This patch enables the fexec-charset option to control the execution charset of string literals. It sets the default internal charset, system charset, and execution charset for z/OS and UTF-8 for all other platforms.

Author: abhina-sree

clang/docs/LanguageExtensions.rst

@@ -416,8 +416,7 @@ Builtin Macros
 ``__clang_literal_encoding__``
   Defined to a narrow string literal that represents the current encoding of
   narrow string literals, e.g., ``"hello"``. This macro typically expands to
-  "UTF-8" (but may change in the future if the
-  ``-fexec-charset="Encoding-Name"`` option is implemented.)
+  the charset specified by -fexec-charset if specified, or the system charset.
 
 ``__clang_wide_literal_encoding__``
   Defined to a narrow string literal that represents the current encoding of

clang/include/clang/Basic/LangOptions.h

@@ -633,6 +633,9 @@ class LangOptions : public LangOptionsBase {
   bool AtomicFineGrainedMemory = false;
   bool AtomicIgnoreDenormalMode = false;
 
+  /// Name of the exec charset to convert the internal charset to.
+  std::string ExecCharset;
+
   LangOptions();
 
   /// Set language defaults for the given input language and

clang/include/clang/Basic/TokenKinds.h

@@ -101,6 +101,13 @@ inline bool isLiteral(TokenKind K) {
          isStringLiteral(K) || K == tok::header_name || K == tok::binary_data;
 }
 
+/// Return true if this is a utf literal kind.
+inline bool isUTFLiteral(TokenKind K) {
+  return K == tok::utf8_char_constant || K == tok::utf8_string_literal ||
+         K == tok::utf16_char_constant || K == tok::utf16_string_literal ||
+         K == tok::utf32_char_constant || K == tok::utf32_string_literal;
+}
+
 /// Return true if this is any of tok::annot_* kinds.
 bool isAnnotation(TokenKind K);
 

clang/include/clang/Driver/Options.td

@@ -7197,6 +7197,11 @@ let Visibility = [CC1Option, CC1AsOption, FC1Option] in {
 def tune_cpu : Separate<["-"], "tune-cpu">,
   HelpText<"Tune for a specific cpu type">,
   MarshallingInfoString<TargetOpts<"TuneCPU">>;
+def fexec_charset : Separate<["-"], "fexec-charset">, MetaVarName<"<charset>">,
+  HelpText<"Set the execution <charset> for string and character literals. "
+           "Supported character encodings include ISO8859-1, UTF-8, IBM-1047 "
+           "and those supported by the host icu or iconv library.">,
+  MarshallingInfoString<LangOpts<"ExecCharset">>;
 def target_cpu : Separate<["-"], "target-cpu">,
   HelpText<"Target a specific cpu type">,
   MarshallingInfoString<TargetOpts<"CPU">>;

clang/include/clang/Lex/LiteralConverter.h

@@ -0,0 +1,36 @@
+//===--- clang/Lex/LiteralConverter.h - Translator for Literals -*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LEX_LITERALCONVERTER_H
+#define LLVM_CLANG_LEX_LITERALCONVERTER_H
+
+#include "clang/Basic/Diagnostic.h"
+#include "clang/Basic/LangOptions.h"
+#include "clang/Basic/TargetInfo.h"
+#include "llvm/ADT/StringMap.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/CharSet.h"
+
+enum ConversionAction { NoConversion, ToSystemCharset, ToExecCharset };
+
+class LiteralConverter {
+  llvm::StringRef InternalCharset;
+  llvm::StringRef SystemCharset;
+  llvm::StringRef ExecCharset;
+  llvm::StringMap<llvm::CharSetConverter> CharsetConverters;
+
+public:
+  llvm::CharSetConverter *getConverter(const char *Codepage);
+  llvm::CharSetConverter *getConverter(ConversionAction Action);
+  llvm::CharSetConverter *createAndInsertCharConverter(const char *To);
+  void setConvertersFromOptions(const clang::LangOptions &Opts,
+                                const clang::TargetInfo &TInfo,
+                                clang::DiagnosticsEngine &Diags);
+};
+
+#endif

clang/include/clang/Lex/LiteralSupport.h

@@ -17,10 +17,12 @@
 #include "clang/Basic/CharInfo.h"
 #include "clang/Basic/LLVM.h"
 #include "clang/Basic/TokenKinds.h"
+#include "clang/Lex/LiteralConverter.h"
 #include "llvm/ADT/APFloat.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/Support/CharSet.h"
 #include "llvm/Support/DataTypes.h"
 
 namespace clang {
@@ -233,6 +235,7 @@ class StringLiteralParser {
   const LangOptions &Features;
   const TargetInfo &Target;
   DiagnosticsEngine *Diags;
+  LiteralConverter *LiteralConv;
 
   unsigned MaxTokenLength;
   unsigned SizeBound;
@@ -246,18 +249,19 @@ class StringLiteralParser {
   StringLiteralEvalMethod EvalMethod;
 
 public:
-  StringLiteralParser(ArrayRef<Token> StringToks, Preprocessor &PP,
-                      StringLiteralEvalMethod StringMethod =
-                          StringLiteralEvalMethod::Evaluated);
+  StringLiteralParser(
+      ArrayRef<Token> StringToks, Preprocessor &PP,
+      StringLiteralEvalMethod StringMethod = StringLiteralEvalMethod::Evaluated,
+      ConversionAction Action = ToExecCharset);
   StringLiteralParser(ArrayRef<Token> StringToks, const SourceManager &sm,
                       const LangOptions &features, const TargetInfo &target,
                       DiagnosticsEngine *diags = nullptr)
       : SM(sm), Features(features), Target(target), Diags(diags),
-        MaxTokenLength(0), SizeBound(0), CharByteWidth(0), Kind(tok::unknown),
-        ResultPtr(ResultBuf.data()),
+        LiteralConv(nullptr), MaxTokenLength(0), SizeBound(0), CharByteWidth(0),
+        Kind(tok::unknown), ResultPtr(ResultBuf.data()),
         EvalMethod(StringLiteralEvalMethod::Evaluated), hadError(false),
         Pascal(false) {
-    init(StringToks);
+    init(StringToks, NoConversion);
   }
 
   bool hadError;
@@ -305,7 +309,7 @@ class StringLiteralParser {
   static bool isValidUDSuffix(const LangOptions &LangOpts, StringRef Suffix);
 
 private:
-  void init(ArrayRef<Token> StringToks);
+  void init(ArrayRef<Token> StringToks, ConversionAction Action);
   bool CopyStringFragment(const Token &Tok, const char *TokBegin,
                           StringRef Fragment);
   void DiagnoseLexingError(SourceLocation Loc);

clang/include/clang/Lex/Preprocessor.h

@@ -25,6 +25,7 @@
 #include "clang/Basic/TokenKinds.h"
 #include "clang/Lex/HeaderSearch.h"
 #include "clang/Lex/Lexer.h"
+#include "clang/Lex/LiteralConverter.h"
 #include "clang/Lex/MacroInfo.h"
 #include "clang/Lex/ModuleLoader.h"
 #include "clang/Lex/ModuleMap.h"
@@ -156,6 +157,7 @@ class Preprocessor {
   std::unique_ptr<ScratchBuffer> ScratchBuf;
   HeaderSearch      &HeaderInfo;
   ModuleLoader      &TheModuleLoader;
+  LiteralConverter LiteralConv;
 
   /// External source of macros.
   ExternalPreprocessorSource *ExternalSource;
@@ -1218,6 +1220,7 @@ class Preprocessor {
   SelectorTable &getSelectorTable() { return Selectors; }
   Builtin::Context &getBuiltinInfo() { return *BuiltinInfo; }
   llvm::BumpPtrAllocator &getPreprocessorAllocator() { return BP; }
+  LiteralConverter &getLiteralConverter() { return LiteralConv; }
 
   void setExternalSource(ExternalPreprocessorSource *Source) {
     ExternalSource = Source;

clang/lib/Driver/ToolChains/Clang.cpp

@@ -50,6 +50,7 @@
 #include "llvm/Frontend/Debug/Options.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Option/ArgList.h"
+#include "llvm/Support/CharSet.h"
 #include "llvm/Support/CodeGen.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/Compression.h"
@@ -7597,12 +7598,20 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                                           << value;
   }
 
-  // -fexec_charset=UTF-8 is default. Reject others
+  // Set the default fexec-charset as the system charset.
+  CmdArgs.push_back("-fexec-charset");
+  CmdArgs.push_back(Args.MakeArgString(Triple.getSystemCharset()));
   if (Arg *execCharset = Args.getLastArg(options::OPT_fexec_charset_EQ)) {
     StringRef value = execCharset->getValue();
-    if (!value.equals_insensitive("utf-8"))
-      D.Diag(diag::err_drv_invalid_value) << execCharset->getAsString(Args)
-                                          << value;
+    llvm::ErrorOr<llvm::CharSetConverter> ErrorOrConverter =
+        llvm::CharSetConverter::create("UTF-8", value.data());
+    if (ErrorOrConverter) {
+      CmdArgs.push_back("-fexec-charset");
+      CmdArgs.push_back(Args.MakeArgString(value));
+    } else {
+      D.Diag(diag::err_drv_invalid_value)
+          << execCharset->getAsString(Args) << value;
+    }
   }
 
   RenderDiagnosticsOptions(D, Args, CmdArgs);

clang/lib/Frontend/CompilerInstance.cpp

@@ -32,6 +32,7 @@
 #include "clang/Frontend/Utils.h"
 #include "clang/Frontend/VerifyDiagnosticConsumer.h"
 #include "clang/Lex/HeaderSearch.h"
+#include "clang/Lex/LiteralConverter.h"
 #include "clang/Lex/Preprocessor.h"
 #include "clang/Lex/PreprocessorOptions.h"
 #include "clang/Sema/CodeCompleteConsumer.h"
@@ -537,6 +538,9 @@ void CompilerInstance::createPreprocessor(TranslationUnitKind TUKind) {
 
   if (GetDependencyDirectives)
     PP->setDependencyDirectivesGetter(*GetDependencyDirectives);
+
+  PP->getLiteralConverter().setConvertersFromOptions(getLangOpts(), getTarget(),
+                                                     getDiagnostics());
 }
 
 std::string CompilerInstance::getSpecificModuleCachePath(StringRef ModuleHash) {

clang/lib/Frontend/InitPreprocessor.cpp

@@ -1058,10 +1058,14 @@ static void InitializePredefinedMacros(const TargetInfo &TI,
     }
   }
 
-  // Macros to help identify the narrow and wide character sets
-  // FIXME: clang currently ignores -fexec-charset=. If this changes,
-  // then this may need to be updated.
-  Builder.defineMacro("__clang_literal_encoding__", "\"UTF-8\"");
+  // Macros to help identify the narrow and wide character sets. This is set
+  // to fexec-charset. If fexec-charset is not specified, the default is the
+  // system charset.
+  if (!LangOpts.ExecCharset.empty())
+    Builder.defineMacro("__clang_literal_encoding__", LangOpts.ExecCharset);
+  else
+    Builder.defineMacro("__clang_literal_encoding__",
+                        TI.getTriple().getSystemCharset());
   if (TI.getTypeWidth(TI.getWCharType()) >= 32) {
     // FIXME: 32-bit wchar_t signals UTF-32. This may change
     // if -fwide-exec-charset= is ever supported.

clang/lib/Lex/CMakeLists.txt

@@ -12,6 +12,7 @@ add_clang_library(clangLex
   InitHeaderSearch.cpp
   Lexer.cpp
   LexHLSLRootSignature.cpp
+  LiteralConverter.cpp
   LiteralSupport.cpp
   MacroArgs.cpp
   MacroInfo.cpp

clang/lib/Lex/LiteralConverter.cpp

@@ -0,0 +1,68 @@
+//===--- LiteralConverter.cpp - Translator for String Literals -----------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/Lex/LiteralConverter.h"
+#include "clang/Basic/DiagnosticDriver.h"
+
+using namespace llvm;
+
+llvm::CharSetConverter *LiteralConverter::getConverter(const char *Codepage) {
+  auto Iter = CharsetConverters.find(Codepage);
+  if (Iter != CharsetConverters.end())
+    return &Iter->second;
+  return nullptr;
+}
+
+llvm::CharSetConverter *
+LiteralConverter::getConverter(ConversionAction Action) {
+  StringRef CodePage;
+  if (Action == ToSystemCharset)
+    CodePage = SystemCharset;
+  else if (Action == ToExecCharset)
+    CodePage = ExecCharset;
+  else
+    CodePage = InternalCharset;
+  return getConverter(CodePage.data());
+}
+
+llvm::CharSetConverter *
+LiteralConverter::createAndInsertCharConverter(const char *To) {
+  const char *From = InternalCharset.data();
+  llvm::CharSetConverter *Converter = getConverter(To);
+  if (Converter)
+    return Converter;
+
+  ErrorOr<CharSetConverter> ErrorOrConverter =
+      llvm::CharSetConverter::create(From, To);
+  if (!ErrorOrConverter)
+    return nullptr;
+  CharsetConverters.insert_or_assign(StringRef(To),
+                                     std::move(*ErrorOrConverter));
+  return getConverter(To);
+}
+
+void LiteralConverter::setConvertersFromOptions(
+    const clang::LangOptions &Opts, const clang::TargetInfo &TInfo,
+    clang::DiagnosticsEngine &Diags) {
+  using namespace llvm;
+  SystemCharset = TInfo.getTriple().getSystemCharset();
+  InternalCharset = "UTF-8";
+  ExecCharset = Opts.ExecCharset.empty() ? InternalCharset : Opts.ExecCharset;
+  // Create converter between internal and system charset
+  if (!InternalCharset.equals(SystemCharset))
+    createAndInsertCharConverter(SystemCharset.data());
+
+  // Create converter between internal and exec charset specified
+  // in fexec-charset option.
+  if (InternalCharset.equals(ExecCharset))
+    return;
+  if (!createAndInsertCharConverter(ExecCharset.data())) {
+    Diags.Report(clang::diag::err_drv_invalid_value)
+        << "-fexec-charset" << ExecCharset;
+  }
+}