Release/20.x: [clang-format] Set C11 instead of C17 for LK_C

[owenca]

Backport d71ee7d

[llvmbot]

@llvm/pr-subscribers-clang-format

Author: Owen Pan (owenca)

Changes

Backport d71ee7d

---

Full diff: https://github.com/llvm/llvm-project/pull/134514.diff

6 Files Affected:

• (modified) clang/lib/Format/Format.cpp (+25-17)
• (modified) clang/lib/Format/FormatToken.cpp (+1-1)
• (modified) clang/lib/Format/TokenAnnotator.cpp (+1-2)
• (modified) clang/lib/Format/TokenAnnotator.h (+1-3)
• (modified) clang/lib/Format/UnwrappedLineParser.cpp (+1-3)
• (modified) clang/unittests/Format/TokenAnnotatorTest.cpp (+6)

diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index 768e655f65ce7..b97d8928178b5 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -3946,34 +3946,42 @@ tooling::Replacements sortUsingDeclarations(const FormatStyle &Style,
 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)
+  auto LexingStd = Style.Standard;
+  if (LexingStd == FormatStyle::LS_Auto || 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;
+
+  const bool SinceCpp11 = LexingStd >= FormatStyle::LS_Cpp11;
+  const bool SinceCpp20 = LexingStd >= FormatStyle::LS_Cpp20;
+
+  switch (Style.Language) {
+  case FormatStyle::LK_C:
+    LangOpts.C11 = 1;
+    break;
+  case FormatStyle::LK_Cpp:
+  case FormatStyle::LK_ObjC:
+    LangOpts.CXXOperatorNames = 1;
+    LangOpts.CPlusPlus11 = SinceCpp11;
+    LangOpts.CPlusPlus14 = LexingStd >= FormatStyle::LS_Cpp14;
+    LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
+    LangOpts.CPlusPlus20 = SinceCpp20;
+    [[fallthrough]];
+  default:
+    LangOpts.CPlusPlus = 1;
+  }
+
+  LangOpts.Char8 = SinceCpp20;
   // 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.Digraphs = SinceCpp11;
 
   LangOpts.LineComment = 1;
-
-  const auto Language = Style.Language;
-  LangOpts.C17 = Language == FormatStyle::LK_C;
-  LangOpts.CXXOperatorNames =
-      Language == FormatStyle::LK_Cpp || Language == FormatStyle::LK_ObjC;
-
   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;
 }
 
diff --git a/clang/lib/Format/FormatToken.cpp b/clang/lib/Format/FormatToken.cpp
index 60e428123d26d..a4e2acc922c0d 100644
--- a/clang/lib/Format/FormatToken.cpp
+++ b/clang/lib/Format/FormatToken.cpp
@@ -44,7 +44,7 @@ static SmallVector<StringRef> CppNonKeywordTypes = {
 bool FormatToken::isTypeName(const LangOptions &LangOpts) const {
   if (is(TT_TypeName) || Tok.isSimpleTypeSpecifier(LangOpts))
     return true;
-  return (LangOpts.CXXOperatorNames || LangOpts.C17) && is(tok::identifier) &&
+  return (LangOpts.CXXOperatorNames || LangOpts.C11) && is(tok::identifier) &&
          std::binary_search(CppNonKeywordTypes.begin(),
                             CppNonKeywordTypes.end(), TokenText);
 }
diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp
index 976c4d888e1fd..3e1a5c7df7f77 100644
--- a/clang/lib/Format/TokenAnnotator.cpp
+++ b/clang/lib/Format/TokenAnnotator.cpp
@@ -129,7 +129,6 @@ class AnnotatingParser {
       : Style(Style), Line(Line), CurrentToken(Line.First), AutoFound(false),
         IsCpp(Style.isCpp()), LangOpts(getFormattingLangOpts(Style)),
         Keywords(Keywords), Scopes(Scopes), TemplateDeclarationDepth(0) {
-    assert(IsCpp == (LangOpts.CXXOperatorNames || LangOpts.C17));
     Contexts.push_back(Context(tok::unknown, 1, /*IsExpression=*/false));
     resetTokenMetadata();
   }
@@ -3820,7 +3819,7 @@ static bool isFunctionDeclarationName(const LangOptions &LangOpts,
   };
 
   const auto *Next = Current.Next;
-  const bool IsCpp = LangOpts.CXXOperatorNames || LangOpts.C17;
+  const bool IsCpp = LangOpts.CXXOperatorNames || LangOpts.C11;
 
   // Find parentheses of parameter list.
   if (Current.is(tok::kw_operator)) {
diff --git a/clang/lib/Format/TokenAnnotator.h b/clang/lib/Format/TokenAnnotator.h
index c0c13941ef4f7..e4b94431e68b4 100644
--- a/clang/lib/Format/TokenAnnotator.h
+++ b/clang/lib/Format/TokenAnnotator.h
@@ -224,9 +224,7 @@ class TokenAnnotator {
 public:
   TokenAnnotator(const FormatStyle &Style, const AdditionalKeywords &Keywords)
       : Style(Style), IsCpp(Style.isCpp()),
-        LangOpts(getFormattingLangOpts(Style)), Keywords(Keywords) {
-    assert(IsCpp == (LangOpts.CXXOperatorNames || LangOpts.C17));
-  }
+        LangOpts(getFormattingLangOpts(Style)), Keywords(Keywords) {}
 
   /// Adapts the indent levels of comment lines to the indent of the
   /// subsequent line.
diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp
index 9a03e9409fcbc..2b348c926294e 100644
--- a/clang/lib/Format/UnwrappedLineParser.cpp
+++ b/clang/lib/Format/UnwrappedLineParser.cpp
@@ -167,9 +167,7 @@ UnwrappedLineParser::UnwrappedLineParser(
                        ? IG_Rejected
                        : IG_Inited),
       IncludeGuardToken(nullptr), FirstStartColumn(FirstStartColumn),
-      Macros(Style.Macros, SourceMgr, Style, Allocator, IdentTable) {
-  assert(IsCpp == (LangOpts.CXXOperatorNames || LangOpts.C17));
-}
+      Macros(Style.Macros, SourceMgr, Style, Allocator, IdentTable) {}
 
 void UnwrappedLineParser::reset() {
   PPBranchLevel = -1;
diff --git a/clang/unittests/Format/TokenAnnotatorTest.cpp b/clang/unittests/Format/TokenAnnotatorTest.cpp
index f1a6999cfdfb8..b7b8a21b726b6 100644
--- a/clang/unittests/Format/TokenAnnotatorTest.cpp
+++ b/clang/unittests/Format/TokenAnnotatorTest.cpp
@@ -3793,6 +3793,12 @@ TEST_F(TokenAnnotatorTest, AfterPPDirective) {
   EXPECT_TOKEN(Tokens[2], tok::minusminus, TT_AfterPPDirective);
 }
 
+TEST_F(TokenAnnotatorTest, UTF8StringLiteral) {
+  auto Tokens = annotate("return u8\"foo\";", getLLVMStyle(FormatStyle::LK_C));
+  ASSERT_EQ(Tokens.size(), 4u) << Tokens;
+  EXPECT_TOKEN(Tokens[1], tok::utf8_string_literal, TT_Unknown);
+}
+
 } // namespace
 } // namespace format
 } // namespace clang

[owenca]

Copied the entire getFormattingLangOpts() function from commit d71ee7d to resolve conflicts.

[mydeveloperday]

LGTM

[github-actions]

@owenca (or anyone else). If you would like to add a note about this fix in the release notes (completely optional). Please reply to this comment with a one or two sentence description of the fix. When you are done, please add the release:note label to this PR.