Revert "[clang-format][NFC] Make LangOpts global in namespace Format (#81390)"

This reverts commit 03f571995b4f0c260254955afd16ec44d0764794.

We can't hide getFormattingLangOpts() as it's used by other tools.

clang/include/clang/Format/Format.h

@@ -14,6 +14,7 @@
 #ifndef LLVM_CLANG_FORMAT_FORMAT_H
 #define LLVM_CLANG_FORMAT_FORMAT_H
 
+#include "clang/Basic/LangOptions.h"
 #include "clang/Tooling/Core/Replacement.h"
 #include "clang/Tooling/Inclusions/IncludeStyle.h"
 #include "llvm/ADT/ArrayRef.h"
@@ -5178,6 +5179,11 @@ tooling::Replacements sortUsingDeclarations(const FormatStyle &Style,
                                             ArrayRef<tooling::Range> Ranges,
                                             StringRef FileName = "<stdin>");
 
+/// Returns the ``LangOpts`` that the formatter expects you to set.
+///
+/// \param Style determines specific settings for lexing mode.
+LangOptions getFormattingLangOpts(const FormatStyle &Style = getLLVMStyle());
+
 /// Description to be used for help text for a ``llvm::cl`` option for
 /// specifying format style. The description is closely related to the operation
 /// of ``getStyle()``.

clang/lib/Format/Format.cpp

@@ -3823,6 +3823,36 @@ tooling::Replacements sortUsingDeclarations(const FormatStyle &Style,
   return UsingDeclarationsSorter(*Env, Style).process().first;
 }
 
+LangOptions getFormattingLangOpts(const FormatStyle &Style) {
+  LangOptions LangOpts;
+
+  FormatStyle::LanguageStandard LexingStd = Style.Standard;
+  if (LexingStd == FormatStyle::LS_Auto)
+    LexingStd = FormatStyle::LS_Latest;
+  if (LexingStd == FormatStyle::LS_Latest)
+    LexingStd = FormatStyle::LS_Cpp20;
+  LangOpts.CPlusPlus = 1;
+  LangOpts.CPlusPlus11 = LexingStd >= FormatStyle::LS_Cpp11;
+  LangOpts.CPlusPlus14 = LexingStd >= FormatStyle::LS_Cpp14;
+  LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
+  LangOpts.CPlusPlus20 = LexingStd >= FormatStyle::LS_Cpp20;
+  LangOpts.Char8 = LexingStd >= FormatStyle::LS_Cpp20;
+  // Turning on digraphs in standards before C++0x is error-prone, because e.g.
+  // the sequence "<::" will be unconditionally treated as "[:".
+  // Cf. Lexer::LexTokenInternal.
+  LangOpts.Digraphs = LexingStd >= FormatStyle::LS_Cpp11;
+
+  LangOpts.LineComment = 1;
+  bool AlternativeOperators = Style.isCpp();
+  LangOpts.CXXOperatorNames = AlternativeOperators ? 1 : 0;
+  LangOpts.Bool = 1;
+  LangOpts.ObjC = 1;
+  LangOpts.MicrosoftExt = 1;    // To get kw___try, kw___finally.
+  LangOpts.DeclSpecKeyword = 1; // To get __declspec.
+  LangOpts.C99 = 1; // To get kw_restrict for non-underscore-prefixed restrict.
+  return LangOpts;
+}
+
 const char *StyleOptionHelpDescription =
     "Set coding style. <string> can be:\n"
     "1. A preset: LLVM, GNU, Google, Chromium, Microsoft,\n"

clang/lib/Format/FormatTokenLexer.cpp

@@ -13,7 +13,11 @@
 //===----------------------------------------------------------------------===//
 
 #include "FormatTokenLexer.h"
-#include "TokenAnalyzer.h"
+#include "FormatToken.h"
+#include "clang/Basic/SourceLocation.h"
+#include "clang/Basic/SourceManager.h"
+#include "clang/Format/Format.h"
+#include "llvm/Support/Regex.h"
 
 namespace clang {
 namespace format {
@@ -24,12 +28,12 @@ FormatTokenLexer::FormatTokenLexer(
     llvm::SpecificBumpPtrAllocator<FormatToken> &Allocator,
     IdentifierTable &IdentTable)
     : FormatTok(nullptr), IsFirstToken(true), StateStack({LexerState::NORMAL}),
-      Column(Column), TrailingWhitespace(0), SourceMgr(SourceMgr), ID(ID),
+      Column(Column), TrailingWhitespace(0),
+      LangOpts(getFormattingLangOpts(Style)), SourceMgr(SourceMgr), ID(ID),
       Style(Style), IdentTable(IdentTable), Keywords(IdentTable),
       Encoding(Encoding), Allocator(Allocator), FirstInLineIndex(0),
       FormattingDisabled(false), MacroBlockBeginRegex(Style.MacroBlockBegin),
       MacroBlockEndRegex(Style.MacroBlockEnd) {
-  assert(LangOpts.CPlusPlus);
   Lex.reset(new Lexer(ID, SourceMgr.getBufferOrFake(ID), SourceMgr, LangOpts));
   Lex->SetKeepWhitespaceMode(true);
 
@@ -1438,7 +1442,7 @@ void FormatTokenLexer::readRawToken(FormatToken &Tok) {
 
 void FormatTokenLexer::resetLexer(unsigned Offset) {
   StringRef Buffer = SourceMgr.getBufferData(ID);
-  assert(LangOpts.CPlusPlus);
+  LangOpts = getFormattingLangOpts(Style);
   Lex.reset(new Lexer(SourceMgr.getLocForStartOfFile(ID), LangOpts,
                       Buffer.begin(), Buffer.begin() + Offset, Buffer.end()));
   Lex->SetKeepWhitespaceMode(true);

clang/lib/Format/FormatTokenLexer.h

@@ -17,6 +17,7 @@
 
 #include "Encoding.h"
 #include "FormatToken.h"
+#include "clang/Basic/LangOptions.h"
 #include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Format/Format.h"
@@ -119,6 +120,7 @@ private:
   unsigned Column;
   unsigned TrailingWhitespace;
   std::unique_ptr<Lexer> Lex;
+  LangOptions LangOpts;
   const SourceManager &SourceMgr;
   FileID ID;
   const FormatStyle &Style;

clang/lib/Format/IntegerLiteralSeparatorFixer.cpp

@@ -79,7 +79,7 @@ IntegerLiteralSeparatorFixer::process(const Environment &Env,
   AffectedRangeManager AffectedRangeMgr(SourceMgr, Env.getCharRanges());
 
   const auto ID = Env.getFileID();
-  assert(LangOpts.CPlusPlus);
+  const auto LangOpts = getFormattingLangOpts(Style);
   Lexer Lex(ID, SourceMgr.getBufferOrFake(ID), SourceMgr, LangOpts);
   Lex.SetCommentRetentionState(true);
 

clang/lib/Format/TokenAnalyzer.cpp

@@ -35,38 +35,6 @@
 namespace clang {
 namespace format {
 
-LangOptions LangOpts;
-
-/// Sets `LangOpts` for the formatter.
-///
-/// \param `Style` determines specific settings for lexing mode.
-static void setFormattingLangOpts(const FormatStyle &Style) {
-  FormatStyle::LanguageStandard LexingStd = Style.Standard;
-  if (LexingStd == FormatStyle::LS_Auto)
-    LexingStd = FormatStyle::LS_Latest;
-  if (LexingStd == FormatStyle::LS_Latest)
-    LexingStd = FormatStyle::LS_Cpp20;
-  LangOpts.CPlusPlus = 1;
-  LangOpts.CPlusPlus11 = LexingStd >= FormatStyle::LS_Cpp11;
-  LangOpts.CPlusPlus14 = LexingStd >= FormatStyle::LS_Cpp14;
-  LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
-  LangOpts.CPlusPlus20 = LexingStd >= FormatStyle::LS_Cpp20;
-  LangOpts.Char8 = LexingStd >= FormatStyle::LS_Cpp20;
-  // Turning on digraphs in standards before C++0x is error-prone, because e.g.
-  // the sequence "<::" will be unconditionally treated as "[:".
-  // Cf. Lexer::LexTokenInternal.
-  LangOpts.Digraphs = LexingStd >= FormatStyle::LS_Cpp11;
-
-  LangOpts.LineComment = 1;
-  bool AlternativeOperators = Style.isCpp();
-  LangOpts.CXXOperatorNames = AlternativeOperators ? 1 : 0;
-  LangOpts.Bool = 1;
-  LangOpts.ObjC = 1;
-  LangOpts.MicrosoftExt = 1;    // To get kw___try, kw___finally.
-  LangOpts.DeclSpecKeyword = 1; // To get __declspec.
-  LangOpts.C99 = 1; // To get kw_restrict for non-underscore-prefixed restrict.
-}
-
 // FIXME: Instead of printing the diagnostic we should store it and have a
 // better way to return errors through the format APIs.
 class FatalDiagnosticConsumer : public DiagnosticConsumer {
@@ -131,11 +99,9 @@ TokenAnalyzer::TokenAnalyzer(const Environment &Env, const FormatStyle &Style)
 
 std::pair<tooling::Replacements, unsigned>
 TokenAnalyzer::process(bool SkipAnnotation) {
-  setFormattingLangOpts(Style);
-
   tooling::Replacements Result;
   llvm::SpecificBumpPtrAllocator<FormatToken> Allocator;
-  IdentifierTable IdentTable(LangOpts);
+  IdentifierTable IdentTable(getFormattingLangOpts(Style));
   FormatTokenLexer Lex(Env.getSourceManager(), Env.getFileID(),
                        Env.getFirstStartColumn(), Style, Encoding, Allocator,
                        IdentTable);

clang/lib/Format/TokenAnalyzer.h

@@ -34,8 +34,6 @@
 namespace clang {
 namespace format {
 
-extern LangOptions LangOpts;
-
 class Environment {
 public:
   // This sets up an virtual file system with file \p FileName containing the

clang/unittests/Format/TestLexer.h

@@ -61,9 +61,7 @@ public:
             std::vector<std::unique_ptr<llvm::MemoryBuffer>> &Buffers,
             FormatStyle Style = getLLVMStyle())
       : Allocator(Allocator), Buffers(Buffers), Style(Style),
-        SourceMgr("test.cpp", ""), IdentTable(LangOpts) {
-    assert(LangOpts.CPlusPlus);
-  }
+        SourceMgr("test.cpp", ""), IdentTable(getFormattingLangOpts(Style)) {}
 
   TokenList lex(llvm::StringRef Code) {
     FormatTokenLexer Lex = getNewLexer(Code);