[clang] [clang][Dependency Scanning] Refactor Scanning Compiler Instance Initialization (PR #161300)

Qiongsi Wu via cfe-commits cfe-commits at lists.llvm.org
Tue Sep 30 09:15:40 PDT 2025


https://github.com/qiongsiwu updated https://github.com/llvm/llvm-project/pull/161300

>From 554613b511baa2772e0f1871008fd124bdc48700 Mon Sep 17 00:00:00 2001
From: Qiongsi Wu <qiongsi_wu at apple.com>
Date: Mon, 29 Sep 2025 16:46:02 -0700
Subject: [PATCH] Extract dependency scanning compiler instance initialization
 stepts into functions.

---
 .../DependencyScannerImpl.cpp                 | 257 +++++++++++++++---
 .../DependencyScannerImpl.h                   |  59 +++-
 .../DependencyScanningWorker.cpp              | 132 ++-------
 3 files changed, 293 insertions(+), 155 deletions(-)

diff --git a/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.cpp b/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.cpp
index d370bfd0dd10f..9a8fabaab42ec 100644
--- a/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.cpp
+++ b/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.cpp
@@ -9,8 +9,10 @@
 #include "DependencyScannerImpl.h"
 #include "clang/Basic/DiagnosticFrontend.h"
 #include "clang/Basic/DiagnosticSerialization.h"
+#include "clang/Driver/Driver.h"
 #include "clang/Frontend/FrontendActions.h"
 #include "clang/Tooling/DependencyScanning/DependencyScanningWorker.h"
+#include "llvm/TargetParser/Host.h"
 
 using namespace clang;
 using namespace tooling;
@@ -334,6 +336,17 @@ class ScanningDependencyDirectivesGetter : public DependencyDirectivesGetter {
 };
 } // namespace
 
+std::unique_ptr<DiagnosticOptions>
+clang::tooling::dependencies::createDiagOptions(
+    const std::vector<std::string> &CommandLine) {
+  std::vector<const char *> CLI;
+  for (const std::string &Arg : CommandLine)
+    CLI.push_back(Arg.c_str());
+  auto DiagOpts = CreateAndPopulateDiagOpts(CLI);
+  sanitizeDiagOpts(*DiagOpts);
+  return DiagOpts;
+}
+
 /// Sanitize diagnostic options for dependency scan.
 void clang::tooling::dependencies::sanitizeDiagOpts(
     DiagnosticOptions &DiagOpts) {
@@ -356,43 +369,131 @@ void clang::tooling::dependencies::sanitizeDiagOpts(
   });
 }
 
-bool DependencyScanningAction::runInvocation(
-    std::shared_ptr<CompilerInvocation> Invocation,
-    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
-    std::shared_ptr<PCHContainerOperations> PCHContainerOps,
-    DiagnosticConsumer *DiagConsumer) {
-  // Making sure that we canonicalize the defines before we create the deep
-  // copy to avoid unnecessary variants in the scanner and in the resulting
-  // explicit command lines.
-  if (any(Service.getOptimizeArgs() & ScanningOptimizations::Macros))
-    canonicalizeDefines(Invocation->getPreprocessorOpts());
+std::pair<std::unique_ptr<driver::Driver>, std::unique_ptr<driver::Compilation>>
+clang::tooling::dependencies::buildCompilation(
+    ArrayRef<std::string> ArgStrs, DiagnosticsEngine &Diags,
+    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS) {
+  SmallVector<const char *, 256> Argv;
+  Argv.reserve(ArgStrs.size());
+  for (const std::string &Arg : ArgStrs)
+    Argv.push_back(Arg.c_str());
+
+  std::unique_ptr<driver::Driver> Driver = std::make_unique<driver::Driver>(
+      Argv[0], llvm::sys::getDefaultTargetTriple(), Diags,
+      "clang LLVM compiler", FS);
+  Driver->setTitle("clang_based_tool");
+
+  llvm::BumpPtrAllocator Alloc;
+  bool CLMode = driver::IsClangCL(
+      driver::getDriverMode(Argv[0], ArrayRef(Argv).slice(1)));
+
+  if (llvm::Error E =
+          driver::expandResponseFiles(Argv, CLMode, Alloc, FS.get())) {
+    Diags.Report(diag::err_drv_expand_response_file)
+        << llvm::toString(std::move(E));
+    return std::make_pair(nullptr, nullptr);
+  }
 
-  // Make a deep copy of the original Clang invocation.
-  CompilerInvocation OriginalInvocation(*Invocation);
+  std::unique_ptr<driver::Compilation> Compilation(
+      Driver->BuildCompilation(llvm::ArrayRef(Argv)));
+  if (!Compilation)
+    return std::make_pair(nullptr, nullptr);
 
-  if (Scanned) {
-    // Scanning runs once for the first -cc1 invocation in a chain of driver
-    // jobs. For any dependent jobs, reuse the scanning result and just
-    // update the LastCC1Arguments to correspond to the new invocation.
-    // FIXME: to support multi-arch builds, each arch requires a separate scan
-    setLastCC1Arguments(std::move(OriginalInvocation));
-    return true;
+  if (Compilation->containsError())
+    return std::make_pair(nullptr, nullptr);
+
+  return std::make_pair(std::move(Driver), std::move(Compilation));
+}
+
+llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>
+clang::tooling::dependencies::initVFSForTUBufferScanning(
+    llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> BaseFS,
+    std::optional<std::vector<std::string>> &ModifiedCommandLine,
+    const std::vector<std::string> &CommandLine, StringRef WorkingDirectory,
+    std::optional<llvm::MemoryBufferRef> TUBuffer) {
+  // Reset what might have been modified in the previous worker invocation.
+  BaseFS->setCurrentWorkingDirectory(WorkingDirectory);
+
+  llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> ModifiedFS;
+  if (TUBuffer) {
+    auto OverlayFS =
+        llvm::makeIntrusiveRefCnt<llvm::vfs::OverlayFileSystem>(BaseFS);
+    auto InMemoryFS =
+        llvm::makeIntrusiveRefCnt<llvm::vfs::InMemoryFileSystem>();
+    InMemoryFS->setCurrentWorkingDirectory(WorkingDirectory);
+    auto InputPath = TUBuffer->getBufferIdentifier();
+    InMemoryFS->addFile(
+        InputPath, 0,
+        llvm::MemoryBuffer::getMemBufferCopy(TUBuffer->getBuffer()));
+    llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> InMemoryOverlay =
+        InMemoryFS;
+
+    OverlayFS->pushOverlay(InMemoryOverlay);
+    ModifiedFS = OverlayFS;
+    ModifiedCommandLine = CommandLine;
+    ModifiedCommandLine->emplace_back(InputPath);
+
+    return ModifiedFS;
   }
 
-  Scanned = true;
+  return BaseFS;
+}
 
-  // Create a compiler instance to handle the actual work.
-  auto ModCache = makeInProcessModuleCache(Service.getModuleCacheEntries());
-  ScanInstanceStorage.emplace(std::move(Invocation), std::move(PCHContainerOps),
-                              ModCache.get());
-  CompilerInstance &ScanInstance = *ScanInstanceStorage;
+llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>
+clang::tooling::dependencies::initVFSForByNameScanning(
+    llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> BaseFS,
+    std::vector<std::string> &CommandLine, StringRef WorkingDirectory,
+    StringRef FakeFileNamePrefix) {
+  // Reset what might have been modified in the previous worker invocation.
+  BaseFS->setCurrentWorkingDirectory(WorkingDirectory);
+
+  // If we're scanning based on a module name alone, we don't expect the client
+  // to provide us with an input file. However, the driver really wants to have
+  // one. Let's just make it up to make the driver happy.
+  auto OverlayFS =
+      llvm::makeIntrusiveRefCnt<llvm::vfs::OverlayFileSystem>(BaseFS);
+  auto InMemoryFS = llvm::makeIntrusiveRefCnt<llvm::vfs::InMemoryFileSystem>();
+  InMemoryFS->setCurrentWorkingDirectory(WorkingDirectory);
+  SmallString<128> FakeInputPath;
+  // TODO: We should retry the creation if the path already exists.
+  llvm::sys::fs::createUniquePath(FakeFileNamePrefix + "-%%%%%%%%.input",
+                                  FakeInputPath,
+                                  /*MakeAbsolute=*/false);
+  InMemoryFS->addFile(FakeInputPath, 0, llvm::MemoryBuffer::getMemBuffer(""));
+  llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> InMemoryOverlay = InMemoryFS;
+  OverlayFS->pushOverlay(InMemoryOverlay);
+
+  CommandLine.emplace_back(FakeInputPath);
+
+  return OverlayFS;
+}
+
+std::unique_ptr<CompilerInvocation>
+clang::tooling::dependencies::createCompilerInvocation(
+    const std::vector<std::string> &CommandLine, DiagnosticsEngine &Diags) {
+  llvm::opt::ArgStringList Argv;
+  for (const std::string &Str : ArrayRef(CommandLine).drop_front())
+    Argv.push_back(Str.c_str());
+
+  auto Invocation = std::make_unique<CompilerInvocation>();
+  if (!CompilerInvocation::CreateFromArgs(*Invocation, Argv, Diags)) {
+    // FIXME: Should we just go on like cc1_main does?
+    return nullptr;
+  }
+  return Invocation;
+}
+
+bool clang::tooling::dependencies::initializeScanCompilerInstance(
+    CompilerInstance &ScanInstance,
+    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
+    DiagnosticConsumer *DiagConsumer, DependencyScanningService &Service,
+    llvm::IntrusiveRefCntPtr<DependencyScanningWorkerFilesystem> DepFS) {
   ScanInstance.setBuildingModule(false);
 
   ScanInstance.createVirtualFileSystem(FS, DiagConsumer);
 
   // Create the compiler's actual diagnostics engine.
   sanitizeDiagOpts(ScanInstance.getDiagnosticOpts());
-  assert(!DiagConsumerFinished && "attempt to reuse finished consumer");
   ScanInstance.createDiagnostics(DiagConsumer, /*ShouldOwnClient=*/false);
   if (!ScanInstance.hasDiagnostics())
     return false;
@@ -434,6 +535,26 @@ bool DependencyScanningAction::runInvocation(
 
   ScanInstance.createSourceManager(*FileMgr);
 
+  // Consider different header search and diagnostic options to create
+  // different modules. This avoids the unsound aliasing of module PCMs.
+  //
+  // TODO: Implement diagnostic bucketing to reduce the impact of strict
+  // context hashing.
+  ScanInstance.getHeaderSearchOpts().ModulesStrictContextHash = true;
+  ScanInstance.getHeaderSearchOpts().ModulesSerializeOnlyPreprocessor = true;
+  ScanInstance.getHeaderSearchOpts().ModulesSkipDiagnosticOptions = true;
+  ScanInstance.getHeaderSearchOpts().ModulesSkipHeaderSearchPaths = true;
+  ScanInstance.getHeaderSearchOpts().ModulesSkipPragmaDiagnosticMappings = true;
+  ScanInstance.getHeaderSearchOpts().ModulesForceValidateUserHeaders = false;
+
+  // Avoid some checks and module map parsing when loading PCM files.
+  ScanInstance.getPreprocessorOpts().ModulesCheckRelocated = false;
+
+  return true;
+}
+
+llvm::SmallVector<StringRef> clang::tooling::dependencies::computeStableDirs(
+    CompilerInstance &ScanInstance) {
   // Create a collection of stable directories derived from the ScanInstance
   // for determining whether module dependencies would fully resolve from
   // those directories.
@@ -441,7 +562,12 @@ bool DependencyScanningAction::runInvocation(
   const StringRef Sysroot = ScanInstance.getHeaderSearchOpts().Sysroot;
   if (!Sysroot.empty() && (llvm::sys::path::root_directory(Sysroot) != Sysroot))
     StableDirs = {Sysroot, ScanInstance.getHeaderSearchOpts().ResourceDir};
+  return StableDirs;
+}
 
+std::optional<PrebuiltModulesAttrsMap>
+clang::tooling::dependencies::computePrebuiltModulesASTMap(
+    CompilerInstance &ScanInstance, llvm::SmallVector<StringRef> &StableDirs) {
   // Store a mapping of prebuilt module files and their properties like header
   // search options. This will prevent the implicit build to create duplicate
   // modules and will force reuse of the existing prebuilt module files
@@ -453,8 +579,18 @@ bool DependencyScanningAction::runInvocation(
             ScanInstance.getPreprocessorOpts().ImplicitPCHInclude, ScanInstance,
             ScanInstance.getHeaderSearchOpts().PrebuiltModuleFiles,
             PrebuiltModulesASTMap, ScanInstance.getDiagnostics(), StableDirs))
-      return false;
+      return {};
 
+  return PrebuiltModulesASTMap;
+}
+
+void clang::tooling::dependencies::initializeModuleDepCollector(
+    CompilerInstance &ScanInstance, std::shared_ptr<ModuleDepCollector> &MDC,
+    StringRef WorkingDirectory, DependencyConsumer &Consumer,
+    DependencyScanningService &Service, CompilerInvocation &Inv,
+    DependencyActionController &Controller,
+    PrebuiltModulesAttrsMap PrebuiltModulesASTMap,
+    llvm::SmallVector<StringRef> &StableDirs) {
   // Create the dependency collector that will collect the produced
   // dependencies.
   //
@@ -463,6 +599,11 @@ bool DependencyScanningAction::runInvocation(
   // which ensures that the compiler won't create new dependency collectors,
   // and thus won't write out the extra '.d' files to disk.
   auto Opts = std::make_unique<DependencyOutputOptions>();
+
+  // We rely on the behaviour that that ScanInstance's Invocation instance's
+  // dependency output opts are cleared here.
+  // TODO: we will need to preserve and recover the original dependency output
+  // opts if we want to reuse ScanInstance.
   std::swap(*Opts, ScanInstance.getInvocation().getDependencyOutputOpts());
   // We need at least one -MT equivalent for the generator of make dependency
   // files to work.
@@ -480,26 +621,58 @@ bool DependencyScanningAction::runInvocation(
   case ScanningOutputFormat::P1689:
   case ScanningOutputFormat::Full:
     MDC = std::make_shared<ModuleDepCollector>(
-        Service, std::move(Opts), ScanInstance, Consumer, Controller,
-        OriginalInvocation, std::move(PrebuiltModulesASTMap), StableDirs);
+        Service, std::move(Opts), ScanInstance, Consumer, Controller, Inv,
+        std::move(PrebuiltModulesASTMap), StableDirs);
     ScanInstance.addDependencyCollector(MDC);
     break;
   }
+}
 
-  // Consider different header search and diagnostic options to create
-  // different modules. This avoids the unsound aliasing of module PCMs.
-  //
-  // TODO: Implement diagnostic bucketing to reduce the impact of strict
-  // context hashing.
-  ScanInstance.getHeaderSearchOpts().ModulesStrictContextHash = true;
-  ScanInstance.getHeaderSearchOpts().ModulesSerializeOnlyPreprocessor = true;
-  ScanInstance.getHeaderSearchOpts().ModulesSkipDiagnosticOptions = true;
-  ScanInstance.getHeaderSearchOpts().ModulesSkipHeaderSearchPaths = true;
-  ScanInstance.getHeaderSearchOpts().ModulesSkipPragmaDiagnosticMappings = true;
-  ScanInstance.getHeaderSearchOpts().ModulesForceValidateUserHeaders = false;
+bool DependencyScanningAction::runInvocation(
+    std::unique_ptr<CompilerInvocation> Invocation,
+    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
+    std::shared_ptr<PCHContainerOperations> PCHContainerOps,
+    DiagnosticConsumer *DiagConsumer) {
+  // Making sure that we canonicalize the defines before we create the deep
+  // copy to avoid unnecessary variants in the scanner and in the resulting
+  // explicit command lines.
+  if (any(Service.getOptimizeArgs() & ScanningOptimizations::Macros))
+    canonicalizeDefines(Invocation->getPreprocessorOpts());
 
-  // Avoid some checks and module map parsing when loading PCM files.
-  ScanInstance.getPreprocessorOpts().ModulesCheckRelocated = false;
+  // Make a deep copy of the original Clang invocation.
+  CompilerInvocation OriginalInvocation(*Invocation);
+
+  if (Scanned) {
+    // Scanning runs once for the first -cc1 invocation in a chain of driver
+    // jobs. For any dependent jobs, reuse the scanning result and just
+    // update the LastCC1Arguments to correspond to the new invocation.
+    // FIXME: to support multi-arch builds, each arch requires a separate scan
+    setLastCC1Arguments(std::move(OriginalInvocation));
+    return true;
+  }
+
+  Scanned = true;
+
+  // Create a compiler instance to handle the actual work.
+  auto ModCache = makeInProcessModuleCache(Service.getModuleCacheEntries());
+  ScanInstanceStorage.emplace(std::move(Invocation), std::move(PCHContainerOps),
+                              ModCache.get());
+  CompilerInstance &ScanInstance = *ScanInstanceStorage;
+
+  assert(!DiagConsumerFinished && "attempt to reuse finished consumer");
+  if (!initializeScanCompilerInstance(ScanInstance, FS, DiagConsumer, Service,
+                                      DepFS))
+    return false;
+
+  llvm::SmallVector<StringRef> StableDirs = computeStableDirs(ScanInstance);
+  auto MaybePrebuiltModulesASTMap =
+      computePrebuiltModulesASTMap(ScanInstance, StableDirs);
+  if (!MaybePrebuiltModulesASTMap)
+    return false;
+
+  initializeModuleDepCollector(ScanInstance, MDC, WorkingDirectory, Consumer,
+                               Service, OriginalInvocation, Controller,
+                               *MaybePrebuiltModulesASTMap, StableDirs);
 
   std::unique_ptr<FrontendAction> Action;
 
diff --git a/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.h b/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.h
index 32fbcfffde53c..c9779fe65e711 100644
--- a/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.h
+++ b/clang/lib/Tooling/DependencyScanning/DependencyScannerImpl.h
@@ -9,8 +9,10 @@
 #ifndef LLVM_CLANG_TOOLING_DEPENDENCYSCANNING_DEPENDENCYSCANNER_H
 #define LLVM_CLANG_TOOLING_DEPENDENCYSCANNING_DEPENDENCYSCANNER_H
 
+#include "clang/Driver/Compilation.h"
 #include "clang/Frontend/CompilerInstance.h"
 #include "clang/Frontend/CompilerInvocation.h"
+#include "clang/Frontend/TextDiagnosticPrinter.h"
 #include "clang/Serialization/ObjectFilePCHContainerReader.h"
 #include "clang/Tooling/DependencyScanning/DependencyScanningFilesystem.h"
 #include "clang/Tooling/DependencyScanning/ModuleDepCollector.h"
@@ -35,7 +37,7 @@ class DependencyScanningAction {
       : Service(Service), WorkingDirectory(WorkingDirectory),
         Consumer(Consumer), Controller(Controller), DepFS(std::move(DepFS)),
         ModuleName(ModuleName) {}
-  bool runInvocation(std::shared_ptr<CompilerInvocation> Invocation,
+  bool runInvocation(std::unique_ptr<CompilerInvocation> Invocation,
                      IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
                      std::shared_ptr<PCHContainerOperations> PCHContainerOps,
                      DiagnosticConsumer *DiagConsumer);
@@ -73,8 +75,63 @@ class DependencyScanningAction {
 };
 
 // Helper functions
+std::unique_ptr<DiagnosticOptions>
+createDiagOptions(const std::vector<std::string> &CommandLine);
 void sanitizeDiagOpts(DiagnosticOptions &DiagOpts);
 
+struct TextDiagnosticsPrinterWithOutput {
+  std::string DiagnosticOutput;
+  llvm::raw_string_ostream DiagnosticsOS;
+  std::unique_ptr<clang::DiagnosticOptions> DiagOpts;
+  TextDiagnosticPrinter DiagPrinter;
+
+  TextDiagnosticsPrinterWithOutput(const std::vector<std::string> &CommandLine)
+      : DiagnosticsOS(DiagnosticOutput),
+        DiagOpts(createDiagOptions(CommandLine)),
+        DiagPrinter(DiagnosticsOS, *DiagOpts) {}
+};
+
+std::pair<std::unique_ptr<driver::Driver>, std::unique_ptr<driver::Compilation>>
+buildCompilation(ArrayRef<std::string> ArgStrs, DiagnosticsEngine &Diags,
+                 IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS);
+
+std::unique_ptr<CompilerInvocation>
+createCompilerInvocation(const std::vector<std::string> &CommandLine,
+                         DiagnosticsEngine &Diags);
+
+llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> initVFSForTUBufferScanning(
+    llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> BaseFS,
+    std::optional<std::vector<std::string>> &ModifiedCommandLine,
+    const std::vector<std::string> &CommandLine, StringRef WorkingDirectory,
+    std::optional<llvm::MemoryBufferRef> TUBuffer);
+
+llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>
+initVFSForByNameScanning(llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> BaseFS,
+                         std::vector<std::string> &CommandLine,
+                         StringRef WorkingDirectory,
+                         StringRef FakeFileNamePrefix);
+
+bool initializeScanCompilerInstance(
+    CompilerInstance &ScanInstance,
+    IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
+    DiagnosticConsumer *DiagConsumer, DependencyScanningService &Service,
+    llvm::IntrusiveRefCntPtr<DependencyScanningWorkerFilesystem> DepFS);
+
+llvm::SmallVector<StringRef> computeStableDirs(CompilerInstance &ScanInstance);
+
+std::optional<PrebuiltModulesAttrsMap>
+computePrebuiltModulesASTMap(CompilerInstance &ScanInstance,
+                             llvm::SmallVector<StringRef> &StableDirs);
+
+void initializeModuleDepCollector(CompilerInstance &ScanInstance,
+                                  std::shared_ptr<ModuleDepCollector> &MDC,
+                                  StringRef WorkingDirectory,
+                                  DependencyConsumer &Consumer,
+                                  DependencyScanningService &Service,
+                                  CompilerInvocation &Inv,
+                                  DependencyActionController &Controller,
+                                  PrebuiltModulesAttrsMap PrebuiltModulesASTMap,
+                                  llvm::SmallVector<StringRef> &StableDirs);
 } // namespace dependencies
 } // namespace tooling
 } // namespace clang
diff --git a/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp b/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp
index 796e587ba9147..4a80189288d9c 100644
--- a/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp
+++ b/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp
@@ -63,32 +63,19 @@ DependencyScanningWorker::DependencyScanningWorker(
   }
 }
 
-static std::unique_ptr<DiagnosticOptions>
-createDiagOptions(const std::vector<std::string> &CommandLine) {
-  std::vector<const char *> CLI;
-  for (const std::string &Arg : CommandLine)
-    CLI.push_back(Arg.c_str());
-  auto DiagOpts = CreateAndPopulateDiagOpts(CLI);
-  sanitizeDiagOpts(*DiagOpts);
-  return DiagOpts;
-}
-
 llvm::Error DependencyScanningWorker::computeDependencies(
     StringRef WorkingDirectory, const std::vector<std::string> &CommandLine,
     DependencyConsumer &Consumer, DependencyActionController &Controller,
     std::optional<llvm::MemoryBufferRef> TUBuffer) {
   // Capture the emitted diagnostics and report them to the client
   // in the case of a failure.
-  std::string DiagnosticOutput;
-  llvm::raw_string_ostream DiagnosticsOS(DiagnosticOutput);
-  auto DiagOpts = createDiagOptions(CommandLine);
-  TextDiagnosticPrinter DiagPrinter(DiagnosticsOS, *DiagOpts);
+  TextDiagnosticsPrinterWithOutput DiagPrinterWithOS(CommandLine);
 
   if (computeDependencies(WorkingDirectory, CommandLine, Consumer, Controller,
-                          DiagPrinter, TUBuffer))
+                          DiagPrinterWithOS.DiagPrinter, TUBuffer))
     return llvm::Error::success();
-  return llvm::make_error<llvm::StringError>(DiagnosticsOS.str(),
-                                             llvm::inconvertibleErrorCode());
+  return llvm::make_error<llvm::StringError>(
+      DiagPrinterWithOS.DiagnosticsOS.str(), llvm::inconvertibleErrorCode());
 }
 
 llvm::Error DependencyScanningWorker::computeDependencies(
@@ -97,51 +84,24 @@ llvm::Error DependencyScanningWorker::computeDependencies(
     StringRef ModuleName) {
   // Capture the emitted diagnostics and report them to the client
   // in the case of a failure.
-  std::string DiagnosticOutput;
-  llvm::raw_string_ostream DiagnosticsOS(DiagnosticOutput);
-  auto DiagOpts = createDiagOptions(CommandLine);
-  TextDiagnosticPrinter DiagPrinter(DiagnosticsOS, *DiagOpts);
+  TextDiagnosticsPrinterWithOutput DiagPrinterWithOS(CommandLine);
 
   if (computeDependencies(WorkingDirectory, CommandLine, Consumer, Controller,
-                          DiagPrinter, ModuleName))
+                          DiagPrinterWithOS.DiagPrinter, ModuleName))
     return llvm::Error::success();
-  return llvm::make_error<llvm::StringError>(DiagnosticsOS.str(),
-                                             llvm::inconvertibleErrorCode());
+  return llvm::make_error<llvm::StringError>(
+      DiagPrinterWithOS.DiagnosticsOS.str(), llvm::inconvertibleErrorCode());
 }
 
 static bool forEachDriverJob(
     ArrayRef<std::string> ArgStrs, DiagnosticsEngine &Diags,
     IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
     llvm::function_ref<bool(const driver::Command &Cmd)> Callback) {
-  SmallVector<const char *, 256> Argv;
-  Argv.reserve(ArgStrs.size());
-  for (const std::string &Arg : ArgStrs)
-    Argv.push_back(Arg.c_str());
-
-  std::unique_ptr<driver::Driver> Driver = std::make_unique<driver::Driver>(
-      Argv[0], llvm::sys::getDefaultTargetTriple(), Diags,
-      "clang LLVM compiler", FS);
-  Driver->setTitle("clang_based_tool");
-
-  llvm::BumpPtrAllocator Alloc;
-  bool CLMode = driver::IsClangCL(
-      driver::getDriverMode(Argv[0], ArrayRef(Argv).slice(1)));
-
-  if (llvm::Error E =
-          driver::expandResponseFiles(Argv, CLMode, Alloc, FS.get())) {
-    Diags.Report(diag::err_drv_expand_response_file)
-        << llvm::toString(std::move(E));
-    return false;
-  }
-
-  const std::unique_ptr<driver::Compilation> Compilation(
-      Driver->BuildCompilation(llvm::ArrayRef(Argv)));
+  // Compilation owns a reference to the Driver, hence we need to
+  // keep the Driver alive when we use Compilation.
+  auto [Driver, Compilation] = buildCompilation(ArgStrs, Diags, FS);
   if (!Compilation)
     return false;
-
-  if (Compilation->containsError())
-    return false;
-
   for (const driver::Command &Job : Compilation->getJobs()) {
     if (!Callback(Job))
       return false;
@@ -150,30 +110,21 @@ static bool forEachDriverJob(
 }
 
 static bool createAndRunToolInvocation(
-    std::vector<std::string> CommandLine, DependencyScanningAction &Action,
+    const std::vector<std::string> &CommandLine,
+    DependencyScanningAction &Action,
     IntrusiveRefCntPtr<llvm::vfs::FileSystem> FS,
     std::shared_ptr<clang::PCHContainerOperations> &PCHContainerOps,
     DiagnosticsEngine &Diags, DependencyConsumer &Consumer) {
-
-  // Save executable path before providing CommandLine to ToolInvocation
-  std::string Executable = CommandLine[0];
-
-  llvm::opt::ArgStringList Argv;
-  for (const std::string &Str : ArrayRef(CommandLine).drop_front())
-    Argv.push_back(Str.c_str());
-
-  auto Invocation = std::make_shared<CompilerInvocation>();
-  if (!CompilerInvocation::CreateFromArgs(*Invocation, Argv, Diags)) {
-    // FIXME: Should we just go on like cc1_main does?
+  auto Invocation = createCompilerInvocation(CommandLine, Diags);
+  if (!Invocation)
     return false;
-  }
 
   if (!Action.runInvocation(std::move(Invocation), std::move(FS),
                             PCHContainerOps, Diags.getClient()))
     return false;
 
   std::vector<std::string> Args = Action.takeLastCC1Arguments();
-  Consumer.handleBuildCommand({std::move(Executable), std::move(Args)});
+  Consumer.handleBuildCommand({CommandLine[0], std::move(Args)});
   return true;
 }
 
@@ -238,37 +189,11 @@ bool DependencyScanningWorker::computeDependencies(
     StringRef WorkingDirectory, const std::vector<std::string> &CommandLine,
     DependencyConsumer &Consumer, DependencyActionController &Controller,
     DiagnosticConsumer &DC, std::optional<llvm::MemoryBufferRef> TUBuffer) {
-  // Reset what might have been modified in the previous worker invocation.
-  BaseFS->setCurrentWorkingDirectory(WorkingDirectory);
-
   std::optional<std::vector<std::string>> ModifiedCommandLine;
-  llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> ModifiedFS;
-
-  // If we're scanning based on a module name alone, we don't expect the client
-  // to provide us with an input file. However, the driver really wants to have
-  // one. Let's just make it up to make the driver happy.
-  if (TUBuffer) {
-    auto OverlayFS =
-        llvm::makeIntrusiveRefCnt<llvm::vfs::OverlayFileSystem>(BaseFS);
-    auto InMemoryFS =
-        llvm::makeIntrusiveRefCnt<llvm::vfs::InMemoryFileSystem>();
-    InMemoryFS->setCurrentWorkingDirectory(WorkingDirectory);
-    auto InputPath = TUBuffer->getBufferIdentifier();
-    InMemoryFS->addFile(
-        InputPath, 0,
-        llvm::MemoryBuffer::getMemBufferCopy(TUBuffer->getBuffer()));
-    llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> InMemoryOverlay =
-        InMemoryFS;
-
-    OverlayFS->pushOverlay(InMemoryOverlay);
-    ModifiedFS = OverlayFS;
-    ModifiedCommandLine = CommandLine;
-    ModifiedCommandLine->emplace_back(InputPath);
-  }
-
+  auto FinalFS = initVFSForTUBufferScanning(
+      BaseFS, ModifiedCommandLine, CommandLine, WorkingDirectory, TUBuffer);
   const std::vector<std::string> &FinalCommandLine =
       ModifiedCommandLine ? *ModifiedCommandLine : CommandLine;
-  auto &FinalFS = ModifiedFS ? ModifiedFS : BaseFS;
 
   return scanDependencies(WorkingDirectory, FinalCommandLine, Consumer,
                           Controller, DC, FinalFS, /*ModuleName=*/std::nullopt);
@@ -278,26 +203,9 @@ bool DependencyScanningWorker::computeDependencies(
     StringRef WorkingDirectory, const std::vector<std::string> &CommandLine,
     DependencyConsumer &Consumer, DependencyActionController &Controller,
     DiagnosticConsumer &DC, StringRef ModuleName) {
-  // Reset what might have been modified in the previous worker invocation.
-  BaseFS->setCurrentWorkingDirectory(WorkingDirectory);
-
-  // If we're scanning based on a module name alone, we don't expect the client
-  // to provide us with an input file. However, the driver really wants to have
-  // one. Let's just make it up to make the driver happy.
-  auto OverlayFS =
-      llvm::makeIntrusiveRefCnt<llvm::vfs::OverlayFileSystem>(BaseFS);
-  auto InMemoryFS = llvm::makeIntrusiveRefCnt<llvm::vfs::InMemoryFileSystem>();
-  InMemoryFS->setCurrentWorkingDirectory(WorkingDirectory);
-  SmallString<128> FakeInputPath;
-  // TODO: We should retry the creation if the path already exists.
-  llvm::sys::fs::createUniquePath(ModuleName + "-%%%%%%%%.input", FakeInputPath,
-                                  /*MakeAbsolute=*/false);
-  InMemoryFS->addFile(FakeInputPath, 0, llvm::MemoryBuffer::getMemBuffer(""));
-  llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> InMemoryOverlay = InMemoryFS;
-
-  OverlayFS->pushOverlay(InMemoryOverlay);
   auto ModifiedCommandLine = CommandLine;
-  ModifiedCommandLine.emplace_back(FakeInputPath);
+  auto OverlayFS = initVFSForByNameScanning(BaseFS, ModifiedCommandLine,
+                                            WorkingDirectory, ModuleName);
 
   return scanDependencies(WorkingDirectory, ModifiedCommandLine, Consumer,
                           Controller, DC, OverlayFS, ModuleName);



More information about the cfe-commits mailing list