Spark 利用udf只对DataFrame其中几列操作，而不对所有列map

定义UDF

import org.apache.spark.sql.functions.udf

def theUDF = udf((inputColumn1: String, inputColumn2: BigInt)=>{
    var resultColumn = 0
    inputColumn1.split(",").foreach(item=>{
      if(java.lang.Long.valueOf(item).equals(inputColumn2)) {
        resultColumn = 1
      }
    })
    resultColumn
  })

调用

dataFrame.withColumn("result_column", 
    theUDF(col("input_column1"), col("input_column2"))
    )