1.使用函数get_json_object逐个取出json当层对象
object testdf {
def main(args: Array[String]): Unit = {
Logger.getLogger("org.apache.spark").setLevel(Level.ERROR)
val spark = SparkSession.builder().master("local[*]").appName("test app").getOrCreate()
import spark.implicits._
val ds = spark.createDataset(Seq("""{"name":"hrr","age":12,"subject":[{"name":"math","level":1}]}"""))
ds.show(false)
ds打印为:
+-------------------------------------------------------------+
|value |
+-------------------------------------------------------------+
|{"name":"hrr","age":12,"subject":[{"name":"math","level":1}]}|
+-------------------------------------------------------------+
ds.createOrReplace