下面的解决方案将允许您Map resource_serialized 至 (String,String) 以后可以解析Map的表。

import org.apache.spark.SparkConf
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.{MapType, StringType}

object TestApp {
  def main(args: Array[String]): Unit = {
    val sparkConf: SparkConf = new SparkConf().setAppName("Loading Data").setMaster("local[*]")

    val spark = org.apache.spark.sql.SparkSession
      .builder
      .config(sparkConf)
      .appName("Test")
      .getOrCreate()

    val json = "[{\"resource_serialized\":\"{\\\"createdOn\\\":\\\"2000-07-20 00:00:00.0\\\",\\\"genderCode\\\":\\\"0\\\"}\",\"id\":\"00529e54-0f3d-4c76-9d3\"}]"

    import spark.implicits._
    val df = spark.read.json(Seq(json).toDS)
    val jsonColumn = from_json($"resource_serialized", MapType(StringType, StringType))
    val keysDF = df.select(explode(map_keys(jsonColumn))).distinct()
    val keys = keysDF.collect().map(f=>f.get(0))
    val keyCols = keys.map(f=> jsonColumn.getItem(f).as(f.toString))
    df.select( $"id" +: keyCols:_*).show(false)

  }
}

输出看起来像

+----------------------+---------------------+----------+
|id                    |createdOn            |genderCode|
+----------------------+---------------------+----------+
|00529e54-0f3d-4c76-9d3|2000-07-20 00:00:00.0|0         |
+----------------------+---------------------+----------+

使用 from_json 函数将json字符串转换为df列。 Example: ```
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._

val sch= new StructType().add("createdOn",StringType).add("genderCode",StringType)
df.select(col("id"),from_json(col("resource_serialized"),sch).alias("str")).
select("id","str.*").
show(10,false)

//result
//+----------------------+---------------------+----------+
//|id |createdOn |genderCode|
//+----------------------+---------------------+----------+
//|00529e54-0f3d-4c76-9d3|2000-07-20 00:00:00.0|0 |
//+----------------------+---------------------+----------+

如果您有一个有效的json，我们可以直接在 `spark.read.json` ```
val json = """[{"resource_serialized":{"createdOn":"2000-07-20 00:00:00.0","genderCode":"0"},"id":"00529e54-0f3d-4c76-9d3"}]"""

val sch=new StructType().
add("id",StringType).
add("resource_serialized", new StructType().add("createdOn",StringType).
add("genderCode",StringType))

spark.read.option("multiline","true").
schema(sch).
json(Seq(json).toDS).
select("id","resource_serialized.*").
show()
//+--------------------+--------------------+----------+
//|                  id|           createdOn|genderCode|
//+--------------------+--------------------+----------+
//|00529e54-0f3d-4c7...|2000-07-20 00:00:...|         0|
//+--------------------+--------------------+----------+