diff --git a/clang/lib/Tooling/JSONCompilationDatabase.cpp b/clang/lib/Tooling/JSONCompilationDatabase.cpp index 76a82b0fd9bd..f19a0f7550b9 100644 --- a/clang/lib/Tooling/JSONCompilationDatabase.cpp +++ b/clang/lib/Tooling/JSONCompilationDatabase.cpp @@ -256,15 +256,57 @@ JSONCompilationDatabase::getAllCompileCommands() const { return Commands; } +static llvm::StringRef stripExecutableExtension(llvm::StringRef Name) { + Name.consume_back(".exe"); + return Name; +} + +// There are compiler-wrappers (ccache, distcc, gomacc) that take the "real" +// compiler as an argument, e.g. distcc gcc -O3 foo.c. +// These end up in compile_commands.json when people set CC="distcc gcc". +// Clang's driver doesn't understand this, so we need to unwrap. +static bool unwrapCommand(std::vector &Args) { + if (Args.size() < 2) + return false; + StringRef Wrapper = + stripExecutableExtension(llvm::sys::path::filename(Args.front())); + if (Wrapper == "distcc" || Wrapper == "gomacc" || Wrapper == "ccache") { + // Most of these wrappers support being invoked 3 ways: + // `distcc g++ file.c` This is the mode we're trying to match. + // We need to drop `distcc`. + // `distcc file.c` This acts like compiler is cc or similar. + // Clang's driver can handle this, no change needed. + // `g++ file.c` g++ is a symlink to distcc. + // We don't even notice this case, and all is well. + // + // We need to distinguish between the first and second case. + // The wrappers themselves don't take flags, so Args[1] is a compiler flag, + // an input file, or a compiler. Inputs have extensions, compilers don't. + bool HasCompiler = + (Args[1][0] != '-') && + !llvm::sys::path::has_extension(stripExecutableExtension(Args[1])); + if (HasCompiler) { + Args.erase(Args.begin()); + return true; + } + // If !HasCompiler, wrappers act like GCC. Fine: so do we. + } + return false; +} + static std::vector nodeToCommandLine(JSONCommandLineSyntax Syntax, const std::vector &Nodes) { SmallString<1024> Storage; - if (Nodes.size() == 1) - return unescapeCommandLine(Syntax, Nodes[0]->getValue(Storage)); std::vector Arguments; - for (const auto *Node : Nodes) - Arguments.push_back(Node->getValue(Storage)); + if (Nodes.size() == 1) + Arguments = unescapeCommandLine(Syntax, Nodes[0]->getValue(Storage)); + else + for (const auto *Node : Nodes) + Arguments.push_back(Node->getValue(Storage)); + // There may be multiple wrappers: using distcc and ccache together is common. + while (unwrapCommand(Arguments)) + ; return Arguments; } diff --git a/clang/unittests/Tooling/CompilationDatabaseTest.cpp b/clang/unittests/Tooling/CompilationDatabaseTest.cpp index da7ae09917df..fde95445bdab 100644 --- a/clang/unittests/Tooling/CompilationDatabaseTest.cpp +++ b/clang/unittests/Tooling/CompilationDatabaseTest.cpp @@ -370,6 +370,33 @@ TEST(findCompileArgsInJsonDatabase, FindsEntry) { EXPECT_EQ("command4", FoundCommand.CommandLine[0]) << ErrorMessage; } +TEST(findCompileArgsInJsonDatabase, ParsesCompilerWrappers) { + StringRef Directory("//net/dir"); + StringRef FileName("//net/dir/filename"); + std::vector> Cases = { + {"distcc gcc foo.c", "gcc foo.c"}, + {"gomacc clang++ foo.c", "clang++ foo.c"}, + {"ccache gcc foo.c", "gcc foo.c"}, + {"ccache.exe gcc foo.c", "gcc foo.c"}, + {"ccache g++.exe foo.c", "g++.exe foo.c"}, + {"ccache distcc gcc foo.c", "gcc foo.c"}, + + {"distcc foo.c", "distcc foo.c"}, + {"distcc -I/foo/bar foo.c", "distcc -I/foo/bar foo.c"}, + }; + std::string ErrorMessage; + + for (const auto &Case : Cases) { + std::string DB = + R"([{"directory":"//net/dir", "file":"//net/dir/foo.c", "command":")" + + Case.first + "\"}]"; + CompileCommand FoundCommand = + findCompileArgsInJsonDatabase("//net/dir/foo.c", DB, ErrorMessage); + EXPECT_EQ(Case.second, llvm::join(FoundCommand.CommandLine, " ")) + << Case.first; + } +} + static std::vector unescapeJsonCommandLine(StringRef Command) { std::string JsonDatabase = ("[{\"directory\":\"//net/root\", \"file\":\"test\", \"command\": \"" +