Relax some preconditions for using FixedCompilationDatabase.

FixedCompilationDatabase (FCD) requires that the arguments it consumes after
'--' must not include positional parameters or the argv[0] of the tool. This
patch relaxes those restrictions.

llvm-svn: 194968

clang/lib/Tooling/CompilationDatabase.cpp

@@ -20,6 +20,16 @@
 #include "llvm/Support/system_error.h"
 #include <sstream>
 
+#include "clang/Basic/Diagnostic.h"
+#include "clang/Driver/Action.h"
+#include "clang/Driver/Driver.h"
+#include "clang/Driver/DriverDiagnostic.h"
+#include "clang/Driver/Job.h"
+#include "clang/Driver/Compilation.h"
+#include "clang/Frontend/TextDiagnosticPrinter.h"
+#include "llvm/Support/Host.h"
+#include "llvm/Option/Arg.h"
+
 namespace clang {
 namespace tooling {
 
@@ -100,6 +110,175 @@ CompilationDatabase::autoDetectFromDirectory(StringRef SourceDir,
 
 CompilationDatabasePlugin::~CompilationDatabasePlugin() {}
 
+// Helper for recursively searching through a chain of actions and collecting
+// all inputs, direct and indirect, of compile jobs.
+struct CompileJobAnalyzer {
+  void run(const driver::Action *A) {
+    runImpl(A, false);
+  }
+
+  SmallVector<std::string, 2> Inputs;
+
+private:
+
+  void runImpl(const driver::Action *A, bool Collect) {
+    bool CollectChildren = Collect;
+    switch (A->getKind()) {
+    case driver::Action::CompileJobClass:
+      CollectChildren = true;
+      break;
+
+    case driver::Action::InputClass: {
+      if (Collect) {
+        const driver::InputAction *IA = cast<driver::InputAction>(A);
+        Inputs.push_back(IA->getInputArg().getSpelling());
+      }
+    } break;
+
+    default:
+      // Don't care about others
+      ;
+    }
+
+    for (driver::ActionList::const_iterator I = A->begin(), E = A->end();
+         I != E; ++I)
+      runImpl(*I, CollectChildren);
+  }
+};
+
+// Special DiagnosticConsumer that looks for warn_drv_input_file_unused
+// diagnostics from the driver and collects the option strings for those unused
+// options.
+class UnusedInputDiagConsumer : public DiagnosticConsumer {
+public:
+  UnusedInputDiagConsumer() : Other(0) {}
+
+  // Useful for debugging, chain diagnostics to another consumer after
+  // recording for our own purposes.
+  UnusedInputDiagConsumer(DiagnosticConsumer *Other) : Other(Other) {}
+
+  virtual void HandleDiagnostic(DiagnosticsEngine::Level DiagLevel,
+                                const Diagnostic &Info) LLVM_OVERRIDE {
+    if (Info.getID() == clang::diag::warn_drv_input_file_unused) {
+      // Arg 1 for this diagnostic is the option that didn't get used.
+      UnusedInputs.push_back(Info.getArgStdStr(0));
+    }
+    if (Other)
+      Other->HandleDiagnostic(DiagLevel, Info);
+  }
+
+  DiagnosticConsumer *Other;
+  SmallVector<std::string, 2> UnusedInputs;
+};
+
+// Unary functor for asking "Given a StringRef S1, does there exist a string
+// S2 in Arr where S1 == S2?"
+struct MatchesAny {
+  MatchesAny(ArrayRef<std::string> Arr) : Arr(Arr) {}
+  bool operator() (StringRef S) {
+    for (const std::string *I = Arr.begin(), *E = Arr.end(); I != E; ++I)
+      if (*I == S)
+        return true;
+    return false;
+  }
+private:
+  ArrayRef<std::string> Arr;
+};
+
+/// \brief Strips any positional args and possible argv[0] from a command-line
+/// provided by the user to construct a FixedCompilationDatabase.
+///
+/// FixedCompilationDatabase requires a command line to be in this format as it
+/// constructs the command line for each file by appending the name of the file
+/// to be compiled. FixedCompilationDatabase also adds its own argv[0] to the
+/// start of the command line although its value is not important as it's just
+/// ignored by the Driver invoked by the ClangTool using the
+/// FixedCompilationDatabase.
+///
+/// FIXME: This functionality should probably be made available by
+/// clang::driver::Driver although what the interface should look like is not
+/// clear.
+///
+/// \param[in] Args Args as provided by the user.
+/// \param[out] Resulting stripped command line.
+///
+/// \returns \li true if successful.
+///          \li false if \c Args cannot be used for compilation jobs (e.g.
+///          contains an option like -E or -version).
+bool stripPositionalArgs(std::vector<const char *> Args,
+                         std::vector<std::string> &Result) {
+  IntrusiveRefCntPtr<DiagnosticOptions> DiagOpts = new DiagnosticOptions();
+  UnusedInputDiagConsumer DiagClient;
+  DiagnosticsEngine Diagnostics(
+      IntrusiveRefCntPtr<clang::DiagnosticIDs>(new DiagnosticIDs()),
+      &*DiagOpts, &DiagClient, false);
+
+  // Neither clang executable nor default image name are required since the
+  // jobs the driver builds will not be executed.
+  OwningPtr<driver::Driver> NewDriver(new driver::Driver(
+      /* ClangExecutable= */ "", llvm::sys::getDefaultTargetTriple(),
+      /* DefaultImageName= */ "", Diagnostics));
+  NewDriver->setCheckInputsExist(false);
+
+  // This becomes the new argv[0]. The value is actually not important as it
+  // isn't used for invoking Tools.
+  Args.insert(Args.begin(), "clang-tool");
+
+  // By adding -c, we force the driver to treat compilation as the last phase.
+  // It will then issue warnings via Diagnostics about un-used options that
+  // would have been used for linking. If the user provided a compiler name as
+  // the original argv[0], this will be treated as a linker input thanks to
+  // insertng a new argv[0] above. All un-used options get collected by
+  // UnusedInputdiagConsumer and get stripped out later.
+  Args.push_back("-c");
+
+  // Put a dummy C++ file on to ensure there's at least one compile job for the
+  // driver to construct. If the user specified some other argument that
+  // prevents compilation, e.g. -E or something like -version, we may still end
+  // up with no jobs but then this is the user's fault.
+  Args.push_back("placeholder.cpp");
+
+  const OwningPtr<driver::Compilation> Compilation(
+      NewDriver->BuildCompilation(Args));
+
+  const driver::JobList &Jobs = Compilation->getJobs();
+
+  CompileJobAnalyzer CompileAnalyzer;
+
+  for (driver::JobList::const_iterator I = Jobs.begin(), E = Jobs.end(); I != E;
+       ++I) {
+    if ((*I)->getKind() == driver::Job::CommandClass) {
+      const driver::Command *Cmd = cast<driver::Command>(*I);
+      // Collect only for Assemble jobs. If we do all jobs we get duplicates
+      // since Link jobs point to Assemble jobs as inputs.
+      if (Cmd->getSource().getKind() == driver::Action::AssembleJobClass)
+        CompileAnalyzer.run(&Cmd->getSource());
+    }
+  }
+
+  if (CompileAnalyzer.Inputs.empty()) {
+    // No compile jobs found.
+    // FIXME: Emit a warning of some kind?
+    return false;
+  }
+
+  // Remove all compilation input files from the command line. This is
+  // necessary so that getCompileCommands() can construct a command line for
+  // each file.
+  std::vector<const char *>::iterator End = std::remove_if(
+      Args.begin(), Args.end(), MatchesAny(CompileAnalyzer.Inputs));
+
+  // Remove all inputs deemed unused for compilation.
+  End = std::remove_if(Args.begin(), End, MatchesAny(DiagClient.UnusedInputs));
+
+  // Remove the -c add above as well. It will be at the end right now.
+  assert(*(End - 1) == "-c");
+  --End;
+
+  Result = std::vector<std::string>(Args.begin() + 1, End);
+  return true;
+}
+
 FixedCompilationDatabase *
 FixedCompilationDatabase::loadFromCommandLine(int &Argc,
                                               const char **Argv,
@@ -107,9 +286,13 @@ FixedCompilationDatabase::loadFromCommandLine(int &Argc,
   const char **DoubleDash = std::find(Argv, Argv + Argc, StringRef("--"));
   if (DoubleDash == Argv + Argc)
     return NULL;
-  std::vector<std::string> CommandLine(DoubleDash + 1, Argv + Argc);
+  std::vector<const char *> CommandLine(DoubleDash + 1, Argv + Argc);
   Argc = DoubleDash - Argv;
-  return new FixedCompilationDatabase(Directory, CommandLine);
+
+  std::vector<std::string> StrippedArgs;
+  if (!stripPositionalArgs(CommandLine, StrippedArgs))
+    return 0;
+  return new FixedCompilationDatabase(Directory, StrippedArgs);
 }
 
 FixedCompilationDatabase::

clang/unittests/Tooling/CompilationDatabaseTest.cpp

@@ -450,7 +450,9 @@ TEST(ParseFixedCompilationDatabase, ReturnsNullWithoutDoubleDash) {
 
 TEST(ParseFixedCompilationDatabase, ReturnsArgumentsAfterDoubleDash) {
   int Argc = 5;
-  const char *Argv[] = { "1", "2", "--\0no-constant-folding", "3", "4" };
+  const char *Argv[] = {
+    "1", "2", "--\0no-constant-folding", "-DDEF3", "-DDEF4"
+  };
   OwningPtr<FixedCompilationDatabase> Database(
       FixedCompilationDatabase::loadFromCommandLine(Argc, Argv));
   ASSERT_TRUE(Database.isValid());
@@ -460,8 +462,8 @@ TEST(ParseFixedCompilationDatabase, ReturnsArgumentsAfterDoubleDash) {
   ASSERT_EQ(".", Result[0].Directory);
   std::vector<std::string> CommandLine;
   CommandLine.push_back("clang-tool");
-  CommandLine.push_back("3");
-  CommandLine.push_back("4");
+  CommandLine.push_back("-DDEF3");
+  CommandLine.push_back("-DDEF4");
   CommandLine.push_back("source");
   ASSERT_EQ(CommandLine, Result[0].CommandLine);
   EXPECT_EQ(2, Argc);
@@ -484,5 +486,41 @@ TEST(ParseFixedCompilationDatabase, ReturnsEmptyCommandLine) {
   EXPECT_EQ(2, Argc);
 }
 
+TEST(ParseFixedCompilationDatabase, HandlesPositionalArgs) {
+  const char *Argv[] = {"1", "2", "--", "-c", "somefile.cpp", "-DDEF3"};
+  int Argc = sizeof(Argv) / sizeof(char*);
+  OwningPtr<FixedCompilationDatabase> Database(
+      FixedCompilationDatabase::loadFromCommandLine(Argc, Argv));
+  ASSERT_TRUE(Database.isValid());
+  std::vector<CompileCommand> Result =
+    Database->getCompileCommands("source");
+  ASSERT_EQ(1ul, Result.size());
+  ASSERT_EQ(".", Result[0].Directory);
+  std::vector<std::string> Expected;
+  Expected.push_back("clang-tool");
+  Expected.push_back("-c");
+  Expected.push_back("-DDEF3");
+  Expected.push_back("source");
+  ASSERT_EQ(Expected, Result[0].CommandLine);
+  EXPECT_EQ(2, Argc);
+}
+
+TEST(ParseFixedCompilationDatabase, HandlesArgv0) {
+  const char *Argv[] = {"1", "2", "--", "mytool", "somefile.cpp"};
+  int Argc = sizeof(Argv) / sizeof(char*);
+  OwningPtr<FixedCompilationDatabase> Database(
+      FixedCompilationDatabase::loadFromCommandLine(Argc, Argv));
+  ASSERT_TRUE(Database.isValid());
+  std::vector<CompileCommand> Result =
+    Database->getCompileCommands("source");
+  ASSERT_EQ(1ul, Result.size());
+  ASSERT_EQ(".", Result[0].Directory);
+  std::vector<std::string> Expected;
+  Expected.push_back("clang-tool");
+  Expected.push_back("source");
+  ASSERT_EQ(Expected, Result[0].CommandLine);
+  EXPECT_EQ(2, Argc);
+}
+
 } // end namespace tooling
 } // end namespace clang