[clang-format] Handle goto labels preceded by C++11 attributes

[owenpan]

Summary

Fixes https://github.com/llvm/llvm-project/issues/64229.

clang/lib/Format/UnwrappedLineParser.cpp

if (Style.Language == FormatStyle::LK_TableGen &&
       FormatTok->is(tok::pp_include)) {
     nextToken();
     if (FormatTok->is(tok::string_literal))
       nextToken();
     addUnwrappedLine();
     return;
   }
 
-  if (Style.isVerilog()) {
+  if (Style.isCpp()) {
+    while (FormatTok->is(tok::l_square) && handleCppAttributes()) {
+    }
+  } else if (Style.isVerilog()) {
     if (Keywords.isVerilogStructuredProcedure(*FormatTok)) {
       parseForOrWhileLoop(/*HasParens=*/false);
       return;
     }
     if (FormatTok->isOneOf(Keywords.kw_foreach, Keywords.kw_repeat)) {
       parseForOrWhileLoop();
       return;
     }
case tok::identifier:
     if (Style.isCpp() && FormatTok->is(TT_StatementMacro)) {
       parseStatementMacro();
       return;
     }
     if (Style.isCpp() && FormatTok->is(TT_NamespaceMacro)) {
       parseNamespace();
       return;
     }
+    // In Verilog labels can be any expression, so we don't do them here.
+    if (!Style.isVerilog() && Tokens->peekNextToken()->is(tok::colon) &&
+        !Line->MustBeDeclaration) {
+      nextToken();
+      Line->Tokens.begin()->Tok->MustBreakBefore = true;
+      FormatTok->setFinalizedType(TT_GotoLabelColon);
+      parseLabel(!Style.IndentGotoLabels);
+      if (HasLabel)
+        *HasLabel = true;
+      return;
+    }
     // In all other cases, parse the declaration.
     break;
   default:
     break;
   }
   do {
     const FormatToken *Previous = FormatTok->Previous;
     switch (FormatTok->Tok.getKind()) {
case tok::identifier: {
         auto I = Line->Tokens.begin(), E = Line->Tokens.end();
         while (I != E && I->Tok->is(tok::comment))
           ++I;
         while (I != E && Style.isVerilog() && I->Tok->is(tok::hash))
           ++I;
         return I != E && (++I == E);
       };
       if (OneTokenSoFar()) {
-        // In Verilog labels can be any expression, so we don't do them here.
-        if (!Style.isVerilog() && FormatTok->is(tok::colon) &&
-            !Line->MustBeDeclaration) {
-          Line->Tokens.begin()->Tok->MustBreakBefore = true;
-          FormatTok->setFinalizedType(TT_GotoLabelColon);
-          parseLabel(!Style.IndentGotoLabels);
-          if (HasLabel)
-            *HasLabel = true;
-          return;
-        }
         // Recognize function-like macro usages without trailing semicolon as
         // well as free-standing macros like Q_OBJECT.
         bool FunctionLike = FormatTok->is(tok::l_paren);
         if (FunctionLike)
           parseParens();
 
         bool FollowedByNewline =
             CommentsBeforeNextToken.empty()

clang/unittests/Format/FormatTest.cpp

verifyFormat("{\n"
                "}");
   verifyFormat("{\n"
                "  some_code();\n"
                "test_label: {\n"
                "  some_other_code();\n"
                "  some_other_code();\n"
                "}\n"
                "}");
+  verifyFormat("{\n"
+               "L0:\n"
+               "[[foo]] L1:\n"
+               "[[bar]] [[baz]] L2:\n"
+               "  g();\n"
+               "}");
+  verifyFormat("{\n"
+               "[[foo]] L1: {\n"
+               "[[bar]] [[baz]] L2:\n"
+               "  g();\n"
+               "}\n"
+               "}");
+  verifyFormat("{\n"
+               "[[foo]] L1:\n"
+               "  f();\n"
+               "  {\n"
+               "  [[bar]] [[baz]] L2:\n"
+               "    g();\n"
+               "  }\n"
+               "}");
   FormatStyle Style = getLLVMStyle();
   Style.IndentGotoLabels = false;
   verifyFormat("void f() {\n"
                "  some_code();\n"
                "test_label:\n"
                "  some_other_code();\n"
                "  {\n"
                "    some_more_code();\n"
                "another_label:\n"
                "    some_more_code();\n"
                "  }\n"
                "}",
                Style);
   verifyFormat("{\n"
                "  some_code();\n"
                "test_label:\n"
                "  some_other_code();\n"
                "}",
                Style);
   verifyFormat("{\n"
                "  some_code();\n"
                "test_label:;\n"
                "  int i = 0;\n"
-               "}");
+               "}",
+               Style);
   verifyFormat("{\n"
                "  some_code();\n"
                "test_label: { some_other_code(); }\n"
                "}",
                Style);
+  verifyFormat("{\n"
+               "[[foo]] L1:\n"
+               "  f();\n"
+               "  {\n"
+               "[[bar]] [[baz]] L2:\n"
+               "    g();\n"
+               "  }\n"
+               "}",
+               Style);
   // The opening brace may either be on the same unwrapped line as the colon or
   // on a separate one. The formatter should recognize both.
   Style = getLLVMStyle();
   Style.BreakBeforeBraces = FormatStyle::BraceBreakingStyle::BS_Allman;
   verifyFormat("{\n"
                "  some_code();\n"
                "test_label:\n"
                "{\n"
                "  some_other_code();\n"
                "}\n"
                "}",
                Style);
+  verifyFormat("{\n"
+               "[[foo]] L1:\n"
+               "{\n"
+               "[[bar]] [[baz]] L2:\n"
+               "  g();\n"
+               "}\n"
+               "}",
+               Style);
 }
 
 TEST_F(FormatTest, MultiLineControlStatements) {
   FormatStyle Style = getLLVMStyleWithColumns(20);
   Style.BreakBeforeBraces = FormatStyle::BraceBreakingStyle::BS_Custom;
   Style.BraceWrapping.AfterControlStatement = FormatStyle::BWACS_MultiLine;
   // Short lines should keep opening brace on same line.
   EXPECT_EQ("if (foo) {\n"