Scale正規マッチング

一、説明
1、Scalaの正規表現はJavaの文法規則を継承している.
2、Scalaはscalaを通過する.util.matchingパッケージのRegexクラスは正規表現をサポートします.
二、demoプレゼンテーション
1、コード

package com.hn.test

import scala.util.matching.Regex

object TestRegex {
  def main(args: Array[String]): Unit = {
    //val p1: Regex = "scala".r //.r        Regex  
    val p1: Regex = new Regex("scala") //         
    val str="scala is a good language,scala is best"

    val iterator: Regex.MatchIterator = p1.findAllIn(str)
    println(iterator.mkString(","))

    val matches: Iterator[Regex.Match] = p1.findAllMatchIn(str)
    println(matches.mkString(","))

    val maybeString: Option[String] = p1.findFirstIn(str)
    println(maybeString)

    val s: String = p1.replaceAllIn(str,"java")
    println(s)

    val s1: String = p1.replaceFirstIn(str,"java")
    println(s1)
  }
}

2、出力

scala,scala
scala,scala
Some(scala)
java is a good language,java is best
java is a good language,scala is best

三、小例
1、コード

package com.hn.test

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

object Test extends App {
  val conf: SparkConf = new SparkConf().setAppName("testRegular").setMaster("local[1]")
  val sc: SparkContext = new SparkContext(conf)
  sc.setLogLevel("WARN")
  val value: RDD[String] = sc.parallelize(Array("1","2","3","4","5","2","2","3"))

  // 2 3      
  val v_rdd: RDD[(String, Int)] = value
    //         
    .filter("[2|3]".r.findAllMatchIn(_).size > 0)
    .map((_,1)).reduceByKey(_+_)
  println(v_rdd.foreachPartition(x=>x.foreach(x=>{
    println(x._1+"_"+x._2)
  })))

}

2、出力

2_3
3_2
()