• Home
• com.github.mrpowers
• spark-stringmetric_2.11
• 0.3.0
• source code
• PhoneticAlgorithms.scala

×

Project download

Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $

You can buy this project and download/modify it how often you want.

com.github.mrpowers.spark.stringmetric.PhoneticAlgorithms.scala Maven / Gradle / Ivy

package com.github.mrpowers.spark.stringmetric

import org.apache.spark.sql.functions._
import org.apache.commons.codec.language.{DoubleMetaphone, Nysiis, RefinedSoundex}

object PhoneticAlgorithms {

  val double_metaphone = udf[Option[String], String](doubleMetaphoneFun)

  def doubleMetaphoneFun(s1: String): Option[String] = {
    val str1 = Option(s1).getOrElse(return None)
    if (str1.equals("")) return None
    val dm = new DoubleMetaphone()
    Some(dm.encode(str1))
  }

  val nysiis = udf[Option[String], String](nysiisFun)

  def nysiisFun(s1: String): Option[String] = {
    val str1 = Option(s1).getOrElse(return None)
    val ny = new Nysiis()
    Some(ny.encode(str1))
  }

  val refined_soundex = udf[Option[String], String](refinedSoundexFun)

  def refinedSoundexFun(s1: String): Option[String] = {
    val str1 = Option(s1).getOrElse(return None)
    val rs = new RefinedSoundex()
    Some(rs.encode(str1))
  }

}