tools.FileJoinerOptions.scala Maven / Gradle / Ivy

Go to download
// Copyright 2015-2022 by Carnegie Mellon University
// See license information in LICENSE.txt

package org.cert.netsa.mothra.tools

import org.apache.hadoop.fs.{Path => HadoopPath}
import org.cert.netsa.mothra.packer.CorePacker

class FileJoinerOptions extends ToolOptions("mothra-filejoiner") {

  note("Required options:\n")

  var targetDirs: Seq[HadoopPath] = Seq()
  arg[HadoopPath]("TARGET-1 .. TARGET-N").required().unbounded()
    .foreach(targetDirs :+= _)
    .text("HDFS directories in which to join files.")
    .validate(checkHadoopDirExists("Argument TARGET"))

  note("\nOptions:\n")

  help("help")
    .text("Print this message and exit.")

  version("version")
    .text(s"Print the version number of $toolName and exit.")

  note("")

  var minCountToJoin: Option[Int] = None
  opt[Int]("min-count-to-join").valueName("N")
    .foreach(n => minCountToJoin = Some(n))
    .text(s"Only process prefixes with at least N files. (Def. 2)")
    .validate(checkPos("min-count-to-join"))

  var spawnThread: Option[String] = None
  opt[String]("spawn-thread").valueName("MODE")
    .foreach(m => spawnThread = Some(m))
    .text("""Break work down in multiple threads on the basis of
                         'by-directory' or 'by-prefix'. (Def. 'by-directory')""")
    .validate({
      case "by-directory" => success
      case "by-prefix" => success
      case _ => failure(
        "Option --spawn-thread must be one of: 'by-directory', 'by-prefix'")
    })

  var maxThreads: Option[Int] = None
  opt[Int]("max-threads").valueName("N")
    .foreach(n => maxThreads = Some(n))
    .text("Run no more than N joiner threads at once. (Def. 6)")
    .validate(checkPos("max-threads"))

  note("\nOptions that control the format of joined files:\n")

  var compression: Option[String] = None
  opt[String]("compression").valueName("CODEC")
    .foreach(c => compression = Some(parseCompression(c)))
    .text(s"Compress joined files using this method.${
      if ( CorePacker.DEFAULT_COMPRESSION == "" ) ""
        else s" (Def. ${CorePacker.DEFAULT_COMPRESSION})"}")
    .validate(checkCompression("compression"))

  var maximumSize: Option[Long] = None
  opt[Long]("maximum-size").valueName("N")
    .foreach(n => maximumSize = Some(n))
    .text("Close output files after their size reaches N bytes.")
    .validate(checkPos("maximum-size"))

}

// @LICENSE_FOOTER@
//
// Copyright 2015-2022 Carnegie Mellon University. All Rights Reserved.
//
// This material is based upon work funded and supported by the
// Department of Defense and Department of Homeland Security under
// Contract No. FA8702-15-D-0002 with Carnegie Mellon University for the
// operation of the Software Engineering Institute, a federally funded
// research and development center sponsored by the United States
// Department of Defense. The U.S. Government has license rights in this
// software pursuant to DFARS 252.227.7014.
//
// NO WARRANTY. THIS CARNEGIE MELLON UNIVERSITY AND SOFTWARE ENGINEERING
// INSTITUTE MATERIAL IS FURNISHED ON AN "AS-IS" BASIS. CARNEGIE MELLON
// UNIVERSITY MAKES NO WARRANTIES OF ANY KIND, EITHER EXPRESSED OR
// IMPLIED, AS TO ANY MATTER INCLUDING, BUT NOT LIMITED TO, WARRANTY OF
// FITNESS FOR PURPOSE OR MERCHANTABILITY, EXCLUSIVITY, OR RESULTS
// OBTAINED FROM USE OF THE MATERIAL. CARNEGIE MELLON UNIVERSITY DOES NOT
// MAKE ANY WARRANTY OF ANY KIND WITH RESPECT TO FREEDOM FROM PATENT,
// TRADEMARK, OR COPYRIGHT INFRINGEMENT.
//
// Released under a GNU GPL 2.0-style license, please see LICENSE.txt or
// contact [email protected] for full terms.
//
// [DISTRIBUTION STATEMENT A] This material has been approved for public
// release and unlimited distribution. Please see Copyright notice for
// non-US Government use and distribution.
//
// Carnegie Mellon(R) and CERT(R) are registered in the U.S. Patent and
// Trademark Office by Carnegie Mellon University.
//
// This software includes and/or makes use of third party software each
// subject to its own license as detailed in LICENSE-thirdparty.tx
//
// DM20-1143