split

import org.apache.spark.sql.{SparkSession, DataFrame}
import org.apache.spark.sql.functions._

object Main extends App {
  // Create SparkSession
  val spark = SparkSession.builder()
    .appName("DataFrameManipulation")
    .master("local[*]")
    .getOrCreate()

  // Dummy data
  val data = Seq(
    ("USER Apple is great"),
    ("USER Banana is tasty"),
    ("Orange is healthy")
  )

  // Create DataFrame
  val df = spark.createDataFrame(data).toDF("A")

  // DataFrame Transformation
  val dfWithSplit = df.withColumn("C", when(col("A").contains("USER Apple"), "USER Apple").otherwise(split(col("A"), " ").getItem(0)))
                      .withColumn("D", when(col("A").contains("USER Apple"), substring_index(col("A"), "USER Apple ", -1)).otherwise(substring_index(col("A"), " ", -1)))

  // Show result
  dfWithSplit.show()

  // Stop SparkSession
  spark.stop()
}



import org.apache.spark.sql.{SparkSession, DataFrame}
import org.apache.spark.sql.functions._

object Main extends App {
  // Create SparkSession
  val spark = SparkSession.builder()
    .appName("DataFrameManipulation")
    .master("local[*]")
    .getOrCreate()

  // Dummy data
  val data = Seq(
    ("USER Apple is great"),
    ("USER Banana is tasty"),
    ("Orange is healthy")
  )

  // Create DataFrame
  val df = data.toDF("A")

  // DataFrame Transformation
  val dfWithRegex = df.withColumn("C", regexp_extract(col("A"), "USER\\s+(\\w+)", 1))
                      .withColumn("D", regexp_replace(col("A"), "USER\\s+\\w+\\s*", ""))

  // Show result
  dfWithRegex.show()

  // Stop SparkSession
  spark.stop()
}