本文章主要通過spark實現udf自定義函式

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.Row
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.types.StructField
import org.apache.spark.sql.types.StringType

/**
 
 * @author jhp
  *         spark實現udf功能
*/
object UDF {
  
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf()
        .setMaster("local") 
        .setAppName("UDF")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
  
    // 構造模擬資料
val names = Array("Leo"
 
, "Marry", "Jack", "Tom") 
    val namesRDD = sc.parallelize(names, 5) 
    val namesRowRDD = namesRDD.map { name => Row(name) }
    val structType = StructType(Array(StructField("name", StringType, true)))  
    val namesDF = sqlContext.createDataFrame(namesRowRDD, structType) 
    
    // 註冊一張names
 
表
namesDF.registerTempTable("names")  
    
    // 定義和註冊自定義函式
// 定義函式：自己寫匿名函式
// 註冊函式：SQLContext.udf.register()
sqlContext.udf.register("strLen", (str: String) => str.length()) 
  
    // 使用自定義函式
sqlContext.sql("select name,strLen(name) from names")
        .collect()
        .foreach(println)  
  }
  
}