From: Olivier Goffart Date: Fri, 14 Jul 2017 09:23:40 +0000 (+0000) Subject: Keep the IdentifierInfo in the Token for alternative operator keyword X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=baa150782312a70256b17d5383d7a5cd6c8dec32;p=clang Keep the IdentifierInfo in the Token for alternative operator keyword The goal of this commit is to fix clang-format so it does not merge tokens when using the alternative spelling keywords. (eg: "not foo" should not become "notfoo") The problem is that Preprocessor::HandleIdentifier used to drop the identifier info from the token for these keyword. This means the first condition of TokenAnnotator::spaceRequiredBefore is not met. We could add explicit check for the spelling in that condition, but I think it is better to keep the IdentifierInfo and handle the operator keyword explicitly when needed. That actually leads to simpler code, and probably slightly more efficient as well. Another side effect of this change is that __identifier(and) will now work as one would expect, removing a FIXME from the MicrosoftExtensions.cpp test Differential Revision: https://reviews.llvm.org/D35172 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@308008 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/include/clang/Basic/IdentifierTable.h b/include/clang/Basic/IdentifierTable.h index 9b1ba4a98e..f94b2c9b2f 100644 --- a/include/clang/Basic/IdentifierTable.h +++ b/include/clang/Basic/IdentifierTable.h @@ -272,10 +272,6 @@ public: /// this identifier is a C++ alternate representation of an operator. void setIsCPlusPlusOperatorKeyword(bool Val = true) { IsCPPOperatorKeyword = Val; - if (Val) - NeedsHandleIdentifier = true; - else - RecomputeNeedsHandleIdentifier(); } bool isCPlusPlusOperatorKeyword() const { return IsCPPOperatorKeyword; } @@ -381,10 +377,9 @@ private: /// This method is very tied to the definition of HandleIdentifier. Any /// change to it should be reflected here. void RecomputeNeedsHandleIdentifier() { - NeedsHandleIdentifier = - (isPoisoned() | hasMacroDefinition() | isCPlusPlusOperatorKeyword() | - isExtensionToken() | isFutureCompatKeyword() || isOutOfDate() || - isModulesImport()); + NeedsHandleIdentifier = isPoisoned() || hasMacroDefinition() || + isExtensionToken() || isFutureCompatKeyword() || + isOutOfDate() || isModulesImport(); } }; diff --git a/lib/Lex/PPDirectives.cpp b/lib/Lex/PPDirectives.cpp index 8c79e50176..4440cf2094 100644 --- a/lib/Lex/PPDirectives.cpp +++ b/lib/Lex/PPDirectives.cpp @@ -220,26 +220,18 @@ bool Preprocessor::CheckMacroName(Token &MacroNameTok, MacroUse isDefineUndef, return Diag(MacroNameTok, diag::err_pp_missing_macro_name); IdentifierInfo *II = MacroNameTok.getIdentifierInfo(); - if (!II) { - bool Invalid = false; - std::string Spelling = getSpelling(MacroNameTok, &Invalid); - if (Invalid) - return Diag(MacroNameTok, diag::err_pp_macro_not_identifier); - II = getIdentifierInfo(Spelling); - - if (!II->isCPlusPlusOperatorKeyword()) - return Diag(MacroNameTok, diag::err_pp_macro_not_identifier); + if (!II) + return Diag(MacroNameTok, diag::err_pp_macro_not_identifier); + if (II->isCPlusPlusOperatorKeyword()) { // C++ 2.5p2: Alternative tokens behave the same as its primary token // except for their spellings. Diag(MacroNameTok, getLangOpts().MicrosoftExt ? diag::ext_pp_operator_used_as_macro_name : diag::err_pp_operator_used_as_macro_name) << II << MacroNameTok.getKind(); - // Allow #defining |and| and friends for Microsoft compatibility or // recovery when legacy C headers are included in C++. - MacroNameTok.setIdentifierInfo(II); } if ((isDefineUndef != MU_Other) && II->getPPKeywordID() == tok::pp_defined) { diff --git a/lib/Lex/PPExpressions.cpp b/lib/Lex/PPExpressions.cpp index 12f5084298..d8431827e9 100644 --- a/lib/Lex/PPExpressions.cpp +++ b/lib/Lex/PPExpressions.cpp @@ -237,35 +237,32 @@ static bool EvaluateValue(PPValue &Result, Token &PeekTok, DefinedTracker &DT, PP.setCodeCompletionReached(); PP.LexNonComment(PeekTok); } - - // If this token's spelling is a pp-identifier, check to see if it is - // 'defined' or if it is a macro. Note that we check here because many - // keywords are pp-identifiers, so we can't check the kind. - if (IdentifierInfo *II = PeekTok.getIdentifierInfo()) { - // Handle "defined X" and "defined(X)". - if (II->isStr("defined")) - return EvaluateDefined(Result, PeekTok, DT, ValueLive, PP); - - // If this identifier isn't 'defined' or one of the special - // preprocessor keywords and it wasn't macro expanded, it turns - // into a simple 0, unless it is the C++ keyword "true", in which case it - // turns into "1". - if (ValueLive && - II->getTokenID() != tok::kw_true && - II->getTokenID() != tok::kw_false) - PP.Diag(PeekTok, diag::warn_pp_undef_identifier) << II; - Result.Val = II->getTokenID() == tok::kw_true; - Result.Val.setIsUnsigned(false); // "0" is signed intmax_t 0. - Result.setIdentifier(II); - Result.setRange(PeekTok.getLocation()); - DT.IncludedUndefinedIds = (II->getTokenID() != tok::kw_true && - II->getTokenID() != tok::kw_false); - PP.LexNonComment(PeekTok); - return false; - } switch (PeekTok.getKind()) { - default: // Non-value token. + default: + // If this token's spelling is a pp-identifier, check to see if it is + // 'defined' or if it is a macro. Note that we check here because many + // keywords are pp-identifiers, so we can't check the kind. + if (IdentifierInfo *II = PeekTok.getIdentifierInfo()) { + // Handle "defined X" and "defined(X)". + if (II->isStr("defined")) + return EvaluateDefined(Result, PeekTok, DT, ValueLive, PP); + + if (!II->isCPlusPlusOperatorKeyword()) { + // If this identifier isn't 'defined' or one of the special + // preprocessor keywords and it wasn't macro expanded, it turns + // into a simple 0 + if (ValueLive) + PP.Diag(PeekTok, diag::warn_pp_undef_identifier) << II; + Result.Val = 0; + Result.Val.setIsUnsigned(false); // "0" is signed intmax_t 0. + Result.setIdentifier(II); + Result.setRange(PeekTok.getLocation()); + DT.IncludedUndefinedIds = true; + PP.LexNonComment(PeekTok); + return false; + } + } PP.Diag(PeekTok, diag::err_pp_expr_bad_token_start_expr); return true; case tok::eod: @@ -481,6 +478,14 @@ static bool EvaluateValue(PPValue &Result, Token &PeekTok, DefinedTracker &DT, DT.State = DefinedTracker::DefinedMacro; return false; } + case tok::kw_true: + case tok::kw_false: + Result.Val = PeekTok.getKind() == tok::kw_true; + Result.Val.setIsUnsigned(false); // "0" is signed intmax_t 0. + Result.setIdentifier(PeekTok.getIdentifierInfo()); + Result.setRange(PeekTok.getLocation()); + PP.LexNonComment(PeekTok); + return false; // FIXME: Handle #assert } diff --git a/lib/Lex/Preprocessor.cpp b/lib/Lex/Preprocessor.cpp index 63f39524d1..d1dc8e1c00 100644 --- a/lib/Lex/Preprocessor.cpp +++ b/lib/Lex/Preprocessor.cpp @@ -712,14 +712,6 @@ bool Preprocessor::HandleIdentifier(Token &Identifier) { II.setIsFutureCompatKeyword(false); } - // C++ 2.11p2: If this is an alternative representation of a C++ operator, - // then we act as if it is the actual operator and not the textual - // representation of it. - if (II.isCPlusPlusOperatorKeyword() && - !(getLangOpts().MSVCCompat && - getSourceManager().isInSystemHeader(Identifier.getLocation()))) - Identifier.setIdentifierInfo(nullptr); - // If this is an extension token, diagnose its use. // We avoid diagnosing tokens that originate from macro definitions. // FIXME: This warning is disabled in cases where it shouldn't be, diff --git a/test/Parser/MicrosoftExtensions.cpp b/test/Parser/MicrosoftExtensions.cpp index 74f4bb3268..c796eded1f 100644 --- a/test/Parser/MicrosoftExtensions.cpp +++ b/test/Parser/MicrosoftExtensions.cpp @@ -261,9 +261,7 @@ int __identifier(else} = __identifier(for); // expected-error {{missing ')' afte #define identifier_weird(x) __identifier(x int k = identifier_weird(if)); // expected-error {{use of undeclared identifier 'if'}} -// This is a bit weird, but the alternative tokens aren't keywords, and this -// behavior matches MSVC. FIXME: Consider supporting this anyway. -extern int __identifier(and) r; // expected-error {{cannot convert '&&' token to an identifier}} +extern int __identifier(and); void f() { __identifier(() // expected-error {{cannot convert '(' token to an identifier}} diff --git a/test/Preprocessor/cxx_oper_keyword.cpp b/test/Preprocessor/cxx_oper_keyword.cpp index 89a094d073..a66e890497 100644 --- a/test/Preprocessor/cxx_oper_keyword.cpp +++ b/test/Preprocessor/cxx_oper_keyword.cpp @@ -29,3 +29,15 @@ #ifdef and #warning and is defined #endif + +#ifdef OPERATOR_NAMES +//expected-error@+2 {{invalid token at start of a preprocessor expression}} +#endif +#if or +#endif + +#ifdef OPERATOR_NAMES +//expected-error@+2 {{invalid token at start of a preprocessor expression}} +#endif +#if and_eq +#endif diff --git a/unittests/Format/FormatTest.cpp b/unittests/Format/FormatTest.cpp index 937362f5c9..eb7bcc1ed8 100644 --- a/unittests/Format/FormatTest.cpp +++ b/unittests/Format/FormatTest.cpp @@ -333,6 +333,16 @@ TEST_F(FormatTest, RecognizesBinaryOperatorKeywords) { verifyFormat("x = (a) xor (b);"); } +TEST_F(FormatTest, RecognizesUnaryOperatorKeywords) { + verifyFormat("x = compl(a);"); + verifyFormat("x = not(a);"); + verifyFormat("x = bitand(a);"); + // Unary operator must not be merged with the next identifier + verifyFormat("x = compl a;"); + verifyFormat("x = not a;"); + verifyFormat("x = bitand a;"); +} + //===----------------------------------------------------------------------===// // Tests for control statements. //===----------------------------------------------------------------------===//