Scala子字符串并将其存储在DF中。

val originalString = "This is a sample string"
val subString = originalString.substring(startIndex, endIndex)

import org.apache.spark.sql.{SparkSession, Row}
import org.apache.spark.sql.types.{StructType, StructField, StringType}

val spark = SparkSession.builder()
  .appName("SubstringExample")
  .getOrCreate()

val schema = StructType(Seq(
  StructField("original_string", StringType, nullable = false),
  StructField("sub_string", StringType, nullable = false)
))

val originalStrings = Seq("This is a sample string", "Another example string")
val rdd = spark.sparkContext.parallelize(originalStrings).map{ originalString =>
  val subString = originalString.substring(startIndex, endIndex)
  Row(originalString, subString)
}

val df = spark.createDataFrame(rdd, schema)