Load Avro files and extract json string as dataframe

AvroJsonToDf.scala

import org.apache.spark.sql.functions.udf
import spark.implicits._

// read avro
val input = "/Users/hakanilter/dev/workspace/mc/data/avroFiles/*"
val data = spark.read
            .format("com.databricks.spark.avro")
            .option("header","true")
            .load(input)

// convert to json
val convertString = udf((payload: Array[Byte]) => new String(payload))
val rdd = data.select("body").withColumn("body", convertString(data("body"))).rdd.map(_.getAs[String](0))

val df = spark.read.json(rdd)
df.printSchema