired
    private SparkSession sparkSession;

    @GetMapping("/analyze")
    public Map<String,Object> test(){
        Map<String,Object> ajax = new HashMap<>();

        // 创建 SparkContext
        JavaSparkContext sparkContext = JavaSparkContext.fromSparkContext(sparkSession.sparkContext());

        // 创建一个 RDD
        JavaRDD<Integer> dataRDD = sparkContext.parallelize(Arrays.asList(1, 2, 3, 4, 5));

        // 执行一些数据分析操作
        long count = dataRDD.count();

        List<Person> personList = Arrays.asList(new Person("Alice", 30), new Person("Bob", 25));
        // 创建一个 Dataset
        Dataset<Row> dataset = sparkSession.createDataFrame(personList, Person.class);

        // 执行一些 SQL 查询
        dataset.createOrReplaceTempView("people");

        Dataset<Row> result = sparkSession.sql("SELECT * FROM people");
        ajax.put("data",count);
        ajax.put("result",result.collectAsList().get(0).json());
        sparkSession.stop();
        return ajax;
    }
}

public class Person implements Serializable {
    private String name;
    private int age;

    public Person() {}

    public Person(String name, int age) {
        this.name = name;
        this.age = age;
    }

    // Getters and setters
}