扩展org.apache.spark.sql.Row功能：Spark Scala

您可以implicit像这样使用scala 类。

package utility
import org.apache.commons.lang3.StringUtils
import org.apache.spark.sql.Row

import scala.util.{Failure, Success, Try}

object MyRowExtensions {

/**

* RowExt.
*
* @param row
*/

implicit class RowExt(row: Row) {

/**
  * anyEmptyString
  *
  * @return Boolean
  */
def anyEmptyString(): Boolean = {
  val len = row.length
  var i = 0
  while (i < len) {
    if (StringUtils.isEmpty(row.get(i).toString)) {
      return true
    }
    i += 1
  }
  false
}

/**
  * anyString
  *
  * @param str
  * @return Boolean
  */
def anyStringMatched(matchStr: String): Boolean = {
  val len = row.length
  var i = 0
  while (i < len) {
    if (row.get(i).toString == matchStr) {
      return true
    }
    i += 1
  }
  false
}

/**
  * getAsOption
  *
  * @param fieldName
  * @tparam T
  * @return Option[T]
  */
def getAsOption[T](fieldName: String): Option[T] = {
  Try(row.getAs[T](fieldName)) match {
    case Success(value) => Some(value)
    case Failure(e) => None
  }
}

}

}
看起来这样......

import utility.MyRowExtensions.RowExt

myDataFrame.map(r => r.anyStringMatched("myteststring")).show
myDataFrame.filter(_.anyEmptyString).show