How can I create a Spark DataFrame from a nested array of struct element?

Question

I have read a JSON file into Spark. This file has the following structure:

scala> tweetBlob.printSchema
root
 |-- related: struct (nullable = true)
 |             


        

Answer 1

scala> import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.DataFrame

scala> import org.apache.spark.sql.types._
import org.apache.spark.sql.types._

scala> case class Bar(x: Int, y: String)
defined class Bar

scala> case class Foo(bar: Bar)
defined class Foo

scala> val df = sc.parallelize(Seq(Foo(Bar(1, "first")), Foo(Bar(2, "second")))).toDF
df: org.apache.spark.sql.DataFrame = [bar: struct]


scala> df.printSchema
root
 |-- bar: struct (nullable = true)
 |    |-- x: integer (nullable = false)
 |    |-- y: string (nullable = true)


scala> df.select("bar.*").printSchema
root
 |-- x: integer (nullable = true)
 |-- y: string (nullable = true)


scala>