将txt文件转换为Dataset<Row>

import org.apache.spark.sql.{SparkSession, Row}
import org.apache.spark.sql.types.{StructType, StructField, StringType}

object TxtToDataset {
  def main(args: Array[String]): Unit = {
    // 创建SparkSession
    val spark = SparkSession.builder()
      .appName("TxtToDataset")
      .master("local[*]")
      .getOrCreate()

    // 读取txt文件
    val filePath = "path/to/your/file.txt"
    val data = spark.read.textFile(filePath)

    // 定义Schema
    val schema = new StructType()
      .add(StructField("column1", StringType, true))
      .add(StructField("column2", StringType, true))

    // 将RDD转换为Dataset<Row>
    import spark.implicits._
    val dataset = data.map(line => {
      val parts = line.split(",")
      Row(parts(0), parts(1))
    }).toDF(schema)

    // 显示数据
    dataset.show()

    // 停止SparkSession
    spark.stop()
  }
}