Scala CLI script to find Top X largest files by line counts in a given directory (including sub-directories)

find_largest_files.sc

//> using scala 3
//> using lib "com.lihaoyi::os-lib::0.9.0"

import scala.util.Try
// args(0) fails with java.lang.ArrayIndexOutOfBoundsException if no argument was provided by the user
val inputDir: Try[String] = Try(args(0))
// Default input directory is current working directory where the script is being run at.
val directory: os.Path = inputDir.map(os.Path(_)).getOrElse(os.pwd)
// Default number of largest files to show is 5.
val topN: Int = Try(args(1).toInt).getOrElse(5)
// Default file type is scala
val fileType: String = Try(args(2)).getOrElse("scala").toLowerCase()

def isFileOfType(path: os.Path, fileType: String): Boolean = {
  val ext: String = path.ext.toLowerCase()
  os.isFile(path) && (fileType match {
    case "scala"      => ext == "scala" || ext == "sc"
    case "java"       => ext == "java"
    case "python"     => ext == "py"
    case "sql"        => ext == "sql"
    case "text"       => ext == "txt"
    case "json"       => ext == "json"
    case "xml"        => ext == "xml"
    case "yaml"       => ext == "yaml" || ext == "yml"
    case "markdown"   => ext == "md"
    case "html"       => ext == "html"
    case "css"        => ext == "css"
    case "javascript" => ext == "js"
    case "typescript" => ext == "ts"
    case "shell"      => ext == "sh"
    case _            => ext == fileType || ext == s".$fileType"
  })

}

println(s"Finding top $topN largest ${fileType.toUpperCase()} files in $directory")

os
  .walk(directory)
  .filter(path => isFileOfType(path, fileType))
  .map(path => (path, os.read.lines(path).size))
  .sortBy((path, lineCount) => lineCount) // short form: sortBy(_._2)
  .reverse
  .take(topN)
  .foreach { (path, lineCount) =>
    val relativeFilePath: String =
      directory.toNIO.toUri().relativize(path.toNIO.toUri()).getPath
    println(s"$lineCount $relativeFilePath")
  }

/*
 * How to run this script:
 $  scala-cli https://gist.github.com/ganeshchand/6ff6e408b5144de44055d5ca17516769 -- /Users/Shared/repos/opensource/delta 5 scala
   Finding top 5 largest SCALA files in /Users/Shared/repos/opensource/delta
   38153 benchmarks/src/main/scala/benchmark/TPCDSBenchmarkQueries.scala
   5305 core/src/test/scala/org/apache/spark/sql/delta/MergeIntoSuiteBase.scala
   3060 core/src/test/scala/org/apache/spark/sql/delta/DeltaSuite.scala
   2996 core/src/main/scala/org/apache/spark/sql/delta/DeltaErrors.scala
   2785 core/src/test/scala/org/apache/spark/sql/delta/DeltaErrorsSuite.scala
 */