Emit warning if define or undef reserved identifier or keyword.

Summary:
This change implements warnings if macro name is identical to a keyword or
reserved identifier. The warnings are different depending on the "danger"
of the operation. Defining macro that replaces a keyword is on by default.
Other cases produce warning that is off by default but can be turned on
using option -Wreserved-id-macro.

This change fixes PR11488.

Reviewers: rnk

Reviewed By: rnk

Subscribers: rnk, cfe-commits

Differential Revision: http://reviews.llvm.org/D6194

llvm-svn: 223114

diff --git a/clang/include/clang/Basic/DiagnosticGroups.td b/clang/include/clang/Basic/DiagnosticGroups.td
index af0b948..34609b2 100644 (file)
--- a/clang/include/clang/Basic/DiagnosticGroups.td
+++ b/clang/include/clang/Basic/DiagnosticGroups.td
@@ -337,6 +337,8 @@ def : DiagGroup<"sequence-point", [Unsequenced]>;
 
 // Preprocessor warnings.
 def AmbiguousMacro : DiagGroup<"ambiguous-macro">;
+def KeywordAsMacro : DiagGroup<"keyword-macro">;
+def ReservedIdAsMacro : DiagGroup<"reserved-id-macro">;
 
 // Just silence warnings about -Wstrict-aliasing for now.
 def : DiagGroup<"strict-aliasing=0">;

diff --git a/clang/include/clang/Basic/DiagnosticLexKinds.td b/clang/include/clang/Basic/DiagnosticLexKinds.td
index 2fcfa02..5eb9e65 100644 (file)
--- a/clang/include/clang/Basic/DiagnosticLexKinds.td
+++ b/clang/include/clang/Basic/DiagnosticLexKinds.td
@@ -290,6 +290,14 @@ def note_pp_ambiguous_macro_chosen : Note<
   "expanding this definition of %0">;
 def note_pp_ambiguous_macro_other : Note<
   "other definition of %0">;
+def warn_pp_macro_hides_keyword : Warning<
+  "keyword or reserved identifier is hidden by macro definition">,
+  InGroup<KeywordAsMacro>;
+def warn_pp_macro_is_reserved_id : Warning<
+  "macro name is a keyword or reserved identifier">, InGroup<KeywordAsMacro>;
+def warn_pp_defundef_reserved_ident : Warning<
+  "reserved identifier is used as macro name">, DefaultIgnore,
+  InGroup<ReservedIdAsMacro>;
 
 def pp_invalid_string_literal : Warning<
   "invalid string literal, ignoring final '\\'">;

diff --git a/clang/include/clang/Basic/IdentifierTable.h b/clang/include/clang/Basic/IdentifierTable.h
index ed92339..1de9dd1 100644 (file)
--- a/clang/include/clang/Basic/IdentifierTable.h
+++ b/clang/include/clang/Basic/IdentifierTable.h
@@ -249,6 +249,9 @@ public:
   }
   bool isCPlusPlusOperatorKeyword() const { return IsCPPOperatorKeyword; }
 
+  /// \brief Return true if this token is a keyword in the specified language.
+  bool isKeyword(const LangOptions &LangOpts);
+
   /// getFETokenInfo/setFETokenInfo - The language front-end is allowed to
   /// associate arbitrary metadata with this token.
   template<typename T>

diff --git a/clang/lib/Basic/IdentifierTable.cpp b/clang/lib/Basic/IdentifierTable.cpp
index dd09704..613b43f 100644 (file)
--- a/clang/lib/Basic/IdentifierTable.cpp
+++ b/clang/lib/Basic/IdentifierTable.cpp
@@ -122,7 +122,7 @@ namespace {
 
 /// \brief Translates flags as specified in TokenKinds.def into keyword status
 /// in the given language standard.
-static KeywordStatus GetKeywordStatus(const LangOptions &LangOpts,
+static KeywordStatus getKeywordStatus(const LangOptions &LangOpts,
                                       unsigned Flags) {
   if (Flags == KEYALL) return KS_Enabled;
   if (LangOpts.CPlusPlus && (Flags & KEYCXX)) return KS_Enabled;
@@ -151,7 +151,7 @@ static KeywordStatus GetKeywordStatus(const LangOptions &LangOpts,
 static void AddKeyword(StringRef Keyword,
                        tok::TokenKind TokenCode, unsigned Flags,
                        const LangOptions &LangOpts, IdentifierTable &Table) {
-  KeywordStatus AddResult = GetKeywordStatus(LangOpts, Flags);
+  KeywordStatus AddResult = getKeywordStatus(LangOpts, Flags);
 
   // Don't add this keyword under MSVCCompat.
   if (LangOpts.MSVCCompat && (Flags & KEYNOMS))
@@ -209,6 +209,31 @@ void IdentifierTable::AddKeywords(const LangOptions &LangOpts) {
                LangOpts, *this);
 }
 
+/// \brief Checks if the specified token kind represents a keyword in the
+/// specified language.
+/// \returns Status of the keyword in the language.
+static KeywordStatus getTokenKwStatus(const LangOptions &LangOpts,
+                                      tok::TokenKind K) {
+  switch (K) {
+#define KEYWORD(NAME, FLAGS) \
+  case tok::kw_##NAME: return getKeywordStatus(LangOpts, FLAGS);
+#include "clang/Basic/TokenKinds.def"
+  default: return KS_Disabled;
+  }
+}
+
+/// \brief Returns true if the identifier represents a keyword in the
+/// specified language.
+bool IdentifierInfo::isKeyword(const LangOptions &LangOpts) {
+  switch (getTokenKwStatus(LangOpts, getTokenID())) {
+  case KS_Enabled:
+  case KS_Extension:
+    return true;
+  default:
+    return false;
+  }
+}
+
 tok::PPKeywordKind IdentifierInfo::getPPKeywordID() const {
   // We use a perfect hash function here involving the length of the keyword,
   // the first and third character.  For preprocessor ID's there are no

diff --git a/clang/lib/Lex/PPDirectives.cpp b/clang/lib/Lex/PPDirectives.cpp
index 0a46663..16b86b7 100644 (file)
--- a/clang/lib/Lex/PPDirectives.cpp
+++ b/clang/lib/Lex/PPDirectives.cpp
@@ -100,6 +100,58 @@ void Preprocessor::DiscardUntilEndOfDirective() {
   } while (Tmp.isNot(tok::eod));
 }
 
+/// \brief Enumerates possible cases of #define/#undef a reserved identifier.
+enum MacroDiag {
+  MD_NoWarn,        //> Not a reserved identifier
+  MD_KeywordDef,    //> Macro hides keyword, enabled by default
+  MD_KeywordUndef,  //> #undef keyword, enabled by default
+  MD_WarnStrict     //> Other reserved id, disabled by default
+};
+
+/// \brief Checks if the specified identifier is reserved in the specified
+/// language.
+/// This function does not check if the identifier is a keyword.
+static bool isReservedId(StringRef Text, const LangOptions &Lang) {
+  // C++ [macro.names], C11 7.1.3:
+  // All identifiers that begin with an underscore and either an uppercase
+  // letter or another underscore are always reserved for any use.
+  if (Text.size() >= 2 && Text[0] == '_' &&
+      (isUppercase(Text[1]) || Text[1] == '_'))
+    return true;
+  // C++ [global.names]
+  // Each name that contains a double underscore ... is reserved to the
+  // implementation for any use.
+  if (Lang.CPlusPlus) {
+    if (Text.find("__") != StringRef::npos)
+      return true;
+  }
+  return false;
+}
+
+static MacroDiag shouldWarnOnMacroDef(Preprocessor &PP, IdentifierInfo *II) {
+  const LangOptions &Lang = PP.getLangOpts();
+  StringRef Text = II->getName();
+  if (isReservedId(Text, Lang))
+    return MD_WarnStrict;
+  if (II->isKeyword(Lang))
+    return MD_KeywordDef;
+  if (Lang.CPlusPlus && (Text.equals("override") || Text.equals("final")))
+    return MD_KeywordDef;
+  return MD_NoWarn;
+}
+
+static MacroDiag shouldWarnOnMacroUndef(Preprocessor &PP, IdentifierInfo *II) {
+  const LangOptions &Lang = PP.getLangOpts();
+  if (II->isKeyword(Lang))
+    return MD_KeywordUndef;
+  StringRef Text = II->getName();
+  if (Lang.CPlusPlus && (Text.equals("override") || Text.equals("final")))
+    return MD_KeywordUndef;
+  if (isReservedId(Text, Lang))
+    return MD_WarnStrict;
+  return MD_NoWarn;
+}
+
 bool Preprocessor::CheckMacroName(Token &MacroNameTok, MacroUse isDefineUndef) {
   // Missing macro name?
   if (MacroNameTok.is(tok::eod))
@@ -140,6 +192,23 @@ bool Preprocessor::CheckMacroName(Token &MacroNameTok, MacroUse isDefineUndef) {
     Diag(MacroNameTok, diag::ext_pp_undef_builtin_macro);
   }
 
+  // Warn if defining/undefining reserved identifier including keywords.
+  SourceLocation MacroNameLoc = MacroNameTok.getLocation();
+  if (!SourceMgr.isInSystemHeader(MacroNameLoc) &&
+      (strcmp(SourceMgr.getBufferName(MacroNameLoc), "<built-in>") != 0)) {
+    MacroDiag D = MD_NoWarn;
+    if (isDefineUndef == MU_Define)
+      D = shouldWarnOnMacroDef(*this, II);
+    else if (isDefineUndef == MU_Undef)
+      D = shouldWarnOnMacroUndef(*this, II);
+    if (D == MD_KeywordDef)
+      Diag(MacroNameTok, diag::warn_pp_macro_hides_keyword);
+    if (D == MD_KeywordUndef)
+      Diag(MacroNameTok, diag::warn_pp_macro_is_reserved_id);
+    else if (D == MD_WarnStrict)
+      Diag(MacroNameTok, diag::warn_pp_defundef_reserved_ident);
+  }
+
   // Okay, we got a good identifier.
   return false;
 }

diff --git a/clang/test/PCH/single-token-macro.c b/clang/test/PCH/single-token-macro.c
index aa02f65..b077aba 100644 (file)
--- a/clang/test/PCH/single-token-macro.c
+++ b/clang/test/PCH/single-token-macro.c
@@ -12,6 +12,8 @@
 #ifndef HEADER
 #define HEADER
 
+#pragma clang diagnostic ignored "-Wreserved-id-macro"
+
 #ifdef __stdcall
 // __stdcall is defined as __attribute__((__stdcall__)) for targeting mingw32.
 #undef __stdcall

diff --git a/clang/test/Preprocessor/cxx_oper_keyword_ms_compat.cpp b/clang/test/Preprocessor/cxx_oper_keyword_ms_compat.cpp
index 8e1351e..24a3898 100644 (file)
--- a/clang/test/Preprocessor/cxx_oper_keyword_ms_compat.cpp
+++ b/clang/test/Preprocessor/cxx_oper_keyword_ms_compat.cpp
@@ -1,6 +1,8 @@
 // RUN: %clang_cc1 %s -E -verify -fms-extensions
 // expected-no-diagnostics
 
+#pragma clang diagnostic ignored "-Wkeyword-macro"
+
 bool f() {
   // Check that operators still work before redefining them.
 #if compl 0 bitand 1

diff --git a/clang/test/Sema/thread-specifier.c b/clang/test/Sema/thread-specifier.c
index 3968ae1..71e44c3 100644 (file)
--- a/clang/test/Sema/thread-specifier.c
+++ b/clang/test/Sema/thread-specifier.c
@@ -5,6 +5,8 @@
 // RUN: %clang_cc1 -triple i686-pc-linux-gnu -fsyntax-only -Wno-private-extern -verify -pedantic -x c++ %s -DCXX11 -D__thread=thread_local -std=c++11 -Wno-deprecated
 // RUN: %clang_cc1 -triple i686-pc-linux-gnu -fsyntax-only -Wno-private-extern -verify -pedantic -x c++ %s -DC11 -D__thread=_Thread_local -std=c++11 -Wno-deprecated
 
+#pragma clang diagnostic ignored "-Wkeyword-macro"
+
 #ifdef __cplusplus
 // In C++, we define __private_extern__ to extern.
 #undef __private_extern__