[Gosrc2cpg] download dependencies and caching improvements

joern-cli/frontends/gosrc2cpg/src/main/scala/io/joern/gosrc2cpg/GoSrc2Cpg.scala

@@ -22,31 +22,42 @@ import io.shiftleft.codepropertygraph.generated.Languages
 import java.nio.file.Paths
 import scala.util.Try
 
-class GoSrc2Cpg extends X2CpgFrontend[Config] {
+class GoSrc2Cpg(goGlobalOption: Option[GoGlobal] = Option(GoGlobal())) extends X2CpgFrontend[Config] {
   private val report: Report = new Report()
 
+  private var goMod: Option[GoModHelper] = None
   def createCpg(config: Config): Try[Cpg] = {
     withNewEmptyCpg(config.outputPath, config) { (cpg, config) =>
       File.usingTemporaryDirectory("gosrc2cpgOut") { tmpDir =>
-        val goGlobal = GoGlobal()
-        new MetaDataPass(cpg, Languages.GOLANG, config.inputPath).createAndApply()
-        val astGenResult = new AstGenRunner(config).execute(tmpDir).asInstanceOf[GoAstGenRunnerResult]
-        val goMod = new GoModHelper(
-          Some(config),
-          astGenResult.parsedModFile.flatMap(modFile => GoAstJsonParser.readModFile(Paths.get(modFile)).map(x => x))
-        )
-        if (config.fetchDependencies) {
-          goGlobal.processingDependencies = true
-          new DownloadDependenciesPass(goMod, goGlobal, config).process()
-          goGlobal.processingDependencies = false
-        }
-        val astCreators =
-          new MethodAndTypeCacheBuilderPass(Some(cpg), astGenResult.parsedFiles, config, goMod, goGlobal).process()
-        new AstCreationPass(cpg, astCreators, report).createAndApply()
-        if goGlobal.pkgLevelVarAndConstantAstMap.size() > 0 then
-          new PackageCtorCreationPass(cpg, config, goGlobal).createAndApply()
-        report.print()
+        goGlobalOption
+          .orElse(Option(GoGlobal()))
+          .foreach(goGlobal => {
+            new MetaDataPass(cpg, Languages.GOLANG, config.inputPath).createAndApply()
+            val astGenResult = new AstGenRunner(config).execute(tmpDir).asInstanceOf[GoAstGenRunnerResult]
+            goMod = Some(
+              new GoModHelper(
+                Some(config),
+                astGenResult.parsedModFile
+                  .flatMap(modFile => GoAstJsonParser.readModFile(Paths.get(modFile)).map(x => x))
+              )
+            )
+            goGlobal.mainModule = goMod.flatMap(modHelper => modHelper.getModMetaData().map(mod => mod.module.name))
+            val astCreators =
+              new MethodAndTypeCacheBuilderPass(Some(cpg), astGenResult.parsedFiles, config, goMod.get, goGlobal)
+                .process()
+            if (config.fetchDependencies) {
+              goGlobal.processingDependencies = true
+              new DownloadDependenciesPass(goMod.get, goGlobal, config).process()
+              goGlobal.processingDependencies = false
+            }
+            new AstCreationPass(cpg, astCreators, report).createAndApply()
+            if goGlobal.pkgLevelVarAndConstantAstMap.size() > 0 then
+              new PackageCtorCreationPass(cpg, config, goGlobal).createAndApply()
+            report.print()
+          })
       }
     }
   }
+
+  def getGoModHelper: GoModHelper = goMod.get
 }

joern-cli/frontends/gosrc2cpg/src/main/scala/io/joern/gosrc2cpg/astcreation/AstCreatorHelper.scala

@@ -131,8 +131,8 @@ trait AstCreatorHelper { this: AstCreator =>
       .toMap
   }
 
-  protected def resolveAliasToFullName(alias: String, typeOrMethodName: String): String = {
-    s"${aliasToNameSpaceMapping.getOrElse(alias, goGlobal.aliasToNameSpaceMapping.getOrDefault(alias, s"${XDefines.Unknown}.<$alias>"))}.$typeOrMethodName"
+  protected def resolveAliasToFullName(alias: String): String = {
+    s"${aliasToNameSpaceMapping.getOrElse(alias, goGlobal.aliasToNameSpaceMapping.getOrDefault(alias, s"${XDefines.Unknown}.<$alias>"))}"
   }
   protected def generateTypeFullName(
     typeName: Option[String] = None,
@@ -156,7 +156,7 @@ trait AstCreatorHelper { this: AstCreator =>
               Defines.primitiveTypeMap.getOrElse(typname, s"$fullyQualifiedPackage.$typname")
             }
           case Some(alias) =>
-            resolveAliasToFullName(alias, typname)
+            s"${resolveAliasToFullName(alias)}.$typname"
 
   }
   private def internalTypeFullName(

joern-cli/frontends/gosrc2cpg/src/main/scala/io/joern/gosrc2cpg/astcreation/AstForGenDeclarationCreator.scala

@@ -65,11 +65,12 @@ trait AstForGenDeclarationCreator(implicit withSchemaValidation: ValidationMode)
             val localParserNode = createParserNodeInfo(parserNode)
             if globalStatements then {
               val variableName = localParserNode.json(ParserKeys.Name).str
-              if (checkForDependencyFlags(variableName)) {
+              if (goGlobal.checkForDependencyFlags(variableName)) {
                 // While processing the dependencies code ignoring package level global variables starting with lower case letter
                 // as these variables are only accessible within package. So those will not be referred from main source code.
-                goGlobal.recordStructTypeMemberType(
-                  s"$fullyQualifiedPackage${Defines.dot}$variableName",
+                goGlobal.recordStructTypeMemberTypeInfo(
+                  fullyQualifiedPackage,
+                  variableName,
                   typeFullName.getOrElse(Defines.anyTypeName)
                 )
                 astForGlobalVarAndConstants(typeFullName.getOrElse(Defines.anyTypeName), localParserNode)
@@ -94,8 +95,8 @@ trait AstForGenDeclarationCreator(implicit withSchemaValidation: ValidationMode)
     val rhsTypeFullName = typeFullName.getOrElse(getTypeFullNameFromAstNode(rhsAst))
     if (globalStatements) {
       val variableName = lhsParserNode.json(ParserKeys.Name).str
-      if (checkForDependencyFlags(variableName)) {
-        goGlobal.recordStructTypeMemberType(s"$fullyQualifiedPackage${Defines.dot}$variableName", rhsTypeFullName)
+      if (goGlobal.checkForDependencyFlags(variableName)) {
+        goGlobal.recordStructTypeMemberTypeInfo(fullyQualifiedPackage, variableName, rhsTypeFullName)
         astForGlobalVarAndConstants(rhsTypeFullName, lhsParserNode, Some(rhsAst))
       }
       (Ast(), Ast())
@@ -160,14 +161,4 @@ trait AstForGenDeclarationCreator(implicit withSchemaValidation: ValidationMode)
       Ast()
     }
   }
-
-  /** While processing the dependencies code ignoring package level global variables, constants, types, and functions
-    * starting with lower case letter as those are only accessible within package. So those will not be referred from
-    * main source code.
-    * @param name
-    * @return
-    */
-  protected def checkForDependencyFlags(name: String): Boolean = {
-    !goGlobal.processingDependencies || goGlobal.processingDependencies && name.headOption.exists(_.isUpper)
-  }
 }

joern-cli/frontends/gosrc2cpg/src/main/scala/io/joern/gosrc2cpg/astcreation/AstForLambdaCreator.scala

@@ -1,5 +1,6 @@
 package io.joern.gosrc2cpg.astcreation
 
+import io.joern.gosrc2cpg.datastructures.{LambdaTypeInfo, MethodCacheMetaData}
 import io.joern.gosrc2cpg.parser.{ParserKeys, ParserNodeInfo}
 import io.joern.x2cpg.datastructures.Stack.StackWrapper
 import io.joern.x2cpg.utils.NodeBuilders.newModifierNode
@@ -8,6 +9,8 @@ import io.shiftleft.codepropertygraph.generated.nodes.{NewMethod, NewMethodRetur
 import io.shiftleft.codepropertygraph.generated.{ModifierTypes, NodeTypes}
 import ujson.Value
 
+import scala.jdk.CollectionConverters.*
+
 trait AstForLambdaCreator(implicit withSchemaValidation: ValidationMode) { this: AstCreator =>
 
   def astForFuncLiteral(funcLiteral: ParserNodeInfo): Seq[Ast] = {
@@ -17,9 +20,8 @@ trait AstForLambdaCreator(implicit withSchemaValidation: ValidationMode) { this:
       .collectFirst({ case m: NewMethod if !m.fullName.endsWith(parserResult.filename) => m.fullName })
       .getOrElse(fullyQualifiedPackage)
     val fullName = s"$baseFullName.$lambdaName"
-    val (signature, returnTypeStr, methodReturn, params, genericTypeMethodMap) = generateLambdaSignature(
-      createParserNodeInfo(funcLiteral.json(ParserKeys.Type))
-    )
+    val LambdaFunctionMetaData(signature, returnTypeStr, methodReturn, params, genericTypeMethodMap) =
+      generateLambdaSignature(createParserNodeInfo(funcLiteral.json(ParserKeys.Type)))
     val methodNode_ = methodNode(funcLiteral, lambdaName, funcLiteral.code, fullName, Some(signature), relPathFileName)
     methodAstParentStack.push(methodNode_)
     scope.pushNewScope(methodNode_)
@@ -40,7 +42,7 @@ trait AstForLambdaCreator(implicit withSchemaValidation: ValidationMode) { this:
         typeDeclNode_.astParentType(NodeTypes.TYPE_DECL).astParentFullName(fullyQualifiedPackage)
       else typeDeclNode_.astParentType(NodeTypes.METHOD).astParentFullName(baseFullName)
       val structTypes = Option(goGlobal.lambdaSignatureToLambdaTypeMap.get(signature)) match {
-        case Some(types) => types.map(_._1)
+        case Some(types) => types.asScala.map(_.lambdaStructTypeFullName)
         case None        => Seq.empty
       }
       typeDeclNode_.inheritsFromTypeFullName(structTypes)
@@ -50,13 +52,11 @@ trait AstForLambdaCreator(implicit withSchemaValidation: ValidationMode) { this:
       methodNode_.astParentFullName(fullName)
       Ast.storeInDiffGraph(astForMethod, diffGraph)
     }
-    goGlobal.recordFullNameToReturnType(fullName, returnTypeStr, signature)
+    goGlobal.recordMethodMetadata(baseFullName, lambdaName, MethodCacheMetaData(returnTypeStr, signature))
     Seq(Ast(methodRefNode(funcLiteral, funcLiteral.code, fullName, fullName)))
   }
 
-  protected def generateLambdaSignature(
-    funcType: ParserNodeInfo
-  ): (String, String, NewMethodReturn, Value, Map[String, List[String]]) = {
+  protected def generateLambdaSignature(funcType: ParserNodeInfo): LambdaFunctionMetaData = {
     val genericTypeMethodMap: Map[String, List[String]] = Map()
     // TODO: While handling the tuple return type we need to handle it here as well.
     val (returnTypeStr, returnTypeInfo) =
@@ -68,6 +68,14 @@ trait AstForLambdaCreator(implicit withSchemaValidation: ValidationMode) { this:
     val paramSignature = parameterSignature(params, genericTypeMethodMap)
     val signature =
       s"${XDefines.ClosurePrefix}($paramSignature)$returnTypeStr"
-    (signature, returnTypeStr, methodReturn, params, genericTypeMethodMap)
+    LambdaFunctionMetaData(signature, returnTypeStr, methodReturn, params, genericTypeMethodMap)
   }
 }
+
+case class LambdaFunctionMetaData(
+  signature: String,
+  returnTypeStr: String,
+  methodReturn: NewMethodReturn,
+  params: Value,
+  genericTypeMethodMap: Map[String, List[String]]
+)

joern-cli/frontends/gosrc2cpg/src/main/scala/io/joern/gosrc2cpg/astcreation/AstForMethodCallExpressionCreator.scala

@@ -1,5 +1,6 @@
 package io.joern.gosrc2cpg.astcreation
 
+import io.joern.gosrc2cpg.datastructures.MethodCacheMetaData
 import io.joern.gosrc2cpg.parser.ParserAst.*
 import io.joern.gosrc2cpg.parser.{ParserKeys, ParserNodeInfo}
 import io.joern.x2cpg.{Ast, ValidationMode, Defines as XDefines}
@@ -94,26 +95,22 @@ trait AstForMethodCallExpressionCreator(implicit withSchemaValidation: Validatio
         // Then we are assuming that the given function is defined inside same package as that of current file's package.
         // This assumption will be invalid when another package is imported with alias "."
         val methodFullName = s"$fullyQualifiedPackage.$methodName"
-        val (returnTypeFullNameCache, signatureCache) =
-          goGlobal.methodFullNameReturnTypeMap
-            .getOrDefault(methodFullName, (Defines.anyTypeName, s"$methodFullName()"))
+        val methodInfo = goGlobal
+          .getMethodMetadata(fullyQualifiedPackage, methodName)
+          .getOrElse(MethodCacheMetaData(Defines.anyTypeName, s"$methodFullName()"))
         val (signature, fullName, returnTypeFullName) =
-          Defines.builtinFunctions.getOrElse(methodName, (signatureCache, methodFullName, returnTypeFullNameCache))
+          Defines.builtinFunctions.getOrElse(methodName, (methodInfo.signature, methodFullName, methodInfo.returnType))
         val probableLambdaTypeFullName = scope.lookupVariable(methodName) match
           case Some((_, lambdaTypeFullName)) => Some(lambdaTypeFullName)
           case _ =>
-            Option(goGlobal.structTypeMemberTypeMapping.get(methodFullName)) match
-              case Some(globalLambdaTypeFullName) => Some(globalLambdaTypeFullName)
-              case _                              => None
+            goGlobal.getStructTypeMemberType(fullyQualifiedPackage, methodName)
         val (postLambdaFullname, postLambdaSignature, postLambdaReturnTypeFullName) = probableLambdaTypeFullName match
           case Some(lambdaTypeFullName) =>
-            Option(
-              goGlobal.methodFullNameReturnTypeMap
-                .get(lambdaTypeFullName)
-            ) match
-              case Some((lambdaReturnTypeFullNameCache, lambdaSignatureCache)) =>
-                (lambdaTypeFullName, lambdaSignatureCache, lambdaReturnTypeFullNameCache)
-              case _ => (fullName, signature, returnTypeFullName)
+            val (nameSpaceName, lambdaName) = goGlobal.splitNamespaceFromMember(lambdaTypeFullName)
+            goGlobal.getMethodMetadata(nameSpaceName, lambdaName) match {
+              case Some(metaData) => (lambdaTypeFullName, metaData.signature, metaData.returnType)
+              case _              => (fullName, signature, returnTypeFullName)
+            }
           case _ =>
             (fullName, signature, returnTypeFullName)
         (methodName, postLambdaSignature, postLambdaFullname, postLambdaReturnTypeFullName, Seq.empty)
@@ -126,18 +123,21 @@ trait AstForMethodCallExpressionCreator(implicit withSchemaValidation: Validatio
                 processReceiverAst(methodName, xnode)
               case _ =>
                 // Otherwise its an alias to imported namespace on which method call is made
-                val alias = xnode.json(ParserKeys.Name).str
-                val callMethodFullName =
-                  resolveAliasToFullName(alias, methodName)
+                val alias              = xnode.json(ParserKeys.Name).str
+                val fullNamespace      = resolveAliasToFullName(alias)
+                val callMethodFullName = s"$fullNamespace.$methodName"
                 val lambdaFullName =
-                  goGlobal.structTypeMemberTypeMapping.getOrDefault(callMethodFullName, callMethodFullName)
-                val (returnTypeFullNameCache, signatureCache) = Option(
-                  goGlobal.methodFullNameReturnTypeMap
-                    .get(lambdaFullName)
-                ) match
-                  case Some((returnTypeFullName, signature)) => (returnTypeFullName, signature)
-                  case _ => (s"$callMethodFullName.${Defines.ReturnType}.${XDefines.Unknown}", s"$callMethodFullName()")
-
+                  goGlobal.getStructTypeMemberType(fullNamespace, methodName).getOrElse(callMethodFullName)
+                val (nameSpace, memberName) = goGlobal.splitNamespaceFromMember(lambdaFullName)
+                val MethodCacheMetaData(returnTypeFullNameCache, signatureCache) =
+                  goGlobal
+                    .getMethodMetadata(nameSpace, memberName)
+                    .getOrElse(
+                      MethodCacheMetaData(
+                        s"$callMethodFullName.${Defines.ReturnType}.${XDefines.Unknown}",
+                        s"$callMethodFullName()"
+                      )
+                    )
                 (methodName, signatureCache, lambdaFullName, returnTypeFullNameCache, Seq.empty)
           case _ =>
             // This will take care of chained method calls. It will call `astForCallExpression` in recursive way,
@@ -157,12 +157,14 @@ trait AstForMethodCallExpressionCreator(implicit withSchemaValidation: Validatio
         .getOrElse(Defines.anyTypeName)
         .stripPrefix("*")
     val callMethodFullName = s"$receiverTypeFullName.$methodName"
-    val (returnTypeFullNameCache, signatureCache) =
-      goGlobal.methodFullNameReturnTypeMap
-        .getOrDefault(
-          callMethodFullName,
-          (s"$receiverTypeFullName.$methodName.${Defines.ReturnType}.${XDefines.Unknown}", s"$callMethodFullName()")
+    val MethodCacheMetaData(returnTypeFullNameCache, signatureCache) = goGlobal
+      .getMethodMetadata(receiverTypeFullName, methodName)
+      .getOrElse(
+        MethodCacheMetaData(
+          s"$receiverTypeFullName.$methodName.${Defines.ReturnType}.${XDefines.Unknown}",
+          s"$callMethodFullName()"
         )
+      )
     (methodName, signatureCache, callMethodFullName, returnTypeFullNameCache, receiverAst)
   }
 }

joern-cli/frontends/gosrc2cpg/src/main/scala/io/joern/gosrc2cpg/astcreation/AstForPrimitivesCreator.scala

@@ -1,6 +1,5 @@
 package io.joern.gosrc2cpg.astcreation
 
-import io.joern.gosrc2cpg.datastructures.GoGlobal
 import io.joern.gosrc2cpg.parser.ParserAst.*
 import io.joern.gosrc2cpg.parser.{ParserKeys, ParserNodeInfo}
 import io.joern.x2cpg.utils.NodeBuilders.newOperatorCallNode
@@ -72,11 +71,12 @@ trait AstForPrimitivesCreator(implicit withSchemaValidation: ValidationMode) { t
           Ast(node).withRefEdge(node, variable)
         case _ =>
           // If its not local node then check if its global member variable of package TypeDecl
-          Option(goGlobal.structTypeMemberTypeMapping.get(s"$fullyQualifiedPackage${Defines.dot}$identifierName")) match
+          goGlobal.getStructTypeMemberType(fullyQualifiedPackage, identifierName) match {
             case Some(fieldTypeFullName) => astForPackageGlobalFieldAccess(fieldTypeFullName, identifierName, ident)
             case _                       =>
               // TODO: something is wrong here. Refer to SwitchTests -> "be correct for switch case 4"
               Ast(identifierNode(ident, identifierName, ident.json(ParserKeys.Name).str, Defines.anyTypeName))
+          }
       }
     } else {
       Ast()