[clang-format] Allow configuring list of function-like macros that resolve to a type

Summary:
Adds a `TypenameMacros` configuration option that causes certain identifiers to be handled in a way similar to `typeof()`.

This is enough to:
- Prevent misinterpreting declarations of pointers to such types as expressions (`STACK_OF(int) * foo` -> `STACK_OF(int) *foo`),
- Avoid surprising line breaks in variable/struct field declarations (`STACK_OF(int)\nfoo;` -> `STACK_OF(int) foo;`, see https://bugs.llvm.org/show_bug.cgi?id=30353).

Reviewers: Typz, krasimir, djasper

Reviewed By: Typz

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D57184

llvm-svn: 361986

clang/docs/ClangFormatStyleOptions.rst

@@ -1367,6 +1367,24 @@ the configuration (without a prefix: ``Auto``).
 
   For example: BOOST_FOREACH.
 
+**TypenameMacros** (``std::vector<std::string>``)
+  A vector of macros that should be interpreted as type declarations
+  instead of as function calls.
+
+  These are expected to be macros of the form:
+
+  .. code-block: c++
+
+    STACK_OF(...)
+
+  In the .clang-format configuration file, this can be configured like:
+
+  .. code-block: yaml
+
+    TypenameMacros: ['STACK_OF', 'LIST']
+
+  For example: OpenSSL STACK_OF, BSD LIST_ENTRY.
+
 **IncludeBlocks** (``IncludeBlocksStyle``)
   Dependent on the value, multiple ``#include`` blocks can be sorted
   as one and divided based on category.

clang/include/clang/Format/Format.h

@@ -1160,6 +1160,22 @@ struct FormatStyle {
   /// For example: BOOST_FOREACH.
   std::vector<std::string> ForEachMacros;
 
+  /// \brief A vector of macros that should be interpreted as type declarations
+  /// instead of as function calls.
+  ///
+  /// These are expected to be macros of the form:
+  /// \code
+  ///   STACK_OF(...)
+  /// \endcode
+  ///
+  /// In the .clang-format configuration file, this can be configured like:
+  /// \code{.yaml}
+  ///   TypenameMacros: ['STACK_OF', 'LIST']
+  /// \endcode
+  ///
+  /// For example: OpenSSL STACK_OF, BSD LIST_ENTRY.
+  std::vector<std::string> TypenameMacros;
+
   /// A vector of macros that should be interpreted as complete
   /// statements.
   ///
@@ -1952,7 +1968,8 @@ struct FormatStyle {
            SpacesInParentheses == R.SpacesInParentheses &&
            SpacesInSquareBrackets == R.SpacesInSquareBrackets &&
            Standard == R.Standard && TabWidth == R.TabWidth &&
-           StatementMacros == R.StatementMacros && UseTab == R.UseTab;
+           StatementMacros == R.StatementMacros && UseTab == R.UseTab &&
+           TypenameMacros == R.TypenameMacros;
   }
 
   llvm::Optional<FormatStyle> GetLanguageStyle(LanguageKind Language) const;

clang/lib/Format/Format.cpp

@@ -505,6 +505,7 @@ template <> struct MappingTraits<FormatStyle> {
     IO.mapOptional("Standard", Style.Standard);
     IO.mapOptional("StatementMacros", Style.StatementMacros);
     IO.mapOptional("TabWidth", Style.TabWidth);
+    IO.mapOptional("TypenameMacros", Style.TypenameMacros);
     IO.mapOptional("UseTab", Style.UseTab);
   }
 };

clang/lib/Format/FormatToken.h

@@ -96,6 +96,7 @@ namespace format {
   TYPE(TrailingAnnotation)                                                     \
   TYPE(TrailingReturnArrow)                                                    \
   TYPE(TrailingUnaryOperator)                                                  \
+  TYPE(TypenameMacro)                                                          \
   TYPE(UnaryOperator)                                                          \
   TYPE(CSharpStringLiteral)                                                    \
   TYPE(CSharpNullCoalescing)                                                   \

clang/lib/Format/FormatTokenLexer.cpp

@@ -39,6 +39,8 @@ FormatTokenLexer::FormatTokenLexer(const SourceManager &SourceMgr, FileID ID,
     Macros.insert({&IdentTable.get(ForEachMacro), TT_ForEachMacro});
   for (const std::string &StatementMacro : Style.StatementMacros)
     Macros.insert({&IdentTable.get(StatementMacro), TT_StatementMacro});
+  for (const std::string &TypenameMacro : Style.TypenameMacros)
+    Macros.insert({&IdentTable.get(TypenameMacro), TT_TypenameMacro});
 }
 
 ArrayRef<FormatToken *> FormatTokenLexer::lex() {

clang/lib/Format/TokenAnnotator.cpp

@@ -1194,11 +1194,12 @@ private:
 
     // Reset token type in case we have already looked at it and then
     // recovered from an error (e.g. failure to find the matching >).
-    if (!CurrentToken->isOneOf(
-            TT_LambdaLSquare, TT_LambdaLBrace, TT_ForEachMacro,
-            TT_FunctionLBrace, TT_ImplicitStringLiteral, TT_InlineASMBrace,
-            TT_JsFatArrow, TT_LambdaArrow, TT_OverloadedOperator,
-            TT_RegexLiteral, TT_TemplateString, TT_ObjCStringLiteral))
+    if (!CurrentToken->isOneOf(TT_LambdaLSquare, TT_LambdaLBrace,
+                               TT_ForEachMacro, TT_TypenameMacro,
+                               TT_FunctionLBrace, TT_ImplicitStringLiteral,
+                               TT_InlineASMBrace, TT_JsFatArrow, TT_LambdaArrow,
+                               TT_OverloadedOperator, TT_RegexLiteral,
+                               TT_TemplateString, TT_ObjCStringLiteral))
       CurrentToken->Type = TT_Unknown;
     CurrentToken->Role.reset();
     CurrentToken->MatchingParen = nullptr;
@@ -1416,6 +1417,7 @@ private:
           if (AfterParen->Tok.isNot(tok::caret)) {
             if (FormatToken *BeforeParen = Current.MatchingParen->Previous)
               if (BeforeParen->is(tok::identifier) &&
+                  !BeforeParen->is(TT_TypenameMacro) &&
                   BeforeParen->TokenText == BeforeParen->TokenText.upper() &&
                   (!BeforeParen->Previous ||
                    BeforeParen->Previous->ClosesTemplateDeclaration))
@@ -1667,7 +1669,8 @@ private:
       FormatToken *TokenBeforeMatchingParen =
           PrevToken->MatchingParen->getPreviousNonComment();
       if (TokenBeforeMatchingParen &&
-          TokenBeforeMatchingParen->isOneOf(tok::kw_typeof, tok::kw_decltype))
+          TokenBeforeMatchingParen->isOneOf(tok::kw_typeof, tok::kw_decltype,
+                                            TT_TypenameMacro))
         return TT_PointerOrReference;
     }
 
@@ -2527,7 +2530,8 @@ bool TokenAnnotator::spaceRequiredBetween(const AnnotatedLine &Line,
       FormatToken *TokenBeforeMatchingParen =
           Left.MatchingParen->getPreviousNonComment();
       if (!TokenBeforeMatchingParen ||
-          !TokenBeforeMatchingParen->isOneOf(tok::kw_typeof, tok::kw_decltype))
+          !TokenBeforeMatchingParen->isOneOf(tok::kw_typeof, tok::kw_decltype,
+                                             TT_TypenameMacro))
         return true;
     }
     return (Left.Tok.isLiteral() ||

clang/unittests/Format/FormatTest.cpp

@@ -13545,6 +13545,35 @@ TEST_F(FormatTest, GuessLanguageWithChildLines) {
       guessLanguage("foo.h", "#define FOO ({ foo(); ({ NSString *s; }) })"));
 }
 
+TEST_F(FormatTest, TypenameMacros) {
+  std::vector<std::string> TypenameMacros = {"STACK_OF", "LIST", "TAILQ_ENTRY"};
+
+  // Test case reported in https://bugs.llvm.org/show_bug.cgi?id=30353
+  FormatStyle Google = getGoogleStyleWithColumns(0);
+  Google.TypenameMacros = TypenameMacros;
+  verifyFormat("struct foo {\n"
+               "  int bar;\n"
+               "  TAILQ_ENTRY(a) bleh;\n"
+               "};", Google);
+
+  FormatStyle Macros = getLLVMStyle();
+  Macros.TypenameMacros = TypenameMacros;
+
+  verifyFormat("STACK_OF(int) a;", Macros);
+  verifyFormat("STACK_OF(int) *a;", Macros);
+  verifyFormat("STACK_OF(int const *) *a;", Macros);
+  verifyFormat("STACK_OF(int *const) *a;", Macros);
+  verifyFormat("STACK_OF(int, string) a;", Macros);
+  verifyFormat("STACK_OF(LIST(int)) a;", Macros);
+  verifyFormat("STACK_OF(LIST(int)) a, b;", Macros);
+  verifyFormat("for (LIST(int) *a = NULL; a;) {\n}", Macros);
+  verifyFormat("STACK_OF(int) f(LIST(int) *arg);", Macros);
+
+  Macros.PointerAlignment = FormatStyle::PAS_Left;
+  verifyFormat("STACK_OF(int)* a;", Macros);
+  verifyFormat("STACK_OF(int*)* a;", Macros);
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang