读取嵌套的json格式数据

直接正常读取json格式数据，然后某些下是嵌套的格式，直接使用 "列.属性" 就可以获取对应的值
【1】数据 文件 NestJsonFile 数据如下

{"name":"zhangsan","score":100,"infos":{"age":20,"gender":'man'}}
{"name":"lisi","score":70,"infos":{"age":21,"gender":'femal'}}
{"name":"wangwu","score":80,"infos":{"age":23,"gender":'man'}}
{"name":"maliu","score":50,"infos":{"age":16,"gender":'femal'}}
{"name":"tianqi","score":90,"infos":{"age":19,"gender":'man'}}

【2】scala代码实现

package com.it.baizhan.scalacode.sparksql.examples

import org.apache.spark.sql.SparkSession

/**
  * 读取嵌套的json格式数据
  *   直接正常读取json格式数据，然后某些下是嵌套的格式，直接使用"列.属性"就可以获取对应的值
  */
object ReadNestJsonFile {
  def main(args: Array[String]): Unit = {
    val session = SparkSession.builder().master("local").appName("test").getOrCreate()
    val df = session.read.json("./data/NestJsonFile")
    df.printSchema()
    
    /**
     * root
     * |-- infos: struct (nullable = true)
     * |    |-- age: long (nullable = true)
     * |    |-- gender: string (nullable = true)
     * |-- name: string (nullable = true)
     * |-- score: long (nullable = true)
     */

    df.createTempView("t")
    session.sql(
      """
        | select name,score,infos.gender,infos.age
        | from t
      """.stripMargin).show()

    /**
     * +--------+-----+------+---+
     * |    name|score|gender|age|
     * +--------+-----+------+---+
     * |zhangsan|  100|   man| 20|
     * |    lisi|   70| femal| 21|
     * |  wangwu|   80|   man| 23|
     * |   maliu|   50| femal| 16|
     * |  tianqi|   90|   man| 19|
     * +--------+-----+------+---+
     */

    import org.apache.spark.sql.functions._
//    df.select(col("name"),col("score"),col("infos.gender"),col("infos.age"))
//      .show(100,false)

  }

}