Java Spark 简单示例（三）Spark SQL

本篇开始介绍Spark SQL的入门示例

Maven中引入

  org.apache.spark
  spark-sql_2.11
  2.3.1

在项目根目录下新建配置文件people.json

{"name":"Andy", "age":30, "sex":"女"}
{"name":"Justin", "age":19, "sex":"男"}
{"name":"Michael", "age":20, "sex":"男"}

代码示例

package com.yzy.spark;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.VoidFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;

public class demo4 {
    private static String appName = "spark.sql.demo";
    private static String master = "local[*]";

    public static void main(String[] args) {
        //初始化SparkSession
        SparkSession spark = SparkSession
                .builder()
                .appName(appName)
                .master(master)
                .getOrCreate();
        //读取元数据文件
        Dataset df = spark.read().json("people.json");
        //生成rdd
        JavaRDD rdd = df.toJavaRDD();
        //遍历
        rdd.foreach(new VoidFunction() {
            public void call(Row row) throws Exception {
                System.out.println(row.toString());
            }
        });

        spark.stop();
    }
}

输出结果

[30,Andy,女]
[19,Justin,男]
[20,Michael,男]

以上示例只是把元数据简单的打印出来，Spark SQL的功能远远不止如此，他甚至可以像写原生sql语句一样对数据进行过滤，下面列举一些Spark SQL的其他用法。也可以参考官方Demo，下载到本地，查看examples文件夹。

注意：示例中col()函数需导入

import static org.apache.spark.sql.functions.col;

自定义选择某些字段

df = df.select("name","age");
----------------------------------
输出结果：
[Andy,30]
[Justin,19]
[Michael,20]

对年龄字段进行加1计算

df = df.select(col("name"), col("age").plus(1));
----------------------------------
输出结果：
[Andy,31]
[Justin,20]
[Michael,21]

筛选年龄大于19岁的记录

df = df.filter(col("age").gt(19));
----------------------------------
输出结果：
[30,Andy,女]
[20,Michael,男]

按照年龄计数

df = df.groupBy("age").count();
----------------------------------
输出结果：
[30,1]
[19,1]
[20,1]

此外，我还可以使用原生sql来处理以上操作。首先我们要建立people视图

df.createOrReplaceTempView("people");

然后查询元数据就可以这样了

Dataset sqlDF = spark.sql("SELECT * FROM people");
JavaRDD rdd = sqlDF.toJavaRDD();
//......

注意：df.createOrReplaceTempView("people");方式创建的是临时视图，属于会话级别的。如果你希望在所有会话之间共享临时视图并保持活动状态，直到Spark应用程序终止，则可以创建全局临时视图。全局临时视图与系统保存的数据库绑定global_temp，我们必须使用限定名称来引用它，例如SELECT * FROM global_temp.view1。

全局视图示例

df.createGlobalTempView("people");
Dataset sqlDF = spark.sql("SELECT * FROM global_temp.people");
JavaRDD rdd = sqlDF.toJavaRDD();
//......

JavaRDD 转 Dataset

//people.txt
Michael, 29
Andy, 30
Justin, 19

package com.yzy.spark;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;

import java.io.Serializable;

public class demo6 {
    private static String appName = "spark.sql.demo";
    private static String master = "local[*]";

    public static void main(String[] args) {
        SparkSession spark = SparkSession
                .builder()
                .appName(appName)
                .master(master)
                .getOrCreate();

        JavaRDD peopleRDD = spark.read()
                .textFile("people.txt")
                .javaRDD()
                .map(new Function() {
                    public Person call(String s) throws Exception {
                        String[] parts = s.split(",");
                        Person person = new Person();
                        person.setName(parts[0]);
                        person.setAge(Integer.parseInt(parts[1].trim()));
                        return person;
                    }
                });

        Dataset peopleDF = spark.createDataFrame(peopleRDD, Person.class);
        peopleDF.show();
    }

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

        public String getName() {
            return name;
        }

        public void setName(String name) {
            this.name = name;
        }

        public int getAge() {
            return age;
        }

        public void setAge(int age) {
            this.age = age;
        }
    }
}

控制台输出

+---+-------+
|age|   name|
+---+-------+
| 29|Michael|
| 30|   Andy|
| 19| Justin|
+---+-------+