https://github.com/abhina-sree updated https://github.com/llvm/llvm-project/pull/169803
>From 62b2ec561f96375bcd1ddb6c97734523588f37ac Mon Sep 17 00:00:00 2001 From: Abhina Sreeskantharajan <[email protected]> Date: Fri, 8 May 2026 12:17:22 -0400 Subject: [PATCH 1/5] add ParserConversionAction, do not translate unevaluated strings --- clang/include/clang/Parse/Parser.h | 1 + clang/include/clang/Sema/Sema.h | 4 +++- clang/lib/Parse/ParseDecl.cpp | 10 ++++++++++ clang/lib/Parse/ParseDeclCXX.cpp | 2 ++ clang/lib/Parse/ParseExpr.cpp | 6 +++--- clang/lib/Parse/Parser.cpp | 4 ++++ clang/lib/Sema/SemaExpr.cpp | 12 ++++++------ clang/test/CodeGen/systemz-charset-diag.cpp | 8 ++++++++ clang/test/CodeGen/systemz-charset.c | 5 +++++ 9 files changed, 42 insertions(+), 10 deletions(-) diff --git a/clang/include/clang/Parse/Parser.h b/clang/include/clang/Parse/Parser.h index f0e06473bf615..889df34ab9bfb 100644 --- a/clang/include/clang/Parse/Parser.h +++ b/clang/include/clang/Parse/Parser.h @@ -5706,6 +5706,7 @@ class Parser : public CodeCompletionHandler { bool Finished; }; ObjCImplParsingDataRAII *CurParsedObjCImpl; + ConversionAction ParserConversionAction; /// StashAwayMethodOrFunctionBodyTokens - Consume the tokens and store them /// for later parsing. diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h index f7d0d493e7081..859c975b4e099 100644 --- a/clang/include/clang/Sema/Sema.h +++ b/clang/include/clang/Sema/Sema.h @@ -55,6 +55,7 @@ #include "clang/Basic/TemplateKinds.h" #include "clang/Basic/TokenKinds.h" #include "clang/Basic/TypeTraits.h" +#include "clang/Lex/LiteralConverter.h" #include "clang/Sema/AnalysisBasedWarnings.h" #include "clang/Sema/Attr.h" #include "clang/Sema/CleanupInfo.h" @@ -7379,7 +7380,8 @@ class Sema final : public SemaBase { /// from multiple tokens. However, the common case is that StringToks points /// to one string. ExprResult ActOnStringLiteral(ArrayRef<Token> StringToks, - Scope *UDLScope = nullptr); + Scope *UDLScope = nullptr, + ConversionAction Action = CA_ToExecEncoding); ExprResult ActOnUnevaluatedStringLiteral(ArrayRef<Token> StringToks); diff --git a/clang/lib/Parse/ParseDecl.cpp b/clang/lib/Parse/ParseDecl.cpp index 3f41e7c5c6f0d..6c7becf184a92 100644 --- a/clang/lib/Parse/ParseDecl.cpp +++ b/clang/lib/Parse/ParseDecl.cpp @@ -564,6 +564,9 @@ unsigned Parser::ParseAttributeArgsCommon( nullptr, Sema::ExpressionEvaluationContextRecord::EK_AttrArgument); + SaveAndRestore<ConversionAction> SavedTranslationState( + ParserConversionAction, CA_NoConversion); + ExprResult ArgExpr = ParseAssignmentExpression(); if (ArgExpr.isInvalid()) { SkipUntil(tok::r_paren, StopAtSemi); @@ -644,6 +647,9 @@ void Parser::ParseGNUAttributeArgs( ParsedAttr::Kind AttrKind = ParsedAttr::getParsedKind(AttrName, ScopeName, Form.getSyntax()); + SaveAndRestore<ConversionAction> SavedTranslationState(ParserConversionAction, + CA_NoConversion); + if (AttrKind == ParsedAttr::AT_Availability) { ParseAvailabilityAttribute(*AttrName, AttrNameLoc, Attrs, EndLoc, ScopeName, ScopeLoc, Form); @@ -723,6 +729,9 @@ unsigned Parser::ParseClangAttributeArgs( ParsedAttr::Kind AttrKind = ParsedAttr::getParsedKind(AttrName, ScopeName, Form.getSyntax()); + SaveAndRestore<ConversionAction> SavedTranslationState(ParserConversionAction, + CA_NoConversion); + switch (AttrKind) { default: return ParseAttributeArgsCommon(AttrName, AttrNameLoc, Attrs, EndLoc, @@ -1546,6 +1555,7 @@ void Parser::ParseExternalSourceSymbolAttribute( SkipUntil(tok::comma, tok::r_paren, StopAtSemi | StopBeforeMatch); continue; } + if (Keyword == Ident_language) { if (HadLanguage) { Diag(KeywordLoc, diag::err_external_source_symbol_duplicate_clause) diff --git a/clang/lib/Parse/ParseDeclCXX.cpp b/clang/lib/Parse/ParseDeclCXX.cpp index 893989bd2398f..388cfa662068a 100644 --- a/clang/lib/Parse/ParseDeclCXX.cpp +++ b/clang/lib/Parse/ParseDeclCXX.cpp @@ -1001,6 +1001,8 @@ Decl *Parser::ParseStaticAssertDeclaration(SourceLocation &DeclEnd) { return nullptr; } } else if (tokenIsLikeStringLiteral(Tok, getLangOpts())) { + SaveAndRestore<ConversionAction> SavedTranslationState( + ParserConversionAction, CA_NoConversion); AssertMessage = ParseUnevaluatedStringLiteralExpression(); } else { Diag(Tok, diag::err_expected_string_literal) diff --git a/clang/lib/Parse/ParseExpr.cpp b/clang/lib/Parse/ParseExpr.cpp index 451287bbeee3f..bff32eed404f1 100644 --- a/clang/lib/Parse/ParseExpr.cpp +++ b/clang/lib/Parse/ParseExpr.cpp @@ -3041,9 +3041,9 @@ ExprResult Parser::ParseStringLiteralExpression(bool AllowUserDefinedLiteral, } // Pass the set of string tokens, ready for concatenation, to the actions. - return Actions.ActOnStringLiteral(StringToks, - AllowUserDefinedLiteral ? getCurScope() - : nullptr); + return Actions.ActOnStringLiteral( + StringToks, AllowUserDefinedLiteral ? getCurScope() : nullptr, + ParserConversionAction); } ExprResult Parser::ParseGenericSelectionExpression() { diff --git a/clang/lib/Parse/Parser.cpp b/clang/lib/Parse/Parser.cpp index 5e1fd4df1a3f0..7ac5e0a36d60e 100644 --- a/clang/lib/Parse/Parser.cpp +++ b/clang/lib/Parse/Parser.cpp @@ -70,6 +70,8 @@ Parser::Parser(Preprocessor &pp, Sema &actions, bool skipFunctionBodies) NumCachedScopes = 0; CurParsedObjCImpl = nullptr; + ParserConversionAction = CA_ToExecEncoding; + // Add #pragma handlers. These are removed and destroyed in the // destructor. initializePragmaHandlers(); @@ -1551,6 +1553,8 @@ void Parser::ParseKNRParamDeclarations(Declarator &D) { } ExprResult Parser::ParseAsmStringLiteral(bool ForAsmLabel) { + SaveAndRestore<ConversionAction> SavedTranslationState(ParserConversionAction, + CA_NoConversion); ExprResult AsmString; if (isTokenStringLiteral()) { diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp index 592cb1d588370..9eed681dff359 100644 --- a/clang/lib/Sema/SemaExpr.cpp +++ b/clang/lib/Sema/SemaExpr.cpp @@ -2165,8 +2165,8 @@ ExprResult Sema::ActOnUnevaluatedStringLiteral(ArrayRef<Token> StringToks) { if (getLangOpts().MicrosoftExt) StringToks = ExpandedToks = ExpandFunctionLocalPredefinedMacros(StringToks); - StringLiteralParser Literal(StringToks, PP, - StringLiteralEvalMethod::Unevaluated); + StringLiteralParser Literal( + StringToks, PP, StringLiteralEvalMethod::Unevaluated, CA_NoConversion); if (Literal.hadError) return ExprError(); @@ -2237,8 +2237,8 @@ Sema::ExpandFunctionLocalPredefinedMacros(ArrayRef<Token> Toks) { return ExpandedToks; } -ExprResult -Sema::ActOnStringLiteral(ArrayRef<Token> StringToks, Scope *UDLScope) { +ExprResult Sema::ActOnStringLiteral(ArrayRef<Token> StringToks, Scope *UDLScope, + ConversionAction Action) { assert(!StringToks.empty() && "Must have at least one string!"); // StringToks needs backing storage as it doesn't hold array elements itself @@ -2246,8 +2246,8 @@ Sema::ActOnStringLiteral(ArrayRef<Token> StringToks, Scope *UDLScope) { if (getLangOpts().MicrosoftExt) StringToks = ExpandedToks = ExpandFunctionLocalPredefinedMacros(StringToks); - StringLiteralParser Literal( - StringToks, PP, StringLiteralEvalMethod::Evaluated, CA_ToLiteralEncoding); + StringLiteralParser Literal(StringToks, PP, + StringLiteralEvalMethod::Evaluated, Action); if (Literal.hadError) return ExprError(); diff --git a/clang/test/CodeGen/systemz-charset-diag.cpp b/clang/test/CodeGen/systemz-charset-diag.cpp index 4ed94810150a3..ad08e1f391214 100644 --- a/clang/test/CodeGen/systemz-charset-diag.cpp +++ b/clang/test/CodeGen/systemz-charset-diag.cpp @@ -1,3 +1,11 @@ // RUN: %clang_cc1 -triple s390x-none-zos -fexec-charset IBM-1047 %s -std=c++17 -emit-llvm -o - -verify const char* Computer = "🖥️"; // expected-error-re {{conversion to literal encoding failed: {{.*}}}} + +static_assert(false, "Error string"); // expected-error {{static assertion failed: Error string}} + +[[deprecated("message")]] void test_deprecated() {return;} // expected-note {{'test_deprecated' has been explicitly marked deprecated here}} + +int main() { + test_deprecated(); // expected-warning {{'test_deprecated' is deprecated: message}} +} diff --git a/clang/test/CodeGen/systemz-charset.c b/clang/test/CodeGen/systemz-charset.c index 766b6a83f00ff..618b0cc203ab6 100644 --- a/clang/test/CodeGen/systemz-charset.c +++ b/clang/test/CodeGen/systemz-charset.c @@ -66,3 +66,8 @@ const char* hello_macro = HELLO; const char* preprocessor_concatenation = HELLO_WORLD; //CHECK: c"\C8\85\93\93\96@\E6\96\99\93\84Z\00" //CHECK-UTF8: c"Hello World!\00" + +void test1() { + printf(__FUNCTION__); +} +//CHECK: @__FUNCTION__.test1 = private unnamed_addr constant [6 x i8] c"\A3\85\A2\A3\F1\00" >From 04ec584205a111174e0704878cd19f5e06e0b67f Mon Sep 17 00:00:00 2001 From: Abhina Sreeskantharajan <[email protected]> Date: Fri, 8 May 2026 12:29:23 -0400 Subject: [PATCH 2/5] Remove old include --- clang/include/clang/Sema/Sema.h | 1 - 1 file changed, 1 deletion(-) diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h index 859c975b4e099..78dad5dbff337 100644 --- a/clang/include/clang/Sema/Sema.h +++ b/clang/include/clang/Sema/Sema.h @@ -55,7 +55,6 @@ #include "clang/Basic/TemplateKinds.h" #include "clang/Basic/TokenKinds.h" #include "clang/Basic/TypeTraits.h" -#include "clang/Lex/LiteralConverter.h" #include "clang/Sema/AnalysisBasedWarnings.h" #include "clang/Sema/Attr.h" #include "clang/Sema/CleanupInfo.h" >From b195e37b1a221c5856cca5e467625dae0b8b7538 Mon Sep 17 00:00:00 2001 From: Abhina Sreeskantharajan <[email protected]> Date: Mon, 11 May 2026 09:27:48 -0400 Subject: [PATCH 3/5] Fix build failure --- clang/include/clang/Sema/Sema.h | 1 + 1 file changed, 1 insertion(+) diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h index 78dad5dbff337..bc6accf5b5b0e 100644 --- a/clang/include/clang/Sema/Sema.h +++ b/clang/include/clang/Sema/Sema.h @@ -55,6 +55,7 @@ #include "clang/Basic/TemplateKinds.h" #include "clang/Basic/TokenKinds.h" #include "clang/Basic/TypeTraits.h" +#include "clang/Lex/TextEncodingConfig.h" #include "clang/Sema/AnalysisBasedWarnings.h" #include "clang/Sema/Attr.h" #include "clang/Sema/CleanupInfo.h" >From ba04fb8698984c16ee0f106cb5486799a3a8f748 Mon Sep 17 00:00:00 2001 From: Abhina Sreeskantharajan <[email protected]> Date: Tue, 12 May 2026 08:07:08 -0400 Subject: [PATCH 4/5] fix CI --- clang/test/CodeGen/systemz-charset.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/clang/test/CodeGen/systemz-charset.c b/clang/test/CodeGen/systemz-charset.c index 618b0cc203ab6..16f269f8fb2f5 100644 --- a/clang/test/CodeGen/systemz-charset.c +++ b/clang/test/CodeGen/systemz-charset.c @@ -1,6 +1,8 @@ // RUN: %clang_cc1 %s -emit-llvm -triple s390x-none-zos -fexec-charset IBM-1047 -o - | FileCheck %s // RUN: %clang_cc1 %s -emit-llvm -triple s390x-none-zos -fexec-charset UTF-8 -DIBM1047_ONLY=1 -o - | FileCheck %s --check-prefix=CHECK-UTF8 +int printf(char const *, ...); + const char *UpperCaseLetters = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"; //CHECK: c"\C1\C2\C3\C4\C5\C6\C7\C8\C9\D1\D2\D3\D4\D5\D6\D7\D8\D9\E2\E3\E4\E5\E6\E7\E8\E9\00" //CHECK-UTF8: c"ABCDEFGHIJKLMNOPQRSTUVWXYZ\00" >From 325eaf0a7b5c5fdb12d3857dcc0155dd9254ca20 Mon Sep 17 00:00:00 2001 From: Abhina Sreeskantharajan <[email protected]> Date: Tue, 12 May 2026 15:21:15 -0400 Subject: [PATCH 5/5] fix CI --- clang/include/clang/Sema/Sema.h | 4 ++-- clang/lib/Parse/ParseDecl.cpp | 1 - clang/lib/Parse/ParseDeclCXX.cpp | 2 -- clang/lib/Parse/Parser.cpp | 2 +- clang/lib/Sema/SemaExpr.cpp | 4 ++-- clang/test/CodeGen/systemz-charset.c | 7 ------- 6 files changed, 5 insertions(+), 15 deletions(-) diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h index bc6accf5b5b0e..51e819840c7a4 100644 --- a/clang/include/clang/Sema/Sema.h +++ b/clang/include/clang/Sema/Sema.h @@ -55,7 +55,7 @@ #include "clang/Basic/TemplateKinds.h" #include "clang/Basic/TokenKinds.h" #include "clang/Basic/TypeTraits.h" -#include "clang/Lex/TextEncodingConfig.h" +#include "clang/Lex/TextEncoding.h" #include "clang/Sema/AnalysisBasedWarnings.h" #include "clang/Sema/Attr.h" #include "clang/Sema/CleanupInfo.h" @@ -7381,7 +7381,7 @@ class Sema final : public SemaBase { /// to one string. ExprResult ActOnStringLiteral(ArrayRef<Token> StringToks, Scope *UDLScope = nullptr, - ConversionAction Action = CA_ToExecEncoding); + ConversionAction Action = CA_ToLiteralEncoding); ExprResult ActOnUnevaluatedStringLiteral(ArrayRef<Token> StringToks); diff --git a/clang/lib/Parse/ParseDecl.cpp b/clang/lib/Parse/ParseDecl.cpp index 6c7becf184a92..cbf4b11a719ca 100644 --- a/clang/lib/Parse/ParseDecl.cpp +++ b/clang/lib/Parse/ParseDecl.cpp @@ -1555,7 +1555,6 @@ void Parser::ParseExternalSourceSymbolAttribute( SkipUntil(tok::comma, tok::r_paren, StopAtSemi | StopBeforeMatch); continue; } - if (Keyword == Ident_language) { if (HadLanguage) { Diag(KeywordLoc, diag::err_external_source_symbol_duplicate_clause) diff --git a/clang/lib/Parse/ParseDeclCXX.cpp b/clang/lib/Parse/ParseDeclCXX.cpp index 388cfa662068a..893989bd2398f 100644 --- a/clang/lib/Parse/ParseDeclCXX.cpp +++ b/clang/lib/Parse/ParseDeclCXX.cpp @@ -1001,8 +1001,6 @@ Decl *Parser::ParseStaticAssertDeclaration(SourceLocation &DeclEnd) { return nullptr; } } else if (tokenIsLikeStringLiteral(Tok, getLangOpts())) { - SaveAndRestore<ConversionAction> SavedTranslationState( - ParserConversionAction, CA_NoConversion); AssertMessage = ParseUnevaluatedStringLiteralExpression(); } else { Diag(Tok, diag::err_expected_string_literal) diff --git a/clang/lib/Parse/Parser.cpp b/clang/lib/Parse/Parser.cpp index 7ac5e0a36d60e..5a199b842fe8e 100644 --- a/clang/lib/Parse/Parser.cpp +++ b/clang/lib/Parse/Parser.cpp @@ -70,7 +70,7 @@ Parser::Parser(Preprocessor &pp, Sema &actions, bool skipFunctionBodies) NumCachedScopes = 0; CurParsedObjCImpl = nullptr; - ParserConversionAction = CA_ToExecEncoding; + ParserConversionAction = CA_ToLiteralEncoding; // Add #pragma handlers. These are removed and destroyed in the // destructor. diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp index 9eed681dff359..ed4fcd3f975dc 100644 --- a/clang/lib/Sema/SemaExpr.cpp +++ b/clang/lib/Sema/SemaExpr.cpp @@ -2165,8 +2165,8 @@ ExprResult Sema::ActOnUnevaluatedStringLiteral(ArrayRef<Token> StringToks) { if (getLangOpts().MicrosoftExt) StringToks = ExpandedToks = ExpandFunctionLocalPredefinedMacros(StringToks); - StringLiteralParser Literal( - StringToks, PP, StringLiteralEvalMethod::Unevaluated, CA_NoConversion); + StringLiteralParser Literal(StringToks, PP, + StringLiteralEvalMethod::Unevaluated); if (Literal.hadError) return ExprError(); diff --git a/clang/test/CodeGen/systemz-charset.c b/clang/test/CodeGen/systemz-charset.c index 16f269f8fb2f5..766b6a83f00ff 100644 --- a/clang/test/CodeGen/systemz-charset.c +++ b/clang/test/CodeGen/systemz-charset.c @@ -1,8 +1,6 @@ // RUN: %clang_cc1 %s -emit-llvm -triple s390x-none-zos -fexec-charset IBM-1047 -o - | FileCheck %s // RUN: %clang_cc1 %s -emit-llvm -triple s390x-none-zos -fexec-charset UTF-8 -DIBM1047_ONLY=1 -o - | FileCheck %s --check-prefix=CHECK-UTF8 -int printf(char const *, ...); - const char *UpperCaseLetters = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"; //CHECK: c"\C1\C2\C3\C4\C5\C6\C7\C8\C9\D1\D2\D3\D4\D5\D6\D7\D8\D9\E2\E3\E4\E5\E6\E7\E8\E9\00" //CHECK-UTF8: c"ABCDEFGHIJKLMNOPQRSTUVWXYZ\00" @@ -68,8 +66,3 @@ const char* hello_macro = HELLO; const char* preprocessor_concatenation = HELLO_WORLD; //CHECK: c"\C8\85\93\93\96@\E6\96\99\93\84Z\00" //CHECK-UTF8: c"Hello World!\00" - -void test1() { - printf(__FUNCTION__); -} -//CHECK: @__FUNCTION__.test1 = private unnamed_addr constant [6 x i8] c"\A3\85\A2\A3\F1\00" _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
