“Nutzen Sie Wert per Key von JSON Array” Code-Antworten

Nutzen Sie Wert per Key von JSON Array

import org.apache.spark.sql.types._
import org.apache.spark.sql.functions._
val df1 = spark.read.format("text").load("file path")
val schema = ArrayType(StructType(Array(
      StructField("key", StringType),
      StructField("value", StringType)
    )))

val arrayToMap = udf[Map[String, String], Seq[Row]] {
  array => array.map { case Row(key: String, value: String) => (key, value) }.toMap
}
val dfJSON = df1.withColumn("jsonData",from_json(col("value"),schema))
    .select("jsonData").withColumn("address", arrayToMap(col("jsonData")))
    .withColumn("city", when(col("address.city").isNotNull, col("address.city")).otherwise(lit(""))).withColumn("street",  when(col("address.street").isNotNull, col("address.street")).otherwise(lit("")))
dfJSON.printSchema()
dfJSON.show(false)