[PATCH] Relax some preconditions for using FixedCompilationDatabase.

[Edwin Vane]

Hi klimek, chandlerc, ddunbar,

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.

Note to reviewers: No tests yet as I wanted to get a preliminary "this
is the right direction" nod. I'll write up tests while waiting for review.

I selected reviewers based on who I understand to be stakeholders, code-owners,
or writers of code relating to the Driver's arg parsing. If I've missed anybody
please add them.

http://llvm-reviews.chandlerc.com/D2039

Files:
  lib/Tooling/CompilationDatabase.cpp

Index: lib/Tooling/CompilationDatabase.cpp
===================================================================
--- lib/Tooling/CompilationDatabase.cpp
+++ 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 {
 
@@ -100,16 +110,160 @@
 
 CompilationDatabasePlugin::~CompilationDatabasePlugin() {}
 
+// Helper for recursively searching through a chain of actions and collecting
+// all inputs, direct and indirect, of compile jobs.
+struct CompileJobAnalyzer {
+  CompileJobAnalyzer() : Collect(false) {}
+
+  void run(const driver::Action *A) {
+    bool setCollect = false;
+    switch (A->getKind()) {
+    case driver::Action::CompileJobClass:
+      setCollect = 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
+      ;
+    }
+
+    if (setCollect)
+      Collect = true;
+    for (driver::ActionList::const_iterator I = A->begin(), E = A->end();
+         I != E; ++I)
+      run(*I);
+    if (setCollect)
+      Collect = false;
+  }
+
+  SmallVector<StringRef, 2> Inputs;
+
+private:
+  bool Collect;
+};
+
+// 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:
+  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));
+    }
+  }
+
+  SmallVector<StringRef, 2> UnusedInputs;
+};
+
+// Unary functor for asking "Given a StringRef S1, does there exist a StringRef
+// S2 in Arr where S1.equals(S2)?".
+struct MatchesAny {
+  MatchesAny(ArrayRef<StringRef> Arr) : Arr(Arr) {}
+  bool operator() (StringRef S) {
+    for (const StringRef *I = Arr.begin(), *E = Arr.end(); I != E; ++I)
+      if (I->equals(S))
+        return true;
+    return false;
+  }
+private:
+  ArrayRef<StringRef> Arr;
+};
+
 FixedCompilationDatabase *
 FixedCompilationDatabase::loadFromCommandLine(int &Argc,
                                               const char **Argv,
                                               Twine Directory) {
   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);
+
+  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.
+  CommandLine.insert(CommandLine.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.
+  CommandLine.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.
+  CommandLine.push_back("placeholder.cpp");
+
+  const OwningPtr<driver::Compilation> Compilation(
+      NewDriver->BuildCompilation(CommandLine));
+
+  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 0;
+  }
+
+  // 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(CommandLine.begin(), CommandLine.end(),
+                     MatchesAny(CompileAnalyzer.Inputs));
+
+  // Remove all inputs deemed unused for compilation.
+  End = std::remove_if(CommandLine.begin(), End,
+                       MatchesAny(DiagClient.UnusedInputs));
+
+  llvm::errs() << "Modified command line:\n";
+  for (std::vector<const char *>::const_iterator I = CommandLine.begin();
+       I != End; ++I) {
+    llvm::errs() << *I << " ";
+  }
+  llvm::errs() << "\n";
+
+  return new FixedCompilationDatabase(
+      Directory, std::vector<std::string>(CommandLine.begin(), End));
 }
 
 FixedCompilationDatabase::
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D2039.1.patch
Type: text/x-patch
Size: 6626 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20131028/76900551/attachment.bin>