[libclang] Record parsing invocation to a temporary file when requested

by client

This patch extends libclang by allowing it to record parsing operations to a
temporary JSON file. The file is deleted after parsing succeeds. When a crash
happens during parsing, the file is preserved and the client will be able to use
it to generate a reproducer for the crash.

These files are not emitted by default, and the client has to specify the
invocation emission path first.

rdar://35322543

Differential Revision: https://reviews.llvm.org/D40527


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@319702 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 99 insertions, 0 deletions

diff --git a/tools/c-index-test/c-index-test.c b/tools/c-index-test/c-index-test.c
index a11e03c846..6cb67e1030 100644
--- a/tools/c-index-test/c-index-test.c
+++ b/tools/c-index-test/c-index-test.c
@@ -1747,11 +1747,15 @@ int perform_test_load_source(int argc, const char **argv,
   int result;
   unsigned Repeats = 0;
   unsigned I;
+  const char *InvocationPath;
 
   Idx = clang_createIndex(/* excludeDeclsFromPCH */
                           (!strcmp(filter, "local") || 
                            !strcmp(filter, "local-display"))? 1 : 0,
                           /* displayDiagnostics=*/1);
+  InvocationPath = getenv("CINDEXTEST_INVOCATION_EMISSION_PATH");
+  if (InvocationPath)
+    clang_CXIndex_setInvocationEmissionPathOption(Idx, InvocationPath);
 
   if ((CommentSchemaFile = parse_comments_schema(argc, argv))) {
     argc--;
diff --git a/tools/libclang/CIndex.cpp b/tools/libclang/CIndex.cpp
index 455151f0fc..b642014c43 100644
--- a/tools/libclang/CIndex.cpp
+++ b/tools/libclang/CIndex.cpp
@@ -3255,6 +3255,12 @@ unsigned clang_CXIndex_getGlobalOptions(CXIndex CIdx) {
   return 0;
 }
 
+void clang_CXIndex_setInvocationEmissionPathOption(CXIndex CIdx,
+                                                   const char *Path) {
+  if (CIdx)
+    static_cast<CIndexer *>(CIdx)->setInvocationEmissionPath(Path ? Path : "");
+}
+
 void clang_toggleCrashRecovery(unsigned isEnabled) {
   if (isEnabled)
     llvm::CrashRecoveryContext::Enable();
@@ -3431,6 +3437,11 @@ clang_parseTranslationUnit_Impl(CXIndex CIdx, const char *source_filename,
   // faster, trading for a slower (first) reparse.
   unsigned PrecompilePreambleAfterNParses =
       !PrecompilePreamble ? 0 : 2 - CreatePreambleOnFirstParse;
+
+  // FIXME: Record the hash of the unsaved files.
+  LibclangInvocationReporter InvocationReporter(
+      *CXXIdx, LibclangInvocationReporter::OperationKind::ParseOperation,
+      options, llvm::makeArrayRef(*Args));
   std::unique_ptr<ASTUnit> Unit(ASTUnit::LoadFromCommandLine(
       Args->data(), Args->data() + Args->size(),
       CXXIdx->getPCHContainerOperations(), Diags,
diff --git a/tools/libclang/CIndexer.cpp b/tools/libclang/CIndexer.cpp
index 694ed60630..13774bd8b7 100644
--- a/tools/libclang/CIndexer.cpp
+++ b/tools/libclang/CIndexer.cpp
@@ -14,8 +14,10 @@
 #include "CIndexer.h"
 #include "clang/Basic/LLVM.h"
 #include "clang/Basic/Version.h"
+#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/Config/llvm-config.h"
+#include "llvm/Support/MutexGuard.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Program.h"
 #include <cstdio>
@@ -76,3 +78,56 @@ const std::string &CIndexer::getClangResourcesPath() {
   ResourcesPath = LibClangPath.str();
   return ResourcesPath;
 }
+
+StringRef CIndexer::getClangToolchainPath() {
+  if (!ToolchainPath.empty())
+    return ToolchainPath;
+  StringRef ResourcePath = getClangResourcesPath();
+  ToolchainPath = llvm::sys::path::parent_path(
+      llvm::sys::path::parent_path(llvm::sys::path::parent_path(ResourcePath)));
+  return ToolchainPath;
+}
+
+LibclangInvocationReporter::LibclangInvocationReporter(
+    CIndexer &Idx, OperationKind Op, unsigned ParseOptions,
+    llvm::ArrayRef<const char *> Args) {
+  StringRef Path = Idx.getInvocationEmissionPath();
+  if (Path.empty())
+    return;
+
+  // Create a temporary file for the invocation log.
+  SmallString<256> TempPath;
+  TempPath = Path;
+  llvm::sys::path::append(TempPath, "libclang-%%%%%%%%%%%%");
+  int FD;
+  if (llvm::sys::fs::createUniqueFile(TempPath, FD, TempPath))
+    return;
+  File = std::string(TempPath.begin(), TempPath.end());
+  llvm::raw_fd_ostream OS(FD, /*ShouldClose=*/true);
+
+  // Write out the information about the invocation to it.
+  auto WriteStringKey = [&OS](StringRef Key, StringRef Value) {
+    OS << R"(")" << Key << R"(":")";
+    OS << Value << '"';
+  };
+  OS << '{';
+  WriteStringKey("toolchain", Idx.getClangToolchainPath());
+  OS << ',';
+  WriteStringKey("libclang.operation",
+                 Op == OperationKind::ParseOperation ? "parse" : "complete");
+  OS << ',';
+  OS << R"("libclang.opts":)" << ParseOptions;
+  OS << ',';
+  OS << R"("args":[)";
+  for (const auto &I : llvm::enumerate(Args)) {
+    if (I.index())
+      OS << ',';
+    OS << '"' << I.value() << '"';
+  }
+  OS << "]}";
+}
+
+LibclangInvocationReporter::~LibclangInvocationReporter() {
+  if (!File.empty())
+    llvm::sys::fs::remove(File);
+}
diff --git a/tools/libclang/CIndexer.h b/tools/libclang/CIndexer.h
index b227f943f7..b3346cd955 100644
--- a/tools/libclang/CIndexer.h
+++ b/tools/libclang/CIndexer.h
@@ -18,6 +18,7 @@
 #include "clang-c/Index.h"
 #include "clang/Frontend/PCHContainerOperations.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/Support/Mutex.h"
 #include <utility>
 
 namespace llvm {
@@ -40,6 +41,10 @@ class CIndexer {
   std::string ResourcesPath;
   std::shared_ptr<PCHContainerOperations> PCHContainerOps;
 
+  std::string ToolchainPath;
+
+  std::string InvocationEmissionPath;
+
 public:
   CIndexer(std::shared_ptr<PCHContainerOperations> PCHContainerOps =
                std::make_shared<PCHContainerOperations>())
@@ -71,6 +76,29 @@ public:
 
   /// \brief Get the path of the clang resource files.
   const std::string &getClangResourcesPath();
+
+  StringRef getClangToolchainPath();
+
+  void setInvocationEmissionPath(StringRef Str) {
+    InvocationEmissionPath = Str;
+  }
+
+  StringRef getInvocationEmissionPath() const { return InvocationEmissionPath; }
+};
+
+/// Logs information about a particular libclang operation like parsing to
+/// a new file in the invocation emission path.
+class LibclangInvocationReporter {
+public:
+  enum class OperationKind { ParseOperation, CompletionOperation };
+
+  LibclangInvocationReporter(CIndexer &Idx, OperationKind Op,
+                             unsigned ParseOptions,
+                             llvm::ArrayRef<const char *> Args);
+  ~LibclangInvocationReporter();
+
+private:
+  std::string File;
 };
 
   /// \brief Return the current size to request for "safety".
diff --git a/tools/libclang/libclang.exports b/tools/libclang/libclang.exports
index fb4547a867..bd262ee1a0 100644
--- a/tools/libclang/libclang.exports
+++ b/tools/libclang/libclang.exports
@@ -2,6 +2,7 @@ clang_CXCursorSet_contains
 clang_CXCursorSet_insert
 clang_CXIndex_getGlobalOptions
 clang_CXIndex_setGlobalOptions
+clang_CXIndex_setInvocationEmissionPathOption
 clang_CXXConstructor_isConvertingConstructor
 clang_CXXConstructor_isCopyConstructor
 clang_CXXConstructor_isDefaultConstructor