如何將JSONSchema從Camel大小寫轉換為小寫

我有一個帶有駝峰式鍵的 JSON 模式，我正在嘗試將所有資料型別轉換為小寫。我正面臨ArrayType.

 import org.apache.spark.sql.types.{ArrayType, IntegerType, StringType, StructField, StructType}
 import org.apache.spark.sql.types.{DataType, StructType}
 import spark.implicits._

 val spark: SparkSession = SparkSession.builder().enableHiveSupport().getOrCreate()
 var sample_schema = spark.read.json("path").schema

 def columnsToLowercase(schema: StructType): StructType = {
    def recurRename(schema: StructType): Seq[StructField] =
       schema.fields.map {
          case StructField(name, dtype: StructType, nullable, meta) =>
             StructField(name.toLowerCase, StructType(recurRename(dtype)), nullable, meta)                        
          case StructField(name, dtype, nullable, meta) =>
             StructField(name.toLowerCase, dtype, nullable, meta)
       }

    StructType(recurRename(schema))
 }

 val jsonDFrame: DataFrame = spark.read.schema(columnsToLowercase(sample_schema)).json("path")

示例架構：

root
 |-- id: string (nullable = true)
 |-- master: struct (nullable = true)
 |    |-- code: string (nullable = true)
 |    |-- provInfo: array (nullable = true)
 |    |    |-- element: struct (containsNull = true)
 |    |    |    |-- claimInfo: array (nullable = true)
 |    |    |    |    |-- element: struct (containsNull = true)
 |    |    |    |    |    |-- claimId: string (nullable = true)
 |    |    |    |-- demoInfo: struct (nullable = true)
 |    |    |    |    |-- family: struct (nullable = true)
 |    |    |    |    |    |-- outOrder: struct (nullable = true)
 |    |    |    |    |    |    |-- LocOut: boolean (nullable = true)
 |    |    |    |    |    |    |-- found: boolean (nullable = true)
 |    |-- claimAddr: array (nullable = true)
 |    |    |-- element: struct (containsNull = true)
 |    |    |    |-- address: string (nullable = true)
 |-- system: string (nullable = true)

uj5u.com熱心網友回復：

您應該能夠ArrayType通過添加另一個 case 子句來小寫嵌套的欄位。對于陣列列，您還需要檢查其子元素型別：

def columnsToLowercase(schema: StructType): StructType = {
     // ....
          case StructField(name, dtype: ArrayType, nullable, meta) => dtype.elementType match {
            case s: StructType => StructField(name.toLowerCase, ArrayType(StructType(recurRename(s)), true), nullable, meta)
            case dt => StructField(name.toLowerCase, dt, nullable, meta)
          }          
    //.... 
}

應用于您的架構：

df.printSchema
//root
// |-- id: string (nullable = true)
// |-- master: struct (nullable = true)
// |    |-- provInfo: struct (nullable = true)
// |    |    |-- claimInfo: array (nullable = true)
// |    |    |    |-- element: struct (containsNull = true)
// |    |    |    |    |-- claimId: string (nullable = true)
// |    |    |-- demoInfo: struct (nullable = true)
// |    |    |    |-- family: struct (nullable = true)
// |    |    |    |    |-- outOrder: struct (nullable = true)
// |    |    |    |    |    |-- LocOut: boolean (nullable = false)
// |    |    |    |    |    |-- found: boolean (nullable = false)
// |    |-- claimAddr: array (nullable = true)
// |    |    |-- element: struct (containsNull = true)
// |    |    |    |-- address: string (nullable = true)
// |-- system: string (nullable = true)


columnsToLowercase(df.schema).printTreeString()
//root
// |-- id: string (nullable = true)
// |-- master: struct (nullable = true)
// |    |-- provinfo: struct (nullable = true)
// |    |    |-- claiminfo: array (nullable = true)
// |    |    |    |-- element: struct (containsNull = true)
// |    |    |    |    |-- claimid: string (nullable = true)
// |    |    |-- demoinfo: struct (nullable = true)
// |    |    |    |-- family: struct (nullable = true)
// |    |    |    |    |-- outorder: struct (nullable = true)
// |    |    |    |    |    |-- locout: boolean (nullable = false)
// |    |    |    |    |    |-- found: boolean (nullable = false)
// |    |-- claimaddr: array (nullable = true)
// |    |    |-- element: struct (containsNull = true)
// |    |    |    |-- address: string (nullable = true)
// |-- system: string (nullable = true)

標籤：斯卡拉 阿帕奇火花

上一篇：SQLconcat函式，結合大小和顏色

下一篇：AzureDatabricksEventHub連接錯誤