[llvm-cxxfilt] Add --quote option to quote demangled function names (#111871)

This is useful when looking at LLVM/MLIR assembly produced from C++
sources. For example
 cir.call @_ZN3aie4tileILi1ELi4EE7programIZ4mainE3$_0EEvOT_(%2, %7) :
will be translated to
cir.call @"void aie::tile<1, 4>::program<main::$_0>(main::$_0&&)"(%2,
%7) : which can be parsed as valid MLIR by the right mlir-lsp-server.

If a symbol is already quoted, do not quote it more.

---------

Co-authored-by: James Henderson <[email protected]>

Author: keryell

llvm/docs/CommandGuide/llvm-cxxfilt.rst

@@ -57,6 +57,11 @@ OPTIONS
   Do not strip a leading underscore. This is the default for all platforms
   except Mach-O based hosts.
 
+.. option:: --quote
+
+  Add `"` `"` around demangled function symbols. Do not quote already quoted
+  symbols.
+
 .. option:: --strip-underscore, -_
 
   Strip a single leading underscore, if present, from each input name before

llvm/test/tools/llvm-cxxfilt/quote.test

@@ -0,0 +1,26 @@
+// Show that llvm-cxxfilt --quote adds quotes around demangled symbols, unless
+// the symbol is already quoted.
+
+RUN: split-file %s %t
+
+RUN: llvm-cxxfilt --quote < %t/symbols-in-file.test | FileCheck --match-full-lines --check-prefix=CHECK-FILE %s
+CHECK-FILE: "bar()" "bar()"
+CHECK-FILE-NEXT: "bar()" "bar()"
+CHECK-FILE: log()
+CHECK-FILE: "import thunk for std::future<void>"
+
+// Check it works with CLI symbols too. Since a quoted mangled name is not a
+// mangled name, it should be unchanged.
+RUN: llvm-cxxfilt --quote _Z3firv '"_Z3barv"' 'saw()' | FileCheck --match-full-lines --check-prefix=CHECK-CLI %s
+CHECK-CLI: "fir()"
+CHECK-CLI-NEXT: "_Z3barv"
+CHECK-CLI-NEXT: saw()
+
+//--- symbols-in-file.test
+_Z3barv "_Z3barv"
+"_Z3barv" _Z3barv
+// This is not mangled, thus it should not be quoted.
+log()
+// Check that an "import thunk for" prefix can be quoted along the demangled
+// name.
+__imp__ZSt6futureIvE

llvm/tools/llvm-cxxfilt/Opts.td

@@ -15,6 +15,7 @@ multiclass Eq<string name, string help> {
 }
 
 def help : FF<"help", "Display this help">;
+def quote : FF<"quote", "Quote demangled function names with \" \" if not already quoted">;
 defm strip_underscore : BB<"strip-underscore", "Strip the leading underscore", "Don't strip the leading underscore">;
 def types : FF<"types", "Attempt to demangle types as well as function names">;
 def no_params : FF<"no-params", "Skip function parameters and return types">;

llvm/tools/llvm-cxxfilt/llvm-cxxfilt.cpp

@@ -54,6 +54,7 @@ class CxxfiltOptTable : public opt::GenericOptTable {
 } // namespace
 
 static bool ParseParams;
+static bool Quote;
 static bool StripUnderscore;
 static bool Types;
 
@@ -64,7 +65,15 @@ static void error(const Twine &Message) {
   exit(1);
 }
 
-static std::string demangle(const std::string &Mangled) {
+// Quote Undecorated with "" if asked for and not already followed by a '"'.
+static std::string optionalQuote(const std::string &Undecorated,
+                                 StringRef Delimiters) {
+  if (Quote && (Delimiters.empty() || Delimiters[0] != '"'))
+    return '"' + Undecorated + '"';
+  return Undecorated;
+}
+
+static std::string demangle(const std::string &Mangled, StringRef Delimiters) {
   using llvm::itanium_demangle::starts_with;
   std::string_view DecoratedStr = Mangled;
   bool CanHaveLeadingDot = true;
@@ -76,7 +85,7 @@ static std::string demangle(const std::string &Mangled) {
   std::string Result;
   if (nonMicrosoftDemangle(DecoratedStr, Result, CanHaveLeadingDot,
                            ParseParams))
-    return Result;
+    return optionalQuote(Result, Delimiters);
 
   std::string Prefix;
   char *Undecorated = nullptr;
@@ -89,7 +98,8 @@ static std::string demangle(const std::string &Mangled) {
     Undecorated = itaniumDemangle(DecoratedStr.substr(6), ParseParams);
   }
 
-  Result = Undecorated ? Prefix + Undecorated : Mangled;
+  Result =
+      Undecorated ? optionalQuote(Prefix + Undecorated, Delimiters) : Mangled;
   free(Undecorated);
   return Result;
 }
@@ -137,9 +147,10 @@ static void demangleLine(llvm::raw_ostream &OS, StringRef Mangled, bool Split) {
     SmallVector<std::pair<StringRef, StringRef>, 16> Words;
     SplitStringDelims(Mangled, Words, IsLegalItaniumChar);
     for (const auto &Word : Words)
-      Result += ::demangle(std::string(Word.first)) + Word.second.str();
+      Result +=
+          ::demangle(std::string(Word.first), Word.second) + Word.second.str();
   } else
-    Result = ::demangle(std::string(Mangled));
+    Result = ::demangle(std::string(Mangled), "");
   OS << Result << '\n';
   OS.flush();
 }
@@ -170,6 +181,8 @@ int llvm_cxxfilt_main(int argc, char **argv, const llvm::ToolContext &) {
 
   ParseParams = !Args.hasArg(OPT_no_params);
 
+  Quote = Args.hasArg(OPT_quote);
+
   Types = Args.hasArg(OPT_types);
 
   std::vector<std::string> Decorated = Args.getAllArgValues(OPT_INPUT);