[clang] [clang-format] Correctly parse C++11 attributes in enum specifiers (PR #85498)

[Owen Pan via cfe-commits]

https://github.com/owenca created https://github.com/llvm/llvm-project/pull/85498

Fixes #85476.

>From 89c06a9acfebffa4f9e65c6d683c3c46774edc88 Mon Sep 17 00:00:00 2001
From: Owen Pan <owenpiano at gmail.com>
Date: Fri, 15 Mar 2024 22:14:01 -0700
Subject: [PATCH] [clang-format] Correctly parse C++11 attributes in enum
 specifiers

Fixes #85476.
---
 clang/lib/Format/UnwrappedLineParser.cpp | 15 +++++++++------
 clang/unittests/Format/FormatTest.cpp    | 21 +++++++++++++++++++++
 2 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp
index a1f6ce05e45ebc..2b893f7abe4023 100644
--- a/clang/lib/Format/UnwrappedLineParser.cpp
+++ b/clang/lib/Format/UnwrappedLineParser.cpp
@@ -1224,7 +1224,6 @@ void UnwrappedLineParser::parsePPUnknown() {
 static bool tokenCanStartNewLine(const FormatToken &Tok) {
   // Semicolon can be a null-statement, l_square can be a start of a macro or
   // a C++11 attribute, but this doesn't seem to be common.
-  assert(Tok.isNot(TT_AttributeSquare));
   return !Tok.isOneOf(tok::semi, tok::l_brace,
                       // Tokens that can only be used as binary operators and a
                       // part of overloaded operator names.
@@ -3712,14 +3711,19 @@ bool UnwrappedLineParser::parseEnum() {
   if (Style.Language == FormatStyle::LK_Proto && FormatTok->is(tok::equal))
     return false;
 
-  // Eat up enum class ...
-  if (FormatTok->isOneOf(tok::kw_class, tok::kw_struct))
-    nextToken();
+  if (IsCpp) {
+    // Eat up enum class ...
+    if (FormatTok->isOneOf(tok::kw_class, tok::kw_struct))
+      nextToken();
+    while (FormatTok->is(tok::l_square))
+      if (!handleCppAttributes())
+        return false;
+  }
 
   while (FormatTok->Tok.getIdentifierInfo() ||
          FormatTok->isOneOf(tok::colon, tok::coloncolon, tok::less,
                             tok::greater, tok::comma, tok::question,
-                            tok::l_square, tok::r_square)) {
+                            tok::l_square)) {
     if (Style.isVerilog()) {
       FormatTok->setFinalizedType(TT_VerilogDimensionedTypeName);
       nextToken();
@@ -3732,7 +3736,6 @@ bool UnwrappedLineParser::parseEnum() {
     // We can have macros or attributes in between 'enum' and the enum name.
     if (FormatTok->is(tok::l_paren))
       parseParens();
-    assert(FormatTok->isNot(TT_AttributeSquare));
     if (FormatTok->is(tok::identifier)) {
       nextToken();
       // If there are two identifiers in a row, this is likely an elaborate
diff --git a/clang/unittests/Format/FormatTest.cpp b/clang/unittests/Format/FormatTest.cpp
index fc367a7a5a8981..add92d3e111089 100644
--- a/clang/unittests/Format/FormatTest.cpp
+++ b/clang/unittests/Format/FormatTest.cpp
@@ -3802,6 +3802,27 @@ TEST_F(FormatTest, FormatsEnum) {
                "  // Comment 2\n"
                "  TWO,\n"
                "};");
+  verifyFormat("enum [[clang::enum_extensibility(open)]] E {\n"
+               "  // Comment 1\n"
+               "  ONE,\n"
+               "  // Comment 2\n"
+               "  TWO\n"
+               "};");
+  verifyFormat("enum [[nodiscard]] [[clang::enum_extensibility(open)]] E {\n"
+               "  // Comment 1\n"
+               "  ONE,\n"
+               "  // Comment 2\n"
+               "  TWO\n"
+               "};");
+  verifyFormat("enum [[clang::enum_extensibility(open)]] E { // foo\n"
+               "  A,\n"
+               "  // bar\n"
+               "  B\n"
+               "};",
+               "enum [[clang::enum_extensibility(open)]] E{// foo\n"
+               "                                           A,\n"
+               "                                           // bar\n"
+               "                                           B};");
 
   // Not enums.
   verifyFormat("enum X f() {\n"