added documentation; restored functionality of the source's iterator; tidied code

This commit is contained in:
Fate-JH 2023-12-17 01:46:52 -05:00
parent a7bdcd5792
commit de1e5d2046

View file

@ -12,7 +12,7 @@ import scopt.OParser
import scala.collection.parallel.CollectionConverters._
import scala.io.{Codec, Source}
import scala.sys.process._
import scala.util.{Try, Using}
import scala.util.Using
case class Config(
inDir: String = System.getProperty("user.dir"),
@ -41,7 +41,7 @@ object DecodePackets {
.text("Input directory"),
opt[Unit]('p', "preprocessed")
.action((_, c) => c.copy(preprocessed = true))
.text("Files are already preprocessed gcapy ascii files (do not call gcapy)"),
.text("Files are already preprocessed gcapy ASCII files"),
opt[Unit]('s', "skip-existing")
.action((_, c) => c.copy(skipExisting = true))
.text("Skip files that already exist in out-dir"),
@ -91,6 +91,12 @@ object DecodePackets {
FileUtils.forceDelete(tmpFolder)
}
/**
* Enumerate over file names found in the given directory for later.
* @param directory where the files are found
* @param opts configuration entity where the files are collated
* @return configuration entity
*/
private def getAllFilesFromDirectory(directory: String, opts: Config): Config = {
val inDir = Paths.get(directory)
if (Files.exists(inDir) && Files.isDirectory(inDir)) {
@ -108,28 +114,37 @@ object DecodePackets {
}
}
/**
* The primary entry point into the process of parsing the packet capture files
* and producing the decoded packet data.
* Should be configurable for whatever state that the packet capture file can be structured.
* @param files all of the discovered files for consideration
* @param extension file extension being concatenated
* @param temporaryDirectory destination directory where files temporarily exist while being written
* @param outDirectory destination directory where the files are stored after being written
* @param skipExisting do not write a file that already exists at the destination directory
* @param readDecodeAndWrite next step of the file decoding process
*/
private def decodeFilesUsing(
files: Seq[File],
extension: String,
temporaryDirectory: File,
outDirectory: String,
skipExisting: Boolean,
decodingFunc: (File,BufferedWriter)=>Try[List[String]]
readDecodeAndWrite: (File,BufferedWriter)=>Unit
): Unit = {
files.par.foreach { file =>
val fileName = file.getName.split(extension)(0)
val outFilePath = outDirectory + "/" + fileName + ".txt"
val fileNameWithExtension = fileName + ".txt"
val outFilePath = outDirectory + "/" + fileNameWithExtension
val outFile = new File(outFilePath)
if (skipExisting && outFile.exists()) {
println(s"file $fileName skipped due to params")
} else {
val tmpFilePath = temporaryDirectory.getAbsolutePath + "/" + fileName + ".txt"
val tmpFilePath = temporaryDirectory.getAbsolutePath + "/" + fileNameWithExtension
val writer = new BufferedWriter(new FileWriter(new File(tmpFilePath), false))
try {
decodingFunc(file, writer).collect { lines =>
println(s"${lines.size} lines read from file $fileName")
processAndRewriteFileContents(writer, lines)
}
readDecodeAndWrite(file, writer)
writer.close()
Files.move(Paths.get(tmpFilePath), Paths.get(outFilePath), StandardCopyOption.REPLACE_EXISTING)
} catch {
@ -142,22 +157,41 @@ object DecodePackets {
}
}
private def preprocessed(file: File, writer: BufferedWriter): Try[List[String]] = {
/**
* Read data from ASCII transcribed gcapy files.
* @param file file to read
* @param writer writer for output
*/
private def preprocessed(file: File, writer: BufferedWriter): Unit = {
Using(Source.fromFile(file.getAbsolutePath)(decoder)) { source =>
source.getLines().toList
println(s"${decodeFileContents(writer, source.getLines())} lines read from file ${file.getName}")
}
}
private def gcapy(file: File, writer: BufferedWriter): Try[List[String]] = {
/**
* Read data from gcapy files.
* @param file file to read
* @param writer writer for output
*/
private def gcapy(file: File, writer: BufferedWriter): Unit = {
Using(Source.fromString(s"gcapy -xa '${file.getAbsolutePath}'" !!)) { source =>
source.getLines().toList
println(s"${decodeFileContents(writer, source.getLines())} lines read from file ${file.getName}")
}
}
/**
* Decode each line from the original file, decode it, then write it to the output file.
* @param writer writer for output
* @param lines raw packet data from the source
* @throws java.io.IOException if writing data goes incorrectly
* @return number of lines read from the source
*/
@throws(classOf[IOException])
private def processAndRewriteFileContents(writer: BufferedWriter, lines: List[String]): Unit = {
private def decodeFileContents(writer: BufferedWriter, lines: Iterator[String]): Int = {
var linesToSkip = 0
var linesRead: Int = 0
for (line <- lines.drop(1)) {
linesRead += 1
if (linesToSkip > 0) {
linesToSkip -= 1
} else {
@ -186,12 +220,25 @@ object DecodePackets {
writer.newLine()
}
}
linesRead
}
/** Traverse down any nested packets such as SlottedMetaPacket, MultiPacket and MultiPacketEx and add indent for each layer down
* The number of lines to skip will be returned so duplicate lines following SlottedMetaPackets in the gcapy output can be filtered out
*/
private def recursivelyHandleNestedPacket(decodedLine: String, writer: BufferedWriter, depth: Int = 0): Int = {
/**
* Traverse down any nested packets such as `SlottedMetaPacket`, `MultiPacket`, and `MultiPacketEx`
* and add indent for each layer down.
* A number of lines to skip will be returned so duplicate lines following the nested packet can be filtered out.
* @param decodedLine decoded packet data
* @param writer writer for output
* @param depth the number of layers to indent
* @throws java.io.IOException if writing data goes incorrectly
* @return current indent layer
*/
@throws(classOf[IOException])
private def recursivelyHandleNestedPacket(
decodedLine: String,
writer: BufferedWriter,
depth: Int = 0
): Int = {
if (decodedLine.indexOf("Failed to parse") >= 0) return depth
val regex = "(0x[a-f0-9]+)".r
val matches = regex.findAllIn(decodedLine)
@ -213,6 +260,11 @@ object DecodePackets {
linesToSkip
}
/**
* Reformat data common to gcapy packet data files and their derivation form of ASCII transcription.
* @param line original string
* @return transformed string
*/
private def shortGcapyString(line: String): String = {
val regex = "Game record ([0-9]+) at ([0-9.]+s) is from ([S|C]).* to ([S|C]).*contents (.*)".r
line match {
@ -222,11 +274,21 @@ object DecodePackets {
}
}
/**
* A nested packet contains more packets.
* @param decodedLine decoded packet data
* @return `true`, if the packet is nested; `false`, otherwise
*/
private def isNestedPacket(decodedLine: String): Boolean = {
// Also matches MultiPacketEx
decodedLine.indexOf("MultiPacket") >= 0 || decodedLine.indexOf("SlottedMetaPacket") >= 0
}
/**
* Actually decode the packet data.
* @param hexString raw packet data
* @return decoded packet data
*/
private def decodePacket(hexString: String): String = {
PacketCoding.decodePacket(ByteVector.fromValidHex(hexString)) match {
case Successful(value) => value.toString