sstwcw updated this revision to Diff 416010.
sstwcw edited the summary of this revision.
sstwcw added a comment.

Add some test cases and use a separate function for the common parts.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121754/new/

https://reviews.llvm.org/D121754

Files:
  clang/lib/Format/TokenAnnotator.cpp
  clang/unittests/Format/FormatTest.cpp

Index: clang/unittests/Format/FormatTest.cpp
===================================================================
--- clang/unittests/Format/FormatTest.cpp
+++ clang/unittests/Format/FormatTest.cpp
@@ -9754,6 +9754,9 @@
   verifyFormat("if (!(a->f())) {\n}");
   verifyFormat("if (!+i) {\n}");
   verifyFormat("~&a;");
+  verifyFormat("for (x = 0; -10 < x; --x) {\n}");
+  verifyFormat("sizeof -x");
+  verifyFormat("sizeof +x");
 
   verifyFormat("a-- > b;");
   verifyFormat("b ? -a : c;");
Index: clang/lib/Format/TokenAnnotator.cpp
===================================================================
--- clang/lib/Format/TokenAnnotator.cpp
+++ clang/lib/Format/TokenAnnotator.cpp
@@ -2129,6 +2129,45 @@
     return true;
   }
 
+  /// Returns true if the token is used as a unary operator.
+  bool determineUnaryOperatorByUsage(const FormatToken &Tok) {
+    const FormatToken *PrevToken = Tok.getPreviousNonComment();
+    if (!PrevToken)
+      return true;
+
+    // These keywords are deliberately not included here. They are either
+    // included in determineStarAmpUsage or determinePlusMinusCaretUsage.
+    // case - In a switch expression, the condition shall be of integral type,
+    //   enumeration type, or class type, and the case label contains a constant
+    //   expression. We were unable to come up with a case where the case
+    //   keyword is followed by a star or amp.
+    // @ - It may be followed by a unary `-` in Objective-C literals. We don't
+    //   know how they can be followed by a star or amp.
+    // co_await, delete - It doesn't make sense to have them followed by a unary
+    //   `+` or `-`.
+    if (PrevToken->isOneOf(TT_ConditionalExpr, tok::l_paren, tok::comma,
+                           tok::colon, tok::semi, tok::equal, tok::question,
+                           tok::l_square, tok::l_brace, tok::kw_co_return,
+                           tok::kw_co_yield, tok::kw_return, tok::kw_throw))
+      return true;
+
+    // We put sizeof here instead of only in determineStarAmpUsage. In the cases
+    // where the unary `+` operator is overloaded, it is reasonable to write
+    // things like `sizeof +x`. Like commit 446d6ec996c6c3.
+    if (PrevToken->is(tok::kw_sizeof))
+      return true;
+
+    // A sequence of leading unary operators.
+    if (PrevToken->isOneOf(TT_CastRParen, TT_UnaryOperator))
+      return true;
+
+    // There can't be two consecutive binary operators.
+    if (PrevToken->is(TT_BinaryOperator))
+      return true;
+
+    return false;
+  }
+
   /// Return the type of the given token assuming it is * or &.
   TokenType determineStarAmpUsage(const FormatToken &Tok, bool IsExpression,
                                   bool InTemplateArgument) {
@@ -2160,12 +2199,10 @@
     if (PrevToken->is(tok::r_paren) && PrevToken->is(TT_TypeDeclarationParen))
       return TT_PointerOrReference;
 
-    if (PrevToken->isOneOf(tok::l_paren, tok::l_square, tok::l_brace,
-                           tok::comma, tok::semi, tok::kw_return, tok::colon,
-                           tok::kw_co_return, tok::kw_co_await,
-                           tok::kw_co_yield, tok::equal, tok::kw_delete,
-                           tok::kw_sizeof, tok::kw_throw, TT_BinaryOperator,
-                           TT_ConditionalExpr, TT_UnaryOperator, TT_CastRParen))
+    if (determineUnaryOperatorByUsage(Tok))
+      return TT_UnaryOperator;
+
+    if (PrevToken->isOneOf(tok::kw_co_await, tok::kw_delete))
       return TT_UnaryOperator;
 
     if (NextToken->is(tok::l_square) && NextToken->isNot(TT_LambdaLSquare))
@@ -2208,23 +2245,14 @@
   }
 
   TokenType determinePlusMinusCaretUsage(const FormatToken &Tok) {
+    if (determineUnaryOperatorByUsage(Tok))
+      return TT_UnaryOperator;
+
     const FormatToken *PrevToken = Tok.getPreviousNonComment();
     if (!PrevToken)
       return TT_UnaryOperator;
 
-    if (PrevToken->isOneOf(TT_CastRParen, TT_UnaryOperator))
-      // This must be a sequence of leading unary operators.
-      return TT_UnaryOperator;
-
-    // Use heuristics to recognize unary operators.
-    if (PrevToken->isOneOf(tok::equal, tok::l_paren, tok::comma, tok::l_square,
-                           tok::question, tok::colon, tok::kw_return,
-                           tok::kw_case, tok::at, tok::l_brace, tok::kw_throw,
-                           tok::kw_co_return, tok::kw_co_yield))
-      return TT_UnaryOperator;
-
-    // There can't be two consecutive binary operators.
-    if (PrevToken->is(TT_BinaryOperator))
+    if (PrevToken->isOneOf(tok::at, tok::kw_case))
       return TT_UnaryOperator;
 
     // Fall back to marking the token as binary operator.
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to