Extend CompilationDatabase by a field for the output filename

In bigger projects like an Operating System, the same source code is
often compiled in slightly different ways. This could be the difference
between PIC and non-PIC code for static vs dynamic libraries, it could
also be the difference between size optimised versions of tools for
ramdisk images. At the moment, the compilation database has no way to
distinguish such cases. As first step, add a field in the JSON format
for it and process it accordingly.

Differential Revision: https://reviews.llvm.org/D27138


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@288436 91177308-0d34-0410-b5e6-96231b3b80d8

docs/JSONCompilationDatabase.rst

@@ -80,6 +80,9 @@ The contracts for each field in the command object are:
    supported.
 -  **arguments:** The compile command executed as list of strings.
    Either **arguments** or **command** is required.
+-  **output:** The name of the output created by this compilation step.
+   This field is optional. It can be used to distinguish different processing
+   modes of the same input file.
 
 Build System Integration
 ========================

include/clang/Tooling/CompilationDatabase.h

@@ -43,10 +43,11 @@ namespace tooling {
 struct CompileCommand {
   CompileCommand() {}
   CompileCommand(Twine Directory, Twine Filename,
-                 std::vector<std::string> CommandLine)
+                 std::vector<std::string> CommandLine, Twine Output)
       : Directory(Directory.str()),
         Filename(Filename.str()),
-        CommandLine(std::move(CommandLine)) {}
+        CommandLine(std::move(CommandLine)),
+        Output(Output.str()){}
 
   /// \brief The working directory the command was executed from.
   std::string Directory;
@@ -57,6 +58,9 @@ struct CompileCommand {
   /// \brief The command line that was executed.
   std::vector<std::string> CommandLine;
 
+  /// The output file associated with the command.
+  std::string Output;
+
   /// \brief An optional mapping from each file's path to its content for all
   /// files needed for the compilation that are not available via the file
   /// system.

include/clang/Tooling/JSONCompilationDatabase.h

@@ -103,15 +103,17 @@ private:
   /// failed.
   bool parse(std::string &ErrorMessage);
 
-  // Tuple (directory, filename, commandline) where 'commandline' points to the
-  // corresponding scalar nodes in the YAML stream.
+  // Tuple (directory, filename, commandline, output) where 'commandline'
+  // points to the corresponding scalar nodes in the YAML stream.
   // If the command line contains a single argument, it is a shell-escaped
   // command line.
   // Otherwise, each entry in the command line vector is a literal
   // argument to the compiler.
+  // The output field may be a nullptr.
   typedef std::tuple<llvm::yaml::ScalarNode *,
                      llvm::yaml::ScalarNode *,
-                    std::vector<llvm::yaml::ScalarNode *>> CompileCommandRef;
+                     std::vector<llvm::yaml::ScalarNode *>,
+                     llvm::yaml::ScalarNode *> CompileCommandRef;
 
   /// \brief Converts the given array of CompileCommandRefs to CompileCommands.
   void getCommands(ArrayRef<CompileCommandRef> CommandsRef,

lib/Tooling/CompilationDatabase.cpp

@@ -300,7 +300,8 @@ FixedCompilationDatabase(Twine Directory, ArrayRef<std::string> CommandLine) {
   ToolCommandLine.insert(ToolCommandLine.end(),
                          CommandLine.begin(), CommandLine.end());
   CompileCommands.emplace_back(Directory, StringRef(),
-                               std::move(ToolCommandLine));
+                               std::move(ToolCommandLine),
+                               StringRef());
 }
 
 std::vector<CompileCommand>

lib/Tooling/JSONCompilationDatabase.cpp

@@ -257,10 +257,13 @@ void JSONCompilationDatabase::getCommands(
   for (int I = 0, E = CommandsRef.size(); I != E; ++I) {
     SmallString<8> DirectoryStorage;
     SmallString<32> FilenameStorage;
+    SmallString<32> OutputStorage;
+    auto Output = std::get<3>(CommandsRef[I]);
     Commands.emplace_back(
         std::get<0>(CommandsRef[I])->getValue(DirectoryStorage),
         std::get<1>(CommandsRef[I])->getValue(FilenameStorage),
-        nodeToCommandLine(Syntax, std::get<2>(CommandsRef[I])));
+        nodeToCommandLine(Syntax, std::get<2>(CommandsRef[I])),
+        Output ? Output->getValue(OutputStorage) : "");
   }
 }
 
@@ -289,6 +292,7 @@ bool JSONCompilationDatabase::parse(std::string &ErrorMessage) {
     llvm::yaml::ScalarNode *Directory = nullptr;
     llvm::Optional<std::vector<llvm::yaml::ScalarNode *>> Command;
     llvm::yaml::ScalarNode *File = nullptr;
+    llvm::yaml::ScalarNode *Output = nullptr;
     for (auto& NextKeyValue : *Object) {
       llvm::yaml::ScalarNode *KeyString =
           dyn_cast<llvm::yaml::ScalarNode>(NextKeyValue.getKey());
@@ -331,6 +335,8 @@ bool JSONCompilationDatabase::parse(std::string &ErrorMessage) {
           Command = std::vector<llvm::yaml::ScalarNode *>(1, ValueString);
       } else if (KeyValue == "file") {
         File = ValueString;
+      } else if (KeyValue == "output") {
+        Output = ValueString;
       } else {
         ErrorMessage = ("Unknown key: \"" +
                         KeyString->getRawValue() + "\"").str();
@@ -361,7 +367,7 @@ bool JSONCompilationDatabase::parse(std::string &ErrorMessage) {
     } else {
       llvm::sys::path::native(FileName, NativeFilePath);
     }
-    auto Cmd = CompileCommandRef(Directory, File, *Command);
+    auto Cmd = CompileCommandRef(Directory, File, *Command, Output);
     IndexByFile[NativeFilePath].push_back(Cmd);
     AllCommands.push_back(Cmd);
     MatchTrie.insert(NativeFilePath);

unittests/Tooling/CompilationDatabaseTest.cpp

@@ -44,6 +44,7 @@ TEST(JSONCompilationDatabase, ErrsOnInvalidFormat) {
   expectFailure("[{\"directory\":\"\",\"command\":[],\"file\":\"\"}]", "Command not string");
   expectFailure("[{\"directory\":\"\",\"arguments\":[[]],\"file\":\"\"}]",
                 "Arguments contain non-string");
+  expectFailure("[{\"output\":[]}]", "Expected strings as value.");
 }
 
 static std::vector<std::string> getAllFiles(StringRef JSONDatabase,
@@ -105,16 +106,19 @@ TEST(JSONCompilationDatabase, GetAllCompileCommands) {
   StringRef Directory1("//net/dir1");
   StringRef FileName1("file1");
   StringRef Command1("command1");
+  StringRef Output1("file1.o");
   StringRef Directory2("//net/dir2");
   StringRef FileName2("file2");
   StringRef Command2("command2");
+  StringRef Output2("");
 
   std::vector<CompileCommand> Commands = getAllCompileCommands(
       JSONCommandLineSyntax::Gnu,
       ("[{\"directory\":\"" + Directory1 + "\"," + "\"command\":\"" + Command1 +
        "\","
        "\"file\":\"" +
-       FileName1 + "\"},"
+       FileName1 + "\", \"output\":\"" +
+       Output1 + "\"},"
                    " {\"directory\":\"" +
        Directory2 + "\"," + "\"command\":\"" + Command2 + "\","
                                                           "\"file\":\"" +
@@ -124,10 +128,12 @@ TEST(JSONCompilationDatabase, GetAllCompileCommands) {
   EXPECT_EQ(2U, Commands.size()) << ErrorMessage;
   EXPECT_EQ(Directory1, Commands[0].Directory) << ErrorMessage;
   EXPECT_EQ(FileName1, Commands[0].Filename) << ErrorMessage;
+  EXPECT_EQ(Output1, Commands[0].Output) << ErrorMessage;
   ASSERT_EQ(1u, Commands[0].CommandLine.size());
   EXPECT_EQ(Command1, Commands[0].CommandLine[0]) << ErrorMessage;
   EXPECT_EQ(Directory2, Commands[1].Directory) << ErrorMessage;
   EXPECT_EQ(FileName2, Commands[1].Filename) << ErrorMessage;
+  EXPECT_EQ(Output2, Commands[1].Output) << ErrorMessage;
   ASSERT_EQ(1u, Commands[1].CommandLine.size());
   EXPECT_EQ(Command2, Commands[1].CommandLine[0]) << ErrorMessage;