[flang][Frontend] Implement printing defined macros via -dM (llvm#87627)

This should work the same way as in clang.

Author: kparzysz

clang/docs/tools/clang-formatted-files.txt

@@ -2147,8 +2147,10 @@ flang/include/flang/Parser/message.h
 flang/include/flang/Parser/parse-state.h
 flang/include/flang/Parser/parse-tree-visitor.h
 flang/include/flang/Parser/parsing.h
+flang/include/flang/Parser/preprocessor.h
 flang/include/flang/Parser/provenance.h
 flang/include/flang/Parser/source.h
+flang/include/flang/Parser/token-sequence.h
 flang/include/flang/Parser/tools.h
 flang/include/flang/Parser/unparse.h
 flang/include/flang/Parser/user-state.h
@@ -2319,7 +2321,6 @@ flang/lib/Parser/openmp-parsers.cpp
 flang/lib/Parser/parse-tree.cpp
 flang/lib/Parser/parsing.cpp
 flang/lib/Parser/preprocessor.cpp
-flang/lib/Parser/preprocessor.h
 flang/lib/Parser/prescan.cpp
 flang/lib/Parser/prescan.h
 flang/lib/Parser/program-parsers.cpp
@@ -2328,7 +2329,6 @@ flang/lib/Parser/source.cpp
 flang/lib/Parser/stmt-parser.h
 flang/lib/Parser/token-parsers.h
 flang/lib/Parser/token-sequence.cpp
-flang/lib/Parser/token-sequence.h
 flang/lib/Parser/tools.cpp
 flang/lib/Parser/type-parser-implementation.h
 flang/lib/Parser/type-parsers.h

clang/include/clang/Driver/Options.td

@@ -1449,7 +1449,7 @@ def dD : Flag<["-"], "dD">, Group<d_Group>, Visibility<[ClangOption, CC1Option]>
 def dI : Flag<["-"], "dI">, Group<d_Group>, Visibility<[ClangOption, CC1Option]>,
   HelpText<"Print include directives in -E mode in addition to normal output">,
   MarshallingInfoFlag<PreprocessorOutputOpts<"ShowIncludeDirectives">>;
-def dM : Flag<["-"], "dM">, Group<d_Group>, Visibility<[ClangOption, CC1Option]>,
+def dM : Flag<["-"], "dM">, Group<d_Group>, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>,
   HelpText<"Print macro definitions in -E mode instead of normal output">;
 def dead__strip : Flag<["-"], "dead_strip">;
 def dependency_file : Separate<["-"], "dependency-file">,

clang/lib/Driver/ToolChains/Flang.cpp

@@ -679,7 +679,10 @@ void Flang::ConstructJob(Compilation &C, const JobAction &JA,
   CmdArgs.push_back(Args.MakeArgString(TripleStr));
 
   if (isa<PreprocessJobAction>(JA)) {
-      CmdArgs.push_back("-E");
+    CmdArgs.push_back("-E");
+    if (Args.getLastArg(options::OPT_dM)) {
+      CmdArgs.push_back("-dM");
+    }
   } else if (isa<CompileJobAction>(JA) || isa<BackendJobAction>(JA)) {
     if (JA.getType() == types::TY_Nothing) {
       CmdArgs.push_back("-fsyntax-only");

flang/include/flang/Frontend/PreprocessorOptions.h

@@ -56,6 +56,9 @@ struct PreprocessorOptions {
   // -fno-reformat: Emit cooked character stream as -E output
   bool noReformat{false};
 
+  // -dM: Show macro definitions with -dM -E
+  bool showMacros{false};
+
   void addMacroDef(llvm::StringRef name) {
     macros.emplace_back(std::string(name), false);
   }

flang/include/flang/Parser/parsing.h

@@ -15,6 +15,7 @@
 #include "parse-tree.h"
 #include "provenance.h"
 #include "flang/Common/Fortran-features.h"
+#include "flang/Parser/preprocessor.h"
 #include "llvm/Support/raw_ostream.h"
 #include <optional>
 #include <string>
@@ -59,6 +60,7 @@ class Parsing {
   const SourceFile *Prescan(const std::string &path, Options);
   void EmitPreprocessedSource(
       llvm::raw_ostream &, bool lineDirectives = true) const;
+  void EmitPreprocessorMacros(llvm::raw_ostream &) const;
   void DumpCookedChars(llvm::raw_ostream &) const;
   void DumpProvenance(llvm::raw_ostream &) const;
   void DumpParsingLog(llvm::raw_ostream &) const;
@@ -83,6 +85,7 @@ class Parsing {
   const char *finalRestingPlace_{nullptr};
   std::optional<Program> parseTree_;
   ParsingLog log_;
+  Preprocessor preprocessor_{allCooked_.allSources()};
 };
 } // namespace Fortran::parser
 #endif // FORTRAN_PARSER_PARSING_H_

flang/lib/Parser/preprocessor.h renamed to flang/include/flang/Parser/preprocessor.h

@@ -15,9 +15,10 @@
 // performed, so that special compiler command options &/or source file name
 // extensions for preprocessing will not be necessary.
 
-#include "token-sequence.h"
 #include "flang/Parser/char-block.h"
 #include "flang/Parser/provenance.h"
+#include "flang/Parser/token-sequence.h"
+#include "llvm/Support/raw_ostream.h"
 #include <cstddef>
 #include <list>
 #include <stack>
@@ -39,7 +40,7 @@ class Definition {
   Definition(const std::string &predefined, AllSources &);
 
   bool isFunctionLike() const { return isFunctionLike_; }
-  std::size_t argumentCount() const { return argumentCount_; }
+  std::size_t argumentCount() const { return argNames_.size(); }
   bool isVariadic() const { return isVariadic_; }
   bool isDisabled() const { return isDisabled_; }
   bool isPredefined() const { return isPredefined_; }
@@ -49,15 +50,21 @@ class Definition {
 
   TokenSequence Apply(const std::vector<TokenSequence> &args, Prescanner &);
 
+  void Print(llvm::raw_ostream &out, const char *macroName = "") const;
+
 private:
   static TokenSequence Tokenize(const std::vector<std::string> &argNames,
       const TokenSequence &token, std::size_t firstToken, std::size_t tokens);
+  // For a given token, return the index of the argument to which the token
+  // corresponds, or `argumentCount` if the token does not correspond to any
+  // argument.
+  std::size_t GetArgumentIndex(const CharBlock &token) const;
 
   bool isFunctionLike_{false};
-  std::size_t argumentCount_{0};
   bool isVariadic_{false};
   bool isDisabled_{false};
   bool isPredefined_{false};
+  std::vector<std::string> argNames_;
   TokenSequence replacement_;
 };
 
@@ -89,6 +96,8 @@ class Preprocessor {
   // Implements a preprocessor directive.
   void Directive(const TokenSequence &, Prescanner &);
 
+  void PrintMacros(llvm::raw_ostream &out) const;
+
 private:
   enum class IsElseActive { No, Yes };
   enum class CanDeadElseAppear { No, Yes };

flang/lib/Parser/token-sequence.h renamed to flang/include/flang/Parser/token-sequence.h

@@ -42,8 +42,8 @@ class TokenSequence {
   }
   TokenSequence(TokenSequence &&that)
       : start_{std::move(that.start_)}, nextStart_{that.nextStart_},
-        char_{std::move(that.char_)}, provenances_{
-                                          std::move(that.provenances_)} {}
+        char_{std::move(that.char_)},
+        provenances_{std::move(that.provenances_)} {}
   TokenSequence(const std::string &s, Provenance p) { Put(s, p); }
 
   TokenSequence &operator=(const TokenSequence &that) {

flang/lib/Frontend/CompilerInvocation.cpp

@@ -772,6 +772,7 @@ static void parsePreprocessorArgs(Fortran::frontend::PreprocessorOptions &opts,
 
   opts.noReformat = args.hasArg(clang::driver::options::OPT_fno_reformat);
   opts.noLineDirectives = args.hasArg(clang::driver::options::OPT_P);
+  opts.showMacros = args.hasArg(clang::driver::options::OPT_dM);
 }
 
 /// Parses all semantic related arguments and populates the variables

flang/lib/Frontend/FrontendActions.cpp

@@ -399,7 +399,9 @@ void PrintPreprocessedAction::executeAction() {
 
   // Format or dump the prescanner's output
   CompilerInstance &ci = this->getInstance();
-  if (ci.getInvocation().getPreprocessorOpts().noReformat) {
+  if (ci.getInvocation().getPreprocessorOpts().showMacros) {
+    ci.getParsing().EmitPreprocessorMacros(outForPP);
+  } else if (ci.getInvocation().getPreprocessorOpts().noReformat) {
     ci.getParsing().DumpCookedChars(outForPP);
   } else {
     ci.getParsing().EmitPreprocessedSource(

flang/lib/Parser/parsing.cpp

@@ -7,10 +7,10 @@
 //===----------------------------------------------------------------------===//
 
 #include "flang/Parser/parsing.h"
-#include "preprocessor.h"
 #include "prescan.h"
 #include "type-parsers.h"
 #include "flang/Parser/message.h"
+#include "flang/Parser/preprocessor.h"
 #include "flang/Parser/provenance.h"
 #include "flang/Parser/source.h"
 #include "llvm/Support/raw_ostream.h"
@@ -60,20 +60,19 @@ const SourceFile *Parsing::Prescan(const std::string &path, Options options) {
     }
   }
 
-  Preprocessor preprocessor{allSources};
   if (!options.predefinitions.empty()) {
-    preprocessor.DefineStandardMacros();
+    preprocessor_.DefineStandardMacros();
     for (const auto &predef : options.predefinitions) {
       if (predef.second) {
-        preprocessor.Define(predef.first, *predef.second);
+        preprocessor_.Define(predef.first, *predef.second);
       } else {
-        preprocessor.Undefine(predef.first);
+        preprocessor_.Undefine(predef.first);
       }
     }
   }
   currentCooked_ = &allCooked_.NewCookedSource();
   Prescanner prescanner{
-      messages_, *currentCooked_, preprocessor, options.features};
+      messages_, *currentCooked_, preprocessor_, options.features};
   prescanner.set_fixedForm(options.isFixedForm)
       .set_fixedFormColumnLimit(options.fixedFormColumns)
       .AddCompilerDirectiveSentinel("dir$");
@@ -87,7 +86,7 @@ const SourceFile *Parsing::Prescan(const std::string &path, Options options) {
   if (options.features.IsEnabled(LanguageFeature::CUDA)) {
     prescanner.AddCompilerDirectiveSentinel("$cuf");
     prescanner.AddCompilerDirectiveSentinel("@cuf");
-    preprocessor.Define("_CUDA", "1");
+    preprocessor_.Define("_CUDA", "1");
   }
   ProvenanceRange range{allSources.AddIncludedFile(
       *sourceFile, ProvenanceRange{}, options.isModuleFile)};
@@ -107,6 +106,10 @@ const SourceFile *Parsing::Prescan(const std::string &path, Options options) {
   return sourceFile;
 }
 
+void Parsing::EmitPreprocessorMacros(llvm::raw_ostream &out) const {
+  preprocessor_.PrintMacros(out);
+}
+
 void Parsing::EmitPreprocessedSource(
     llvm::raw_ostream &out, bool lineDirectives) const {
   const std::string *sourcePath{nullptr};

flang/lib/Parser/preprocessor.cpp

@@ -6,7 +6,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "preprocessor.h"
+#include "flang/Parser/preprocessor.h"
+
 #include "prescan.h"
 #include "flang/Common/idioms.h"
 #include "flang/Parser/characters.h"
@@ -21,6 +22,7 @@
 #include <optional>
 #include <set>
 #include <utility>
+#include <vector>
 
 namespace Fortran::parser {
 
@@ -31,8 +33,7 @@ Definition::Definition(
 Definition::Definition(const std::vector<std::string> &argNames,
     const TokenSequence &repl, std::size_t firstToken, std::size_t tokens,
     bool isVariadic)
-    : isFunctionLike_{true},
-      argumentCount_(argNames.size()), isVariadic_{isVariadic},
+    : isFunctionLike_{true}, isVariadic_{isVariadic}, argNames_{argNames},
       replacement_{Tokenize(argNames, repl, firstToken, tokens)} {}
 
 Definition::Definition(const std::string &predefined, AllSources &sources)
@@ -46,6 +47,37 @@ bool Definition::set_isDisabled(bool disable) {
   return was;
 }
 
+void Definition::Print(llvm::raw_ostream &out, const char *macroName) const {
+  if (!isFunctionLike_) {
+    // If it's not a function-like macro, then just print the replacement.
+    out << ' ' << replacement_.ToString();
+    return;
+  }
+
+  size_t argCount{argumentCount()};
+
+  out << '(';
+  for (size_t i{0}; i != argCount; ++i) {
+    if (i != 0) {
+      out << ", ";
+    }
+    out << argNames_[i];
+  }
+  if (isVariadic_) {
+    out << ", ...";
+  }
+  out << ") ";
+
+  for (size_t i{0}, e{replacement_.SizeInTokens()}; i != e; ++i) {
+    std::string tok{replacement_.TokenAt(i).ToString()};
+    if (size_t idx{GetArgumentIndex(tok)}; idx < argCount) {
+      out << argNames_[idx];
+    } else {
+      out << tok;
+    }
+  }
+}
+
 static bool IsLegalIdentifierStart(const CharBlock &cpl) {
   return cpl.size() > 0 && IsLegalIdentifierStart(cpl[0]);
 }
@@ -73,6 +105,13 @@ TokenSequence Definition::Tokenize(const std::vector<std::string> &argNames,
   return result;
 }
 
+std::size_t Definition::GetArgumentIndex(const CharBlock &token) const {
+  if (token.size() >= 2 && token[0] == '~') {
+    return static_cast<size_t>(token[1] - 'A');
+  }
+  return argumentCount();
+}
+
 static TokenSequence Stringify(
     const TokenSequence &tokens, AllSources &allSources) {
   TokenSequence result;
@@ -159,7 +198,7 @@ TokenSequence Definition::Apply(
       continue;
     }
     if (bytes == 2 && token[0] == '~') { // argument substitution
-      std::size_t index = token[1] - 'A';
+      std::size_t index{GetArgumentIndex(token)};
       if (index >= args.size()) {
         continue;
       }
@@ -202,8 +241,8 @@ TokenSequence Definition::Apply(
       Provenance commaProvenance{
           prescanner.preprocessor().allSources().CompilerInsertionProvenance(
               ',')};
-      for (std::size_t k{argumentCount_}; k < args.size(); ++k) {
-        if (k > argumentCount_) {
+      for (std::size_t k{argumentCount()}; k < args.size(); ++k) {
+        if (k > argumentCount()) {
           result.Put(","s, commaProvenance);
         }
         result.Put(args[k]);
@@ -212,7 +251,7 @@ TokenSequence Definition::Apply(
         j + 2 < tokens && replacement_.TokenAt(j + 1).OnlyNonBlank() == '(' &&
         parenthesesNesting == 0) {
       parenthesesNesting = 1;
-      skipping = args.size() == argumentCount_;
+      skipping = args.size() == argumentCount();
       ++j;
     } else {
       if (parenthesesNesting > 0) {
@@ -713,6 +752,21 @@ void Preprocessor::Directive(const TokenSequence &dir, Prescanner &prescanner) {
   }
 }
 
+void Preprocessor::PrintMacros(llvm::raw_ostream &out) const {
+  // std::set is ordered. Use that to print the macros in an
+  // alphabetical order.
+  std::set<std::string> macroNames;
+  for (const auto &[name, _] : definitions_) {
+    macroNames.insert(name.ToString());
+  }
+
+  for (const std::string &name : macroNames) {
+    out << "#define " << name;
+    definitions_.at(name).Print(out, name.c_str());
+    out << '\n';
+  }
+}
+
 CharBlock Preprocessor::SaveTokenAsName(const CharBlock &t) {
   names_.push_back(t.ToString());
   return {names_.back().data(), names_.back().size()};

flang/lib/Parser/prescan.cpp

@@ -7,12 +7,12 @@
 //===----------------------------------------------------------------------===//
 
 #include "prescan.h"
-#include "preprocessor.h"
-#include "token-sequence.h"
 #include "flang/Common/idioms.h"
 #include "flang/Parser/characters.h"
 #include "flang/Parser/message.h"
+#include "flang/Parser/preprocessor.h"
 #include "flang/Parser/source.h"
+#include "flang/Parser/token-sequence.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cstddef>
 #include <cstring>

flang/lib/Parser/prescan.h

@@ -16,11 +16,11 @@
 // fixed form character literals on truncated card images, file
 // inclusion, and driving the Fortran source preprocessor.
 
-#include "token-sequence.h"
 #include "flang/Common/Fortran-features.h"
 #include "flang/Parser/characters.h"
 #include "flang/Parser/message.h"
 #include "flang/Parser/provenance.h"
+#include "flang/Parser/token-sequence.h"
 #include <bitset>
 #include <optional>
 #include <string>

flang/lib/Parser/token-sequence.cpp

@@ -6,7 +6,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "token-sequence.h"
+#include "flang/Parser/token-sequence.h"
+
 #include "prescan.h"
 #include "flang/Parser/characters.h"
 #include "flang/Parser/message.h"

flang/test/Driver/driver-help-hidden.f90

@@ -21,6 +21,7 @@
 ! CHECK-NEXT: -ccc-print-phases       Dump list of actions to perform
 ! CHECK-NEXT: -cpp                    Enable predefined and command line preprocessor macros
 ! CHECK-NEXT: -c                      Only run preprocess, compile, and assemble steps
+! CHECK-NEXT: -dM                     Print macro definitions in -E mode instead of normal output
 ! CHECK-NEXT: -dumpmachine            Display the compiler's target processor
 ! CHECK-NEXT: -dumpversion            Display the version of the compiler
 ! CHECK-NEXT: -D <macro>=<value>      Define <macro> to <value> (or 1 if <value> omitted)