json - 由于打印后显示的模式不正确，无法展平嵌套的 json

Question

我有一个 JSON 数据集，如下所示：

我使用以下方法将其展平：

def flattenDataframe(df: DataFrame): DataFrame = {
    //getting all the fields from schema
    val fields = df.schema.fields
    val fieldNames = fields.map(x => x.name)
    //length shows the number of fields inside dataframe
    val length = fields.length
    for (i <- 0 to fields.length - 1) {
      val field = fields(i)
      val fieldtype = field.dataType
      val fieldName = field.name
      fieldtype match {
        case arrayType: ArrayType =>
          val fieldName1 = fieldName
          val fieldNamesExcludingArray = fieldNames.filter(_ != fieldName1)
          val fieldNamesAndExplode = fieldNamesExcludingArray ++ Array(s"explode_outer($fieldName1) as $fieldName1")
          //val fieldNamesToSelect = (fieldNamesExcludingArray ++ Array(s"$fieldName1.*"))
          val explodedDf = df.selectExpr(fieldNamesAndExplode: _*)
          return flattenDataframe(explodedDf)

        case structType: StructType =>
          val childFieldnames = structType.fieldNames.map(childname => fieldName + "." + childname)
          val newfieldNames = fieldNames.filter(_ != fieldName) ++ childFieldnames
          val renamedcols = newfieldNames.map(x => (col(x.toString()).as(x.toString().replace(".", "_").replace("$", "_").replace("__", "_").replace(" ", "").replace("-", ""))))
          val explodedf = df.select(renamedcols: _*)
          return flattenDataframe(explodedf)
        case _ =>
      }
    }
    df
  }

展平后，我得到以下架构：

但是，我得到了data列，string但它应该像array of the struct. 那么我哪里错了？我正在使用带有 scala 的 Spark。

标签： jsonscalaapache-spark