将数据加载到源中没有分隔符的Spark Dataframe中

import org.apache.spark.sql.execution.datasources.FileFormat
import org.apache.spark.sql.execution.datasources.FileFormatWriter
import org.apache.spark.sql.execution.datasources.OutputWriterFactory
import org.apache.spark.sql.execution.datasources.PartitionedFile
import org.apache.spark.sql.execution.datasources.SchemaPruning
import org.apache.spark.sql.execution.datasources.TextBasedFileFormat
import org.apache.spark.sql.sources.Filter
import org.apache.spark.sql.sources.PrunedScan
import org.apache.spark.sql.sources.TableScan
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.{DataFrame, SQLContext, SparkSession}
import org.apache.spark.sql.execution.datasources.FileFormat
import org.apache.spark.sql.execution.datasources.FileFormatWriter
import org.apache.spark.sql.execution.datasources.OutputWriterFactory
import org.apache.spark.sql.execution.datasources.PartitionedFile
import org.apache.spark.sql.execution.datasources.SchemaPruning
import org.apache.spark.sql.execution.datasources.TextBasedFileFormat
import org.apache.spark.sql.sources.Filter
import org.apache.spark.sql.sources.PrunedScan
import org.apache.spark.sql.sources.TableScan
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.{DataFrame, SQLContext, SparkSession}

class CustomFileFormat extends TextBasedFileFormat with Serializable {
  override def isSplitable(
      sparkSession: SparkSession,
      options: Map[String, String],
      path: Path): Boolean = false

  override def inferSchema(
      sparkSession: SparkSession,
      options: Map[String, String],
      files: Seq[FileStatus]): Option[StructType] = {
    // 指定数据的模式，例如：
    Some(StructType(Seq(StructField("column1", StringType), StructField("column2", IntegerType))))
  }

  override def buildReader(
      sparkSession: SparkSession,
      dataSchema: StructType,
      partitionSchema: StructType,
      requiredSchema: StructType,
      filters: Seq[Filter],
      options: Map[String, String],
      hadoopConf: Configuration): PartitionedFile => Iterator[InternalRow] = {
    // 在这里实现如何读取没有分隔符的数据，并将其转换为Spark Dataframe
    (file: PartitionedFile) => {
      val fileContent = readFileContent(file.filePath, hadoopConf)
      val rows = fileContent.split("\n").map { line =>
        val Array(column1, column2) = line.split(":")
        InternalRow(column1, column2.toInt)
      }
      rows.iterator
    }
  }
}

object CustomFileFormat {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder()
      .appName("CustomFileFormat")
      .getOrCreate()

    val customFileFormat = new CustomFileFormat()
    spark.sqlContext.experimental.extraFileFormats += "custom" -> customFileFormat

    val dataframe = spark.read
      .format("custom")
      .load("path/to/data")

    dataframe.show()
  }
}