Update chen to bring c fullname improvements (#150)

Signed-off-by: Prabhu Subramanian <prabhu@appthreat.com>

.scalafmt.conf

@@ -1,10 +1,11 @@
-version = 3.8.1
+version = 3.8.2
 runner.dialect = scala3
 preset = IntelliJ
 maxColumn = 100
 align.preset = true
 
 indent.main = 4
+indent.significant = 2
 
 newlines.source = keep
 rewrite.scala3.convertToNewSyntax = true

README.md

@@ -184,10 +184,10 @@ docker run --rm -v /tmp:/tmp -v $HOME:$HOME -v $(pwd):/app:rw -it ghcr.io/appthr
 ## Languages supported
 
 - C/C++
-- H (C/C++ Header files alone)
+- H (C/C++ Header and pre-processed .i files alone)
 - Java (Requires compilation)
 - Jar
-- Android APK (Requires Android SDK. Set the environment variable `ANDROID_HOME`)
+- Android APK (Requires Android SDK. Set the environment variable `ANDROID_HOME` or use the container image.)
 - JavaScript
 - TypeScript
 - Python

build.sbt

@@ -1,9 +1,9 @@
 name                     := "atom"
 ThisBuild / organization := "io.appthreat"
-ThisBuild / version      := "2.0.16"
+ThisBuild / version      := "2.0.17"
 ThisBuild / scalaVersion := "3.4.2"
 
-val chenVersion      = "2.1.2"
+val chenVersion      = "2.1.4"
 
 lazy val atom = Projects.atom
 

codemeta.json

@@ -7,7 +7,7 @@
   "downloadUrl": "https://github.com/AppThreat/atom",
   "issueTracker": "https://github.com/AppThreat/atom/issues",
   "name": "atom",
-  "version": "2.0.16",
+  "version": "2.0.17",
   "description": "Atom is a novel intermediate representation for next-generation code analysis.",
   "applicationCategory": "code-analysis",
   "keywords": [

src/main/scala/io/appthreat/atom/dataflows/DataFlowGraph.scala

@@ -8,48 +8,48 @@ import scala.collection.mutable
 
 private class DataFlowGraph(nodes: Set[Option[DFNode]]):
 
-    private type Path = List[Long]
-    // Maximum number of data-flow paths to compute
-    private val MAX_PATHS = 100
+  private type Path = List[Long]
+  // Maximum number of data-flow paths to compute
+  private val MAX_PATHS = 100
 
-    def paths: Set[Path] =
-        implicit val finalSet: mutable.Set[Path] = mutable.Set.empty
-        implicit val nMap: Map[Long, DFNode]     = nodes.map(x => x.get.id -> x.get).toMap
-        nodes.foreach { n =>
-            val currPath = List(n.get.id)
-            follow(currPath, n.get.out.flatMap(nMap.get))
-        }
-        finalSet.toSet
+  def paths: Set[Path] =
+    implicit val finalSet: mutable.Set[Path] = mutable.Set.empty
+    implicit val nMap: Map[Long, DFNode]     = nodes.map(x => x.get.id -> x.get).toMap
+    nodes.foreach { n =>
+      val currPath = List(n.get.id)
+      follow(currPath, n.get.out.flatMap(nMap.get))
+    }
+    finalSet.toSet
 
-    private def isSubList[A](short: List[A], long: List[A]): Boolean =
-        val sLong  = long.to(LazyList)
-        val sShort = short.to(LazyList)
-        sLong.tails.exists(_.startsWith(sShort))
+  private def isSubList[A](short: List[A], long: List[A]): Boolean =
+    val sLong  = long.to(LazyList)
+    val sShort = short.to(LazyList)
+    sLong.tails.exists(_.startsWith(sShort))
 
-    private def isSubList[A](lst: List[A])(implicit finalSet: mutable.Set[Path]): Boolean =
-        finalSet.filterNot(_.size < lst.size).exists(xs => isSubList(lst, xs))
+  private def isSubList[A](lst: List[A])(implicit finalSet: mutable.Set[Path]): Boolean =
+      finalSet.filterNot(_.size < lst.size).exists(xs => isSubList(lst, xs))
 
-    /** Is there an existing path that starts and ends with the same node
-      */
-    private def isDuplicate(finalSet: mutable.Set[Path], path: Path): Boolean =
-        finalSet.exists(apath =>
-            apath.headOption == path.headOption && apath.lastOption == path.lastOption
-        )
+  /** Is there an existing path that starts and ends with the same node
+    */
+  private def isDuplicate(finalSet: mutable.Set[Path], path: Path): Boolean =
+      finalSet.exists(apath =>
+          apath.headOption == path.headOption && apath.lastOption == path.lastOption
+      )
 
-    private def follow(currPath: List[Long], outNodes: Set[DFNode])(
-      implicit
-      nMap: Map[Long, DFNode],
-      finalSet: mutable.Set[Path]
-    ): Unit =
-        outNodes.foreach { x =>
-            val path  = currPath :+ x.id
-            val queue = x.out.filterNot(currPath.contains)
-            if queue.isEmpty then
-                if !isDuplicate(finalSet, path) && !isSubList(path) then
-                    finalSet.add(path)
-            else if finalSet.size < MAX_PATHS then
-                follow(path, queue.flatMap(nMap.get))
-        }
+  private def follow(currPath: List[Long], outNodes: Set[DFNode])(
+    implicit
+    nMap: Map[Long, DFNode],
+    finalSet: mutable.Set[Path]
+  ): Unit =
+      outNodes.foreach { x =>
+        val path  = currPath :+ x.id
+        val queue = x.out.filterNot(currPath.contains)
+        if queue.isEmpty then
+          if !isDuplicate(finalSet, path) && !isSubList(path) then
+            finalSet.add(path)
+        else if finalSet.size < MAX_PATHS then
+          follow(path, queue.flatMap(nMap.get))
+      }
 end DataFlowGraph
 
 private final case class DFNode(
@@ -62,33 +62,33 @@ private final case class DFNode(
 
 object DataFlowGraph:
 
-    private def DF_EDGES =
-        Set(EdgeTypes.REACHING_DEF, EdgeTypes.CALL, EdgeTypes.REF)
-    val exec: ExecutorService =
-        Executors.newVirtualThreadPerTaskExecutor()
+  private def DF_EDGES =
+      Set(EdgeTypes.REACHING_DEF, EdgeTypes.CALL, EdgeTypes.REF)
+  val exec: ExecutorService =
+      Executors.newVirtualThreadPerTaskExecutor()
 
-    def buildFromSlice(slice: DataFlowSlice): DataFlowGraph =
-        val dfNodes = slice.nodes
-            .flatMap {
-                case n if n.fullName.startsWith("<operator") || n.name.equals("this") => None
-                case n                                                                => Some(n)
-            }
-            .map(n => exec.submit(new DFNodeTask(slice, n)))
-            .map(TimedGet)
-            .filter(_.isDefined)
-        new DataFlowGraph(dfNodes)
+  def buildFromSlice(slice: DataFlowSlice): DataFlowGraph =
+    val dfNodes = slice.nodes
+        .flatMap {
+            case n if n.fullName.startsWith("<operator") || n.name.equals("this") => None
+            case n                                                                => Some(n)
+        }
+        .map(n => exec.submit(new DFNodeTask(slice, n)))
+        .map(TimedGet)
+        .filter(_.isDefined)
+    new DataFlowGraph(dfNodes)
 
-    private def TimedGet(dfn: Future[DFNode]) =
-        try
-            Option(dfn.get(5, TimeUnit.SECONDS))
-        catch
-            case _: Throwable => None
+  private def TimedGet(dfn: Future[DFNode]) =
+      try
+        Option(dfn.get(5, TimeUnit.SECONDS))
+      catch
+        case _: Throwable => None
 
-    private class DFNodeTask(slice: DataFlowSlice, n: SliceNode) extends Callable[DFNode]:
-        override def call(): DFNode =
-            val inEs =
-                slice.edges.filter(e => DF_EDGES.contains(e.label) && e.dst == n.id).map(_.src)
-            val outEs =
-                slice.edges.filter(e => DF_EDGES.contains(e.label) && e.src == n.id).map(_.dst)
-            DFNode(n.id, n.isExternal, n.label, inEs, outEs)
+  private class DFNodeTask(slice: DataFlowSlice, n: SliceNode) extends Callable[DFNode]:
+    override def call(): DFNode =
+      val inEs =
+          slice.edges.filter(e => DF_EDGES.contains(e.label) && e.dst == n.id).map(_.src)
+      val outEs =
+          slice.edges.filter(e => DF_EDGES.contains(e.label) && e.src == n.id).map(_.dst)
+      DFNode(n.id, n.isExternal, n.label, inEs, outEs)
 end DataFlowGraph

src/main/scala/io/appthreat/atom/dataflows/OssDataFlow.scala

@@ -6,10 +6,10 @@ import io.appthreat.dataflowengineoss.semanticsloader.{FlowSemantic, Semantics}
 import io.shiftleft.semanticcpg.layers.{LayerCreator, LayerCreatorContext, LayerCreatorOptions}
 
 object OssDataFlow:
-    val overlayName: String = "dataflowOss"
-    val description: String = "Layer to support the atom data flow tracker"
+  val overlayName: String = "dataflowOss"
+  val description: String = "Layer to support the atom data flow tracker"
 
-    def defaultOpts = new OssDataFlowOptions()
+  def defaultOpts = new OssDataFlowOptions()
 
 class OssDataFlowOptions(
   var maxNumberOfDefinitions: Int = 2000,
@@ -20,12 +20,12 @@ class OssDataFlow(opts: OssDataFlowOptions)(implicit
   s: Semantics = Semantics.fromList(DefaultSemantics().elements ++ opts.extraFlows)
 ) extends LayerCreator:
 
-    override val overlayName: String = OssDataFlow.overlayName
-    override val description: String = OssDataFlow.description
+  override val overlayName: String = OssDataFlow.overlayName
+  override val description: String = OssDataFlow.description
 
-    override def create(context: LayerCreatorContext, storeUndoInfo: Boolean): Unit =
-        val cpg                 = context.cpg
-        val enhancementExecList = Iterator(new DataDepsPass(cpg, opts.maxNumberOfDefinitions))
-        enhancementExecList.zipWithIndex.foreach { case (pass, index) =>
-            runPass(pass, context, storeUndoInfo, index)
-        }
+  override def create(context: LayerCreatorContext, storeUndoInfo: Boolean): Unit =
+    val cpg                 = context.cpg
+    val enhancementExecList = Iterator(new DataDepsPass(cpg, opts.maxNumberOfDefinitions))
+    enhancementExecList.zipWithIndex.foreach { case (pass, index) =>
+        runPass(pass, context, storeUndoInfo, index)
+    }

src/main/scala/io/appthreat/atom/frontends/clike/C2Atom.scala

@@ -12,8 +12,8 @@ import scala.util.Try
 
 class C2Atom extends X2CpgFrontend[Config]:
 
-    def createCpg(config: Config): Try[Cpg] =
-        withNewEmptyCpg(config.outputPath, config) { (cpg, config) =>
-            new MetaDataPass(cpg, Languages.NEWC, config.inputPath).createAndApply()
-            new AstCreationPass(cpg, config).createAndApply()
-        }
+  def createCpg(config: Config): Try[Cpg] =
+      withNewEmptyCpg(config.outputPath, config) { (cpg, config) =>
+        new MetaDataPass(cpg, Languages.NEWC, config.inputPath).createAndApply()
+        new AstCreationPass(cpg, config).createAndApply()
+      }