scala在字符串中替换某个字符_从Spark Scala中的字母数字字符串中排除字母表和特殊字符...

import org.apache.spark.sql.functions._

import spark.implicits._

val df = Seq(

(1, "A", "PT5M", "xy20$", "M100.1!"),

(2, "B", "QU6N", "uv%", "N200.2&")

).toDF("C1", "C2", "C3", "C4", "C5")

val colsToExtract = Seq("C3", "C4", "C5")

val colsRemained = df.columns diff colsToExtract

val prefix = "New"

df.select(colsRemained.map(col) ++ colsToExtract.map(c =>

regexp_extract(col(c), "([0-9.]+)", 1).as(s"${prefix}$c")): _*

).show

// +---+---+-----+-----+-----+

// | C1| C2|NewC3|NewC4|NewC5|

// +---+---+-----+-----+-----+

// | 1| A| 5| 20|100.1|

// | 2| B| 6| |200.2|

// +---+---+-----+-----+-----+