使用Spark/Scala将嵌套的JSON转换为DataFrame

import org.apache.spark.sql.{SparkSession, DataFrame}
import org.apache.spark.sql.functions._

val spark = SparkSession.builder()
  .appName("JSON to DataFrame")
  .getOrCreate()

val json = spark.read.json("path/to/json/file.json")

def flattenNestedJSON(df: DataFrame): DataFrame = {
  val fields = df.schema.fields

  fields.foldLeft(df) { (acc, field) =>
    field.dataType match {
      case st: StructType =>
        val fieldNames = st.fieldNames.map(name => col(s"${field.name}.$name").alias(s"${field.name}_$name"))
        acc.select(col("*") +: fieldNames: _*).drop(field.name)
      case _ => acc
    }
  }
}

val flattenedDF = flattenNestedJSON(json)

flattenedDF.printSchema()