json在读取数据的时候会读取schema描述信息,读取全部数据,才能确定类型
写出文件二种方式
//df2.write.mode(SaveMode.Append).json("out/boy")
df2.write.mode(SaveMode.Append).format("json").save("out2/boy")
读取文件二种方式
//获取数据的schema信息,每一行都有读取,将描述信息返回Driver端了
//val df: DataFrame = spark.read.json("data/user.json")
val df: DataFrame = spark.read.format("json").load("data/user.json")
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types.{DoubleType, IntegerType, StringType, StructField, StructType}
import org.apache.spark.sql.{DataFrame, Row, SaveMode, SparkSession}
object TXTChangeJSON {
def main(args: Array[String]): Unit = {
val spark = SparkSession.builder().appName(this.getClass.getSimpleName).master("local[*]").getOrCreate()
val sc = spark.sparkContext
val lines = sc.textFile("