import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan;
import org.apache.spark.sql.execution.SparkPlan;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

import java.util.Arrays;
import java.util.List;

public class SparkTask {

    public static void main(String[] args) {

        System.setProperty("HADOOP_HOME", "D:\\hadoop-3.0.3");
        System.setProperty("HIVE_HOME", "D:\\apache-hive-3.1.0-bin");
        System.setProperty("HIVE_CONF_DIR", "D:\\apache-hive-3.1.0-bin\\conf");

        SparkSession sparkSession = SparkSession
                .builder()
                .master("local[*]")
//                .config("spark.sql.queryExecutionListeners", "com.crock.listener.FieldLineageListener")  // 注册监听器
                .enableHiveSupport()
                .getOrCreate();

        // 创建示例数据
        List<Row> data = Arrays.asList(
                RowFactory.create(100, "Alice", 34),
                RowFactory.create(10, "Bob", 45),
                RowFactory.create(1,"Cathy", 29)
        );

        // 定义 schema
        StructType schema = new StructType(new StructField[]{
                new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
                new StructField("name", DataTypes.StringType, false, Metadata.empty()),
                new StructField("age", DataTypes.IntegerType, false, Metadata.empty())
        });

        // 创建 DataFrame
        Dataset<Row> dfA = sparkSession.createDataFrame(data, schema);

        // 创建示例数据
        List<Row> datab = Arrays.asList(
                RowFactory.create(100, "Alice", 34),
                RowFactory.create(10, "Bob", 45),
                RowFactory.create(1,"Cathy", 29)
        );

        // 定义 schema
        StructType schemab = new StructType(new StructField[]{
                new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
                new StructField("name", DataTypes.StringType, false, Metadata.empty()),
                new StructField("age", DataTypes.IntegerType, false, Metadata.empty())
        });

        // 创建 DataFrame
        Dataset<Row> dfB = sparkSession.createDataFrame(datab, schemab);

        sparkSession.sql("create table if not exists table_c (id int, name string)");

        // 创建临时视图（只在当前 session 有效）
        dfA.createOrReplaceTempView("table_a");
        dfB.createOrReplaceTempView("table_b");

        Dataset<Row> sql = sparkSession.sql("insert into table_c SELECT a.id, b.name FROM table_a a JOIN table_b b ON a.id = b.id");

//        Dataset<Row> sql = sparkSession.sql("with abc as (select 1 as id , 'abc' as name) SELECT a.id, b.name FROM table_a a JOIN table_b b ON a.id = b.id join abc on a.id=abc.id");
//        sql.explain(true);

//        sql.logicalPlan();
        System.out.println("---------------------------analyzer--------------------------------------");
        LogicalPlan analyzed = sql.queryExecution().analyzed();
        System.out.println(analyzed);
        System.out.println("---------------------------analyzer--------------------------------------");
        LogicalPlan optimizedPlan = sql.queryExecution().optimizedPlan();
        System.out.println(optimizedPlan);
        System.out.println("---------------------------物理执行计划--------------------------------------");
        SparkPlan sparkPlan = sql.queryExecution().sparkPlan();
        System.out.println(sparkPlan);
        System.out.println("---------------------------执行计划--------------------------------------");
        SparkPlan executedPlan = sql.queryExecution().executedPlan();
        System.out.println(executedPlan);

//        System.out.println(sql.queryExecution().logical());

    }

}

问题：

java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$POSIX.stat(Ljava/lang/String;)

下载 hadoop 配置 HADOOP_HOME 环境变量

通过 https://github.com/Zer0r3/winutils ，下载 winutils.exe、hadoop.dll 注意版本对应，winutils.exe 放到 %HADOOP_HOME%/bin 目录下，hadoop.dll 放到 c:/Windows/System32

----------------------------- 以下没用到 -----------------------------

下载 hadoop 源码
复制 org.apache.hadoop.io.nativeio.NativeIO 源码并新建 NativeIO.java

参考：https://zhuanlan.zhihu.com/p/551108454