尽量避免压平所有列。
创建了helper函数&您可以直接调用 df.explodeColumns 在Dataframe上。
下面的代码将展平多级数组和结构类型列。

scala> :paste
// Entering paste mode (ctrl-D to finish)

import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._
import scala.annotation.tailrec
import scala.util.Try

implicit class DFHelpers(df: DataFrame) {
    def columns = {
      val dfColumns = df.columns.map(_.toLowerCase)
      df.schema.fields.flatMap { data =>
        data match {
          case column if column.dataType.isInstanceOf[StructType] => {
            column.dataType.asInstanceOf[StructType].fields.map { field =>
              val columnName = column.name
              val fieldName = field.name
              col(s"${columnName}.${fieldName}").as(s"${columnName}_${fieldName}")
            }.toList
          }
          case column => List(col(s"${column.name}"))
        }
      }
    }

    def flatten: DataFrame = {
      val empty = df.schema.filter(_.dataType.isInstanceOf[StructType]).isEmpty
      empty match {
        case false =>
          df.select(columns: _*).flatten
        case _ => df
      }
    }
    def explodeColumns = {
      @tailrec
      def columns(cdf: DataFrame):DataFrame = cdf.schema.fields.filter(_.dataType.typeName == "array") match {
        case c if !c.isEmpty => columns(c.foldLeft(cdf)((dfa,field) => {
          dfa.withColumn(field.name,explode_outer(col(s"${field.name}"))).flatten
        }))
        case _ => cdf
      }
      columns(df.flatten)
    }
}

// Exiting paste mode, now interpreting.

import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._
import scala.annotation.tailrec
import scala.util.Try
defined class DFHelpers

扁平柱

scala> df.printSchema
root
 |-- stackoverflow: array (nullable = true)
 |    |-- element: struct (containsNull = true)
 |    |    |-- tag: struct (nullable = true)
 |    |    |    |-- author: string (nullable = true)
 |    |    |    |-- frameworks: array (nullable = true)
 |    |    |    |    |-- element: struct (containsNull = true)
 |    |    |    |    |    |-- id: long (nullable = true)
 |    |    |    |    |    |-- name: string (nullable = true)
 |    |    |    |-- id: long (nullable = true)
 |    |    |    |-- name: string (nullable = true)

scala> df.explodeColumns.printSchema
root
 |-- author: string (nullable = true)
 |-- frameworks_id: long (nullable = true)
 |-- frameworks_name: string (nullable = true)
 |-- id: long (nullable = true)
 |-- name: string (nullable = true)

scala>