[Reproducers] Integrate FileProvider with clang

[JDevlieghere]

Summary

This patch hooks up clang to LLDB's FileProvider, so that files used by clang are part of the reproducer.

[labath]

I don't know much about this part of the code, though the changes seem pretty straight-forward to me.

[davide]

LGTM with one comment.

lldb/source/Plugins/ExpressionParser/Clang/ClangExpressionParser.cpp

252–262 ↗

(On Diff #186336)

can you add a comment like: "when recording, set up the state to collect the modules, etc..".

lit/Reproducer/Inputs/ModuleCapture.in

+expr -- @import Cocoa
+reproducer generate

lit/Reproducer/TestClangFileRepro.test

+# REQUIRES: system-darwin
+#
+# This tests that modules files from clang end up in the reproducer.
+#
+# RUN: %lldb -x -b -s %S/Inputs/ModuleCapture.in --capture %t.repro
+# cat %t.repro/files.yaml | FileCheck %s
+#
+# CHECK: Cocoa.h

source/Plugins/ExpressionParser/Clang/ClangExpressionParser.cpp

 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/DynamicLibrary.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/Host.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Signals.h"
 
-#include "ClangDiagnostic.h"
-#include "ClangExpressionParser.h"
-
 #include "ClangASTSource.h"
+#include "ClangDiagnostic.h"
 #include "ClangExpressionDeclMap.h"
 #include "ClangExpressionHelper.h"
+#include "ClangExpressionParser.h"
 #include "ClangModulesDeclVendor.h"
 #include "ClangPersistentVariables.h"
 #include "IRForTarget.h"
+#include "ModuleDependencyCollector.h"
 
 #include "lldb/Core/Debugger.h"
 #include "lldb/Core/Disassembler.h"
 #include "lldb/Core/Module.h"
 #include "lldb/Core/StreamFile.h"
 #include "lldb/Expression/IRDynamicChecks.h"
 #include "lldb/Expression/IRExecutionUnit.h"
 #include "lldb/Expression/IRInterpreter.h"
 #include "lldb/Host/File.h"
 #include "lldb/Host/HostInfo.h"
 #include "lldb/Symbol/ClangASTContext.h"
 #include "lldb/Symbol/SymbolVendor.h"
 #include "lldb/Target/ExecutionContext.h"
 #include "lldb/Target/Language.h"
 #include "lldb/Target/ObjCLanguageRuntime.h"
 #include "lldb/Target/Process.h"
 #include "lldb/Target/Target.h"
 #include "lldb/Target/ThreadPlanCallFunction.h"
 #include "lldb/Utility/DataBufferHeap.h"
 #include "lldb/Utility/LLDBAssert.h"
 #include "lldb/Utility/Log.h"
+#include "lldb/Utility/Reproducer.h"
 #include "lldb/Utility/Stream.h"
 #include "lldb/Utility/StreamString.h"
 #include "lldb/Utility/StringList.h"
 
 #include <cctype>
 #include <memory>
 
 using namespace clang;
if (!target_sp) {
     lldb_assert(target_sp.get(),
                 "Can't make an expression parser with a null target.",
                 __FUNCTION__, __FILE__, __LINE__);
     return;
   }
 
   // 1. Create a new compiler instance.
   m_compiler.reset(new CompilerInstance());
+
+  // When capturing a reproducer, hook up the file collector with clang to
+  // collector modules and headers.
+  if (repro::Generator *g = repro::Reproducer::Instance().GetGenerator()) {
+    repro::FileProvider &fp = g->GetOrCreate<repro::FileProvider>();
+    m_compiler->setModuleDepCollector(
+        std::make_shared<ModuleDependencyCollectorAdaptor>(
+            fp.GetFileCollector()));
+    DependencyOutputOptions &opts = m_compiler->getDependencyOutputOpts();
+    opts.IncludeSystemHeaders = true;
+    opts.IncludeModuleFiles = true;
+  }
+
   lldb::LanguageType frame_lang =
       expr.Language(); // defaults to lldb::eLanguageTypeUnknown
   bool overridden_target_opts = false;
   lldb_private::LanguageRuntime *lang_rt = nullptr;
 
   std::string abi;
   ArchSpec target_arch;
   target_arch = target_sp->GetArchitecture();

source/Plugins/ExpressionParser/Clang/ClangModulesDeclVendor.cpp

 #include "clang/Sema/Lookup.h"
 #include "clang/Serialization/ASTReader.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Threading.h"
 
 #include "ClangHost.h"
 #include "ClangModulesDeclVendor.h"
+#include "ModuleDependencyCollector.h"
 
 #include "lldb/Core/ModuleList.h"
 #include "lldb/Host/Host.h"
 #include "lldb/Host/HostInfo.h"
 #include "lldb/Symbol/CompileUnit.h"
 #include "lldb/Target/Target.h"
 #include "lldb/Utility/FileSpec.h"
 #include "lldb/Utility/LLDBAssert.h"
 #include "lldb/Utility/Log.h"
+#include "lldb/Utility/Reproducer.h"
 #include "lldb/Utility/StreamString.h"
 
 using namespace lldb_private;
 
 namespace {
 // Any Clang compiler requires a consumer for diagnostics.  This one stores
 // them as strings so we can provide them to the user in case a module failed
 // to load.
std::unique_ptr<llvm::MemoryBuffer> source_buffer =
           ModuleImportBufferName);
 
   invocation->getPreprocessorOpts().addRemappedFile(ModuleImportBufferName,
                                                     source_buffer.release());
 
   std::unique_ptr<clang::CompilerInstance> instance(
       new clang::CompilerInstance);
 
+  // When capturing a reproducer, hook up the file collector with clang to
+  // collector modules and headers.
+  if (repro::Generator *g = repro::Reproducer::Instance().GetGenerator()) {
+    repro::FileProvider &fp = g->GetOrCreate<repro::FileProvider>();
+    instance->setModuleDepCollector(
+        std::make_shared<ModuleDependencyCollectorAdaptor>(
+            fp.GetFileCollector()));
+    clang::DependencyOutputOptions &opts = instance->getDependencyOutputOpts();
+    opts.IncludeSystemHeaders = true;
+    opts.IncludeModuleFiles = true;
+  }
+
   instance->setDiagnostics(diagnostics_engine.get());
   instance->setInvocation(invocation);
 
   std::unique_ptr<clang::FrontendAction> action(new clang::SyntaxOnlyAction);
 
   instance->setTarget(clang::TargetInfo::CreateTargetInfo(
       *diagnostics_engine, instance->getInvocation().TargetOpts));
 

source/Plugins/ExpressionParser/Clang/ModuleDependencyCollector.h

+//===-- ModuleDependencyCollector.h -----------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef liblldb_ModuleDependencyCollector_h_
+#define liblldb_ModuleDependencyCollector_h_
+
+#include "lldb/Utility/FileCollector.h"
+#include "clang/Frontend/Utils.h"
+#include "llvm/ADT/StringRef.h"
+
+namespace lldb_private {
+class ModuleDependencyCollectorAdaptor
+    : public clang::ModuleDependencyCollector {
+public:
+  ModuleDependencyCollectorAdaptor(FileCollector &file_collector)
+      : clang::ModuleDependencyCollector(""), m_file_collector(file_collector) {
+  }
+
+  void addFile(llvm::StringRef Filename,
+               llvm::StringRef FileDst = {}) override {
+    m_file_collector.AddFile(Filename);
+  }
+
+  bool insertSeen(llvm::StringRef Filename) override { return false; }
+  void addFileMapping(llvm::StringRef VPath, llvm::StringRef RPath) override {}
+  void writeFileMap() override {}
+
+private:
+  FileCollector &m_file_collector;
+};
+} // namespace lldb_private
+
+#endif