[ClangFormat] Fix formatting bugs. (#76245)

1. There are multiple calls to addFakeParenthesis; move the guard to not
   assign fake parenthesis into the function to make sure we cover all
   calls.
2. MustBreakBefore can be set on a token in two cases: either during
   unwrapped line parsing, or later, during token annotation. We must
   keep the latter, but reset the former.
3. Added a test to document that the intended behavior of preferring not
   to break between a return type and a function identifier.
   For example, with MOCK_METHOD(r, n, a)=r n a, the code
   MOCK_METHOD(void, f, (int a, int b)) should prefer the same breaks as
   the expanded void f(int a, int b).

Author: r4nt

clang/lib/Format/FormatToken.h

@@ -275,14 +275,15 @@ class AnnotatedLine;
 struct FormatToken {
   FormatToken()
       : HasUnescapedNewline(false), IsMultiline(false), IsFirst(false),
-        MustBreakBefore(false), IsUnterminatedLiteral(false),
-        CanBreakBefore(false), ClosesTemplateDeclaration(false),
-        StartsBinaryExpression(false), EndsBinaryExpression(false),
-        PartOfMultiVariableDeclStmt(false), ContinuesLineCommentSection(false),
-        Finalized(false), ClosesRequiresClause(false),
-        EndsCppAttributeGroup(false), BlockKind(BK_Unknown),
-        Decision(FD_Unformatted), PackingKind(PPK_Inconclusive),
-        TypeIsFinalized(false), Type(TT_Unknown) {}
+        MustBreakBefore(false), MustBreakBeforeFinalized(false),
+        IsUnterminatedLiteral(false), CanBreakBefore(false),
+        ClosesTemplateDeclaration(false), StartsBinaryExpression(false),
+        EndsBinaryExpression(false), PartOfMultiVariableDeclStmt(false),
+        ContinuesLineCommentSection(false), Finalized(false),
+        ClosesRequiresClause(false), EndsCppAttributeGroup(false),
+        BlockKind(BK_Unknown), Decision(FD_Unformatted),
+        PackingKind(PPK_Inconclusive), TypeIsFinalized(false),
+        Type(TT_Unknown) {}
 
   /// The \c Token.
   Token Tok;
@@ -318,6 +319,10 @@ struct FormatToken {
   /// before the token.
   unsigned MustBreakBefore : 1;
 
+  /// Whether MustBreakBefore is finalized during parsing and must not
+  /// be reset between runs.
+  unsigned MustBreakBeforeFinalized : 1;
+
   /// Set to \c true if this token is an unterminated literal.
   unsigned IsUnterminatedLiteral : 1;
 
@@ -416,10 +421,14 @@ struct FormatToken {
   /// to another one please use overwriteFixedType, or even better remove the
   /// need to reassign the type.
   void setFinalizedType(TokenType T) {
+    if (MacroCtx && MacroCtx->Role == MR_UnexpandedArg)
+      return;
     Type = T;
     TypeIsFinalized = true;
   }
   void overwriteFixedType(TokenType T) {
+    if (MacroCtx && MacroCtx->Role == MR_UnexpandedArg)
+      return;
     TypeIsFinalized = false;
     setType(T);
   }

clang/lib/Format/TokenAnnotator.cpp

@@ -2769,13 +2769,6 @@ class ExpressionParser {
       // Consume operators with higher precedence.
       parse(Precedence + 1);
 
-      // Do not assign fake parenthesis to tokens that are part of an
-      // unexpanded macro call. The line within the macro call contains
-      // the parenthesis and commas, and we will not find operators within
-      // that structure.
-      if (Current && Current->MacroParent)
-        break;
-
       int CurrentPrecedence = getCurrentPrecedence();
 
       if (Precedence == CurrentPrecedence && Current &&
@@ -2919,6 +2912,13 @@ class ExpressionParser {
 
   void addFakeParenthesis(FormatToken *Start, prec::Level Precedence,
                           FormatToken *End = nullptr) {
+    // Do not assign fake parenthesis to tokens that are part of an
+    // unexpanded macro call. The line within the macro call contains
+    // the parenthesis and commas, and we will not find operators within
+    // that structure.
+    if (Start->MacroParent)
+      return;
+
     Start->FakeLParens.push_back(Precedence);
     if (Precedence > prec::Unknown)
       Start->StartsBinaryExpression = true;

clang/lib/Format/UnwrappedLineFormatter.cpp

@@ -954,13 +954,15 @@ static void markFinalized(FormatToken *Tok) {
       // will be modified as unexpanded arguments (as part of the macro call
       // formatting) in the next pass.
       Tok->MacroCtx->Role = MR_UnexpandedArg;
-      // Reset whether spaces are required before this token, as that is context
-      // dependent, and that context may change when formatting the macro call.
-      // For example, given M(x) -> 2 * x, and the macro call M(var),
-      // the token 'var' will have SpacesRequiredBefore = 1 after being
+      // Reset whether spaces or a line break are required before this token, as
+      // that is context dependent, and that context may change when formatting
+      // the macro call.  For example, given M(x) -> 2 * x, and the macro call
+      // M(var), the token 'var' will have SpacesRequiredBefore = 1 after being
       // formatted as part of the expanded macro, but SpacesRequiredBefore = 0
       // for its position within the macro call.
       Tok->SpacesRequiredBefore = 0;
+      if (!Tok->MustBreakBeforeFinalized)
+        Tok->MustBreakBefore = 0;
     } else {
       Tok->Finalized = true;
     }

clang/lib/Format/UnwrappedLineParser.cpp

@@ -4675,6 +4675,7 @@ void UnwrappedLineParser::readToken(int LevelDifference) {
         conditionalCompilationEnd();
       FormatTok = Tokens->getNextToken();
       FormatTok->MustBreakBefore = true;
+      FormatTok->MustBreakBeforeFinalized = true;
     }
 
     auto IsFirstNonCommentOnLine = [](bool FirstNonCommentOnLine,
@@ -4891,6 +4892,7 @@ void UnwrappedLineParser::pushToken(FormatToken *Tok) {
   Line->Tokens.push_back(UnwrappedLineNode(Tok));
   if (MustBreakBeforeNextToken) {
     Line->Tokens.back().Tok->MustBreakBefore = true;
+    Line->Tokens.back().Tok->MustBreakBeforeFinalized = true;
     MustBreakBeforeNextToken = false;
   }
 }

clang/unittests/Format/FormatTestMacroExpansion.cpp

@@ -255,6 +255,38 @@ TEST_F(FormatTestMacroExpansion,
                          Style);
 }
 
+TEST_F(FormatTestMacroExpansion, CommaAsOperator) {
+  FormatStyle Style = getGoogleStyleWithColumns(42);
+  Style.Macros.push_back("MACRO(a, b, c)=a=(b); if(x) c");
+  verifyFormat("MACRO(auto a,\n"
+               "      looooongfunction(first, second,\n"
+               "                       third),\n"
+               "      fourth);",
+               Style);
+}
+
+TEST_F(FormatTestMacroExpansion, ForcedBreakDiffers) {
+  FormatStyle Style = getGoogleStyleWithColumns(40);
+  Style.Macros.push_back("MACRO(a, b)=a=(b)");
+  verifyFormat("//\n"
+               "MACRO(const type variable,\n"
+               "      functtioncall(\n"
+               "          first, longsecondarg, third));",
+               Style);
+}
+
+TEST_F(FormatTestMacroExpansion,
+       PreferNotBreakingBetweenReturnTypeAndFunction) {
+  FormatStyle Style = getGoogleStyleWithColumns(22);
+  Style.Macros.push_back("MOCK_METHOD(r, n, a)=r n a");
+  // In the expanded code, we parse a full function signature, and afterwards
+  // know that we prefer not to break before the function name.
+  verifyFormat("MOCK_METHOD(\n"
+               "    type, variable,\n"
+               "    (type));",
+               Style);
+}
+
 } // namespace
 } // namespace test
 } // namespace format