Add the clang library to the repo (with some of my changes, too).

4 files changed, 582 insertions, 0 deletions

diff --git a/clang/lib/Tooling/CMakeLists.txt b/clang/lib/Tooling/CMakeLists.txt
new file mode 100644
index 0000000..b84b211
--- /dev/null
+++ b/clang/lib/Tooling/CMakeLists.txt
@@ -0,0 +1,7 @@
+set(LLVM_LINK_COMPONENTS support)
+SET(LLVM_USED_LIBS clangBasic clangFrontend clangAST)
+
+add_clang_library(clangTooling
+  CompilationDatabase.cpp
+  Tooling.cpp
+  )
diff --git a/clang/lib/Tooling/CompilationDatabase.cpp b/clang/lib/Tooling/CompilationDatabase.cpp
new file mode 100644
index 0000000..dd9ccc0
--- /dev/null
+++ b/clang/lib/Tooling/CompilationDatabase.cpp
@@ -0,0 +1,266 @@
+//===--- CompilationDatabase.cpp - ----------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+//  This file contains multiple implementations for CompilationDatabases.
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/Tooling/CompilationDatabase.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/Support/YAMLParser.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/system_error.h"
+
+namespace clang {
+namespace tooling {
+
+namespace {
+
+/// \brief A parser for escaped strings of command line arguments.
+///
+/// Assumes \-escaping for quoted arguments (see the documentation of
+/// unescapeCommandLine(...)).
+class CommandLineArgumentParser {
+ public:
+  CommandLineArgumentParser(StringRef CommandLine)
+      : Input(CommandLine), Position(Input.begin()-1) {}
+
+  std::vector<std::string> parse() {
+    bool HasMoreInput = true;
+    while (HasMoreInput && nextNonWhitespace()) {
+      std::string Argument;
+      HasMoreInput = parseStringInto(Argument);
+      CommandLine.push_back(Argument);
+    }
+    return CommandLine;
+  }
+
+ private:
+  // All private methods return true if there is more input available.
+
+  bool parseStringInto(std::string &String) {
+    do {
+      if (*Position == '"') {
+        if (!parseQuotedStringInto(String)) return false;
+      } else {
+        if (!parseFreeStringInto(String)) return false;
+      }
+    } while (*Position != ' ');
+    return true;
+  }
+
+  bool parseQuotedStringInto(std::string &String) {
+    if (!next()) return false;
+    while (*Position != '"') {
+      if (!skipEscapeCharacter()) return false;
+      String.push_back(*Position);
+      if (!next()) return false;
+    }
+    return next();
+  }
+
+  bool parseFreeStringInto(std::string &String) {
+    do {
+      if (!skipEscapeCharacter()) return false;
+      String.push_back(*Position);
+      if (!next()) return false;
+    } while (*Position != ' ' && *Position != '"');
+    return true;
+  }
+
+  bool skipEscapeCharacter() {
+    if (*Position == '\\') {
+      return next();
+    }
+    return true;
+  }
+
+  bool nextNonWhitespace() {
+    do {
+      if (!next()) return false;
+    } while (*Position == ' ');
+    return true;
+  }
+
+  bool next() {
+    ++Position;
+    return Position != Input.end();
+  }
+
+  const StringRef Input;
+  StringRef::iterator Position;
+  std::vector<std::string> CommandLine;
+};
+
+std::vector<std::string> unescapeCommandLine(
+    StringRef EscapedCommandLine) {
+  CommandLineArgumentParser parser(EscapedCommandLine);
+  return parser.parse();
+}
+
+} // end namespace
+
+CompilationDatabase::~CompilationDatabase() {}
+
+CompilationDatabase *
+CompilationDatabase::loadFromDirectory(StringRef BuildDirectory,
+                                       std::string &ErrorMessage) {
+  llvm::SmallString<1024> JSONDatabasePath(BuildDirectory);
+  llvm::sys::path::append(JSONDatabasePath, "compile_commands.json");
+  llvm::OwningPtr<CompilationDatabase> Database(
+    JSONCompilationDatabase::loadFromFile(JSONDatabasePath, ErrorMessage));
+  if (!Database) {
+    return NULL;
+  }
+  return Database.take();
+}
+
+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);
+  Argc = DoubleDash - Argv;
+  return new FixedCompilationDatabase(Directory, CommandLine);
+}
+
+FixedCompilationDatabase::
+FixedCompilationDatabase(Twine Directory, ArrayRef<std::string> CommandLine) {
+  std::vector<std::string> ToolCommandLine(1, "clang-tool");
+  ToolCommandLine.insert(ToolCommandLine.end(),
+                         CommandLine.begin(), CommandLine.end());
+  CompileCommands.push_back(CompileCommand(Directory, ToolCommandLine));
+}
+
+std::vector<CompileCommand>
+FixedCompilationDatabase::getCompileCommands(StringRef FilePath) const {
+  std::vector<CompileCommand> Result(CompileCommands);
+  Result[0].CommandLine.push_back(FilePath);
+  return Result;
+}
+
+JSONCompilationDatabase *
+JSONCompilationDatabase::loadFromFile(StringRef FilePath,
+                                      std::string &ErrorMessage) {
+  llvm::OwningPtr<llvm::MemoryBuffer> DatabaseBuffer;
+  llvm::error_code Result =
+    llvm::MemoryBuffer::getFile(FilePath, DatabaseBuffer);
+  if (Result != 0) {
+    ErrorMessage = "Error while opening JSON database: " + Result.message();
+    return NULL;
+  }
+  llvm::OwningPtr<JSONCompilationDatabase> Database(
+    new JSONCompilationDatabase(DatabaseBuffer.take()));
+  if (!Database->parse(ErrorMessage))
+    return NULL;
+  return Database.take();
+}
+
+JSONCompilationDatabase *
+JSONCompilationDatabase::loadFromBuffer(StringRef DatabaseString,
+                                        std::string &ErrorMessage) {
+  llvm::OwningPtr<llvm::MemoryBuffer> DatabaseBuffer(
+      llvm::MemoryBuffer::getMemBuffer(DatabaseString));
+  llvm::OwningPtr<JSONCompilationDatabase> Database(
+    new JSONCompilationDatabase(DatabaseBuffer.take()));
+  if (!Database->parse(ErrorMessage))
+    return NULL;
+  return Database.take();
+}
+
+std::vector<CompileCommand>
+JSONCompilationDatabase::getCompileCommands(StringRef FilePath) const {
+  llvm::StringMap< std::vector<CompileCommandRef> >::const_iterator
+    CommandsRefI = IndexByFile.find(FilePath);
+  if (CommandsRefI == IndexByFile.end())
+    return std::vector<CompileCommand>();
+  const std::vector<CompileCommandRef> &CommandsRef = CommandsRefI->getValue();
+  std::vector<CompileCommand> Commands;
+  for (int I = 0, E = CommandsRef.size(); I != E; ++I) {
+    llvm::SmallString<8> DirectoryStorage;
+    llvm::SmallString<1024> CommandStorage;
+    Commands.push_back(CompileCommand(
+      // FIXME: Escape correctly:
+      CommandsRef[I].first->getValue(DirectoryStorage),
+      unescapeCommandLine(CommandsRef[I].second->getValue(CommandStorage))));
+  }
+  return Commands;
+}
+
+bool JSONCompilationDatabase::parse(std::string &ErrorMessage) {
+  llvm::yaml::document_iterator I = YAMLStream.begin();
+  if (I == YAMLStream.end()) {
+    ErrorMessage = "Error while parsing YAML.";
+    return false;
+  }
+  llvm::yaml::Node *Root = I->getRoot();
+  if (Root == NULL) {
+    ErrorMessage = "Error while parsing YAML.";
+    return false;
+  }
+  llvm::yaml::SequenceNode *Array =
+    llvm::dyn_cast<llvm::yaml::SequenceNode>(Root);
+  if (Array == NULL) {
+    ErrorMessage = "Expected array.";
+    return false;
+  }
+  for (llvm::yaml::SequenceNode::iterator AI = Array->begin(),
+                                          AE = Array->end();
+       AI != AE; ++AI) {
+    llvm::yaml::MappingNode *Object =
+      llvm::dyn_cast<llvm::yaml::MappingNode>(&*AI);
+    if (Object == NULL) {
+      ErrorMessage = "Expected object.";
+      return false;
+    }
+    llvm::yaml::ScalarNode *Directory;
+    llvm::yaml::ScalarNode *Command;
+    llvm::SmallString<8> FileStorage;
+    llvm::StringRef File;
+    for (llvm::yaml::MappingNode::iterator KVI = Object->begin(),
+                                           KVE = Object->end();
+         KVI != KVE; ++KVI) {
+      llvm::yaml::Node *Value = (*KVI).getValue();
+      if (Value == NULL) {
+        ErrorMessage = "Expected value.";
+        return false;
+      }
+      llvm::yaml::ScalarNode *ValueString =
+        llvm::dyn_cast<llvm::yaml::ScalarNode>(Value);
+      if (ValueString == NULL) {
+        ErrorMessage = "Expected string as value.";
+        return false;
+      }
+      llvm::yaml::ScalarNode *KeyString =
+        llvm::dyn_cast<llvm::yaml::ScalarNode>((*KVI).getKey());
+      llvm::SmallString<8> KeyStorage;
+      if (KeyString->getValue(KeyStorage) == "directory") {
+        Directory = ValueString;
+      } else if (KeyString->getValue(KeyStorage) == "command") {
+        Command = ValueString;
+      } else if (KeyString->getValue(KeyStorage) == "file") {
+        File = ValueString->getValue(FileStorage);
+      } else {
+        ErrorMessage = ("Unknown key: \"" +
+                        KeyString->getRawValue() + "\"").str();
+        return false;
+      }
+    }
+    IndexByFile[File].push_back(
+      CompileCommandRef(Directory, Command));
+  }
+  return true;
+}
+
+} // end namespace tooling
+} // end namespace clang
+
diff --git a/clang/lib/Tooling/Makefile b/clang/lib/Tooling/Makefile
new file mode 100644
index 0000000..0d2e7a2
--- /dev/null
+++ b/clang/lib/Tooling/Makefile
@@ -0,0 +1,13 @@
+##===- clang/lib/Tooling/Makefile ---------------------------*- Makefile -*-===##
+#
+#                     The LLVM Compiler Infrastructure
+#
+# This file is distributed under the University of Illinois Open Source
+# License. See LICENSE.TXT for details.
+#
+##===----------------------------------------------------------------------===##
+
+CLANG_LEVEL := ../..
+LIBRARYNAME := clangTooling
+
+include $(CLANG_LEVEL)/Makefile
diff --git a/clang/lib/Tooling/Tooling.cpp b/clang/lib/Tooling/Tooling.cpp
new file mode 100644
index 0000000..fa2374f
--- /dev/null
+++ b/clang/lib/Tooling/Tooling.cpp
@@ -0,0 +1,296 @@
+//===--- Tooling.cpp - Running clang standalone tools ---------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+//  This file implements functions to run clang tools standalone instead
+//  of running them as a plugin.
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/Tooling/Tooling.h"
+#include "clang/Tooling/CompilationDatabase.h"
+#include "clang/Driver/Compilation.h"
+#include "clang/Driver/Driver.h"
+#include "clang/Driver/Tool.h"
+#include "clang/Frontend/CompilerInstance.h"
+#include "clang/Frontend/FrontendAction.h"
+#include "clang/Frontend/FrontendDiagnostic.h"
+#include "clang/Frontend/TextDiagnosticPrinter.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/Host.h"
+#include "llvm/Support/raw_ostream.h"
+
+namespace clang {
+namespace tooling {
+
+FrontendActionFactory::~FrontendActionFactory() {}
+
+// FIXME: This file contains structural duplication with other parts of the
+// code that sets up a compiler to run tools on it, and we should refactor
+// it to be based on the same framework.
+
+/// \brief Builds a clang driver initialized for running clang tools.
+static clang::driver::Driver *newDriver(clang::DiagnosticsEngine *Diagnostics,
+                                        const char *BinaryName) {
+  const std::string DefaultOutputName = "a.out";
+  clang::driver::Driver *CompilerDriver = new clang::driver::Driver(
+      BinaryName, llvm::sys::getDefaultTargetTriple(),
+      DefaultOutputName, false, *Diagnostics);
+  CompilerDriver->setTitle("clang_based_tool");
+  return CompilerDriver;
+}
+
+/// \brief Retrieves the clang CC1 specific flags out of the compilation's jobs.
+///
+/// Returns NULL on error.
+static const clang::driver::ArgStringList *getCC1Arguments(
+    clang::DiagnosticsEngine *Diagnostics,
+    clang::driver::Compilation *Compilation) {
+  // We expect to get back exactly one Command job, if we didn't something
+  // failed. Extract that job from the Compilation.
+  const clang::driver::JobList &Jobs = Compilation->getJobs();
+  if (Jobs.size() != 1 || !isa<clang::driver::Command>(*Jobs.begin())) {
+    llvm::SmallString<256> error_msg;
+    llvm::raw_svector_ostream error_stream(error_msg);
+    Compilation->PrintJob(error_stream, Compilation->getJobs(), "; ", true);
+    Diagnostics->Report(clang::diag::err_fe_expected_compiler_job)
+        << error_stream.str();
+    return NULL;
+  }
+
+  // The one job we find should be to invoke clang again.
+  const clang::driver::Command *Cmd =
+      cast<clang::driver::Command>(*Jobs.begin());
+  if (StringRef(Cmd->getCreator().getName()) != "clang") {
+    Diagnostics->Report(clang::diag::err_fe_expected_clang_command);
+    return NULL;
+  }
+
+  return &Cmd->getArguments();
+}
+
+/// \brief Returns a clang build invocation initialized from the CC1 flags.
+static clang::CompilerInvocation *newInvocation(
+    clang::DiagnosticsEngine *Diagnostics,
+    const clang::driver::ArgStringList &CC1Args) {
+  assert(!CC1Args.empty() && "Must at least contain the program name!");
+  clang::CompilerInvocation *Invocation = new clang::CompilerInvocation;
+  clang::CompilerInvocation::CreateFromArgs(
+      *Invocation, CC1Args.data() + 1, CC1Args.data() + CC1Args.size(),
+      *Diagnostics);
+  Invocation->getFrontendOpts().DisableFree = false;
+  return Invocation;
+}
+
+bool runToolOnCode(clang::FrontendAction *ToolAction, const Twine &Code,
+                   const Twine &FileName) {
+  SmallString<16> FileNameStorage;
+  StringRef FileNameRef = FileName.toNullTerminatedStringRef(FileNameStorage);
+  const char *const CommandLine[] = {
+      "clang-tool", "-fsyntax-only", FileNameRef.data()
+  };
+  FileManager Files((FileSystemOptions()));
+  ToolInvocation Invocation(
+      std::vector<std::string>(
+          CommandLine,
+          CommandLine + llvm::array_lengthof(CommandLine)),
+      ToolAction, &Files);
+
+  SmallString<1024> CodeStorage;
+  Invocation.mapVirtualFile(FileNameRef,
+                            Code.toNullTerminatedStringRef(CodeStorage));
+  return Invocation.run();
+}
+
+/// \brief Returns the absolute path of 'File', by prepending it with
+/// 'BaseDirectory' if 'File' is not absolute.
+///
+/// Otherwise returns 'File'.
+/// If 'File' starts with "./", the returned path will not contain the "./".
+/// Otherwise, the returned path will contain the literal path-concatenation of
+/// 'BaseDirectory' and 'File'.
+///
+/// \param File Either an absolute or relative path.
+/// \param BaseDirectory An absolute path.
+static std::string getAbsolutePath(
+    StringRef File, StringRef BaseDirectory) {
+  assert(llvm::sys::path::is_absolute(BaseDirectory));
+  if (llvm::sys::path::is_absolute(File)) {
+    return File;
+  }
+  StringRef RelativePath(File);
+  if (RelativePath.startswith("./")) {
+    RelativePath = RelativePath.substr(strlen("./"));
+  }
+  llvm::SmallString<1024> AbsolutePath(BaseDirectory);
+  llvm::sys::path::append(AbsolutePath, RelativePath);
+  return AbsolutePath.str();
+}
+
+ToolInvocation::ToolInvocation(
+    ArrayRef<std::string> CommandLine, FrontendAction *ToolAction,
+    FileManager *Files)
+    : CommandLine(CommandLine.vec()), ToolAction(ToolAction), Files(Files) {
+}
+
+void ToolInvocation::mapVirtualFile(StringRef FilePath, StringRef Content) {
+  MappedFileContents[FilePath] = Content;
+}
+
+bool ToolInvocation::run() {
+  std::vector<const char*> Argv;
+  for (int I = 0, E = CommandLine.size(); I != E; ++I)
+    Argv.push_back(CommandLine[I].c_str());
+  const char *const BinaryName = Argv[0];
+  DiagnosticOptions DefaultDiagnosticOptions;
+  TextDiagnosticPrinter DiagnosticPrinter(
+      llvm::errs(), DefaultDiagnosticOptions);
+  DiagnosticsEngine Diagnostics(llvm::IntrusiveRefCntPtr<clang::DiagnosticIDs>(
+      new DiagnosticIDs()), &DiagnosticPrinter, false);
+
+  const llvm::OwningPtr<clang::driver::Driver> Driver(
+      newDriver(&Diagnostics, BinaryName));
+  // Since the input might only be virtual, don't check whether it exists.
+  Driver->setCheckInputsExist(false);
+  const llvm::OwningPtr<clang::driver::Compilation> Compilation(
+      Driver->BuildCompilation(llvm::makeArrayRef(Argv)));
+  const clang::driver::ArgStringList *const CC1Args = getCC1Arguments(
+      &Diagnostics, Compilation.get());
+  if (CC1Args == NULL) {
+    return false;
+  }
+  llvm::OwningPtr<clang::CompilerInvocation> Invocation(
+      newInvocation(&Diagnostics, *CC1Args));
+  return runInvocation(BinaryName, Compilation.get(),
+                       Invocation.take(), *CC1Args, ToolAction.take());
+}
+
+// Exists solely for the purpose of lookup of the resource path.
+static int StaticSymbol;
+
+bool ToolInvocation::runInvocation(
+    const char *BinaryName,
+    clang::driver::Compilation *Compilation,
+    clang::CompilerInvocation *Invocation,
+    const clang::driver::ArgStringList &CC1Args,
+    clang::FrontendAction *ToolAction) {
+  llvm::OwningPtr<clang::FrontendAction> ScopedToolAction(ToolAction);
+  // Show the invocation, with -v.
+  if (Invocation->getHeaderSearchOpts().Verbose) {
+    llvm::errs() << "clang Invocation:\n";
+    Compilation->PrintJob(llvm::errs(), Compilation->getJobs(), "\n", true);
+    llvm::errs() << "\n";
+  }
+
+  // Create a compiler instance to handle the actual work.
+  clang::CompilerInstance Compiler;
+  Compiler.setInvocation(Invocation);
+  Compiler.setFileManager(Files);
+  // FIXME: What about LangOpts?
+
+  // Create the compilers actual diagnostics engine.
+  Compiler.createDiagnostics(CC1Args.size(),
+                             const_cast<char**>(CC1Args.data()));
+  if (!Compiler.hasDiagnostics())
+    return false;
+
+  Compiler.createSourceManager(*Files);
+  addFileMappingsTo(Compiler.getSourceManager());
+
+  // Infer the builtin include path if unspecified.
+  if (Compiler.getHeaderSearchOpts().UseBuiltinIncludes &&
+      Compiler.getHeaderSearchOpts().ResourceDir.empty()) {
+    // This just needs to be some symbol in the binary.
+    void *const SymbolAddr = &StaticSymbol;
+    Compiler.getHeaderSearchOpts().ResourceDir =
+        clang::CompilerInvocation::GetResourcesPath(BinaryName, SymbolAddr);
+  }
+
+  const bool Success = Compiler.ExecuteAction(*ToolAction);
+
+  Compiler.resetAndLeakFileManager();
+  return Success;
+}
+
+void ToolInvocation::addFileMappingsTo(SourceManager &Sources) {
+  for (llvm::StringMap<StringRef>::const_iterator
+           It = MappedFileContents.begin(), End = MappedFileContents.end();
+       It != End; ++It) {
+    // Inject the code as the given file name into the preprocessor options.
+    const llvm::MemoryBuffer *Input =
+        llvm::MemoryBuffer::getMemBuffer(It->getValue());
+    // FIXME: figure out what '0' stands for.
+    const FileEntry *FromFile = Files->getVirtualFile(
+        It->getKey(), Input->getBufferSize(), 0);
+    // FIXME: figure out memory management ('true').
+    Sources.overrideFileContents(FromFile, Input, true);
+  }
+}
+
+ClangTool::ClangTool(const CompilationDatabase &Compilations,
+                     ArrayRef<std::string> SourcePaths)
+    : Files((FileSystemOptions())) {
+  llvm::SmallString<1024> BaseDirectory;
+  if (const char *PWD = ::getenv("PWD"))
+    BaseDirectory = PWD;
+  else
+    llvm::sys::fs::current_path(BaseDirectory);
+  for (unsigned I = 0, E = SourcePaths.size(); I != E; ++I) {
+    llvm::SmallString<1024> File(getAbsolutePath(
+        SourcePaths[I], BaseDirectory));
+
+    std::vector<CompileCommand> CompileCommands =
+      Compilations.getCompileCommands(File.str());
+    if (!CompileCommands.empty()) {
+      for (int I = 0, E = CompileCommands.size(); I != E; ++I) {
+        CompileCommand &Command = CompileCommands[I];
+        if (!Command.Directory.empty()) {
+          // FIXME: What should happen if CommandLine includes -working-directory
+          // as well?
+          Command.CommandLine.push_back(
+            "-working-directory=" + Command.Directory);
+        }
+        CommandLines.push_back(std::make_pair(File.str(), Command.CommandLine));
+      }
+    } else {
+      // FIXME: There are two use cases here: doing a fuzzy
+      // "find . -name '*.cc' |xargs tool" match, where as a user I don't care
+      // about the .cc files that were not found, and the use case where I
+      // specify all files I want to run over explicitly, where this should
+      // be an error. We'll want to add an option for this.
+      llvm::outs() << "Skipping " << File << ". Command line not found.\n";
+    }
+  }
+}
+
+void ClangTool::mapVirtualFile(StringRef FilePath, StringRef Content) {
+  MappedFileContents.push_back(std::make_pair(FilePath, Content));
+}
+
+int ClangTool::run(FrontendActionFactory *ActionFactory) {
+  bool ProcessingFailed = false;
+  for (unsigned I = 0; I < CommandLines.size(); ++I) {
+    std::string File = CommandLines[I].first;
+    std::vector<std::string> &CommandLine = CommandLines[I].second;
+    llvm::outs() << "Processing: " << File << ".\n";
+    ToolInvocation Invocation(CommandLine, ActionFactory->create(), &Files);
+    for (int I = 0, E = MappedFileContents.size(); I != E; ++I) {
+      Invocation.mapVirtualFile(MappedFileContents[I].first,
+                                MappedFileContents[I].second);
+    }
+    if (!Invocation.run()) {
+      llvm::outs() << "Error while processing " << File << ".\n";
+      ProcessingFailed = true;
+    }
+  }
+  return ProcessingFailed ? 1 : 0;
+}
+
+} // end namespace tooling
+} // end namespace clang