[clang-format][NFC] Handle language specific stuff at the top...

[HazardyKnusperkeks]

Summary

... of TokenAnnotator::splitPenalty. That is in my eyes a bit clearer in the workflow.

As a drive-by introduce (but not adapt anywhere else) isProto().

[owenpan]

clang/lib/Format/TokenAnnotator.cpp

3121

Otherwise, it wouldn't be NFC.

[HazardyKnusperkeks]

clang/lib/Format/TokenAnnotator.cpp

3121

It was Left == :: || Right == .

[owenpan]

LGTM

clang/lib/Format/TokenAnnotator.cpp

3121

It's NFC because we are still checking Right.is... below.

clang/include/clang/Format/Format.h

enum LanguageKind : int8_t {
     /// https://sci-hub.st/10.1109/IEEESTD.2018.8299595
     LK_Verilog
   };
   bool isCpp() const { return Language == LK_Cpp || Language == LK_ObjC; }
   bool isCSharp() const { return Language == LK_CSharp; }
   bool isJson() const { return Language == LK_Json; }
   bool isJavaScript() const { return Language == LK_JavaScript; }
   bool isVerilog() const { return Language == LK_Verilog; }
+  bool isProto() const { return Language == LK_Proto; }
 
   /// Language, this format style is targeted at.
   /// \version 3.5
   LanguageKind Language;
 
   /// Indentation logic for lambda bodies.
   enum LambdaBodyIndentationKind : int8_t {
     /// Align lambda body relative to the lambda signature. This is the default.

clang/lib/Format/TokenAnnotator.cpp

unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line,
                                       const FormatToken &Tok,
                                       bool InFunctionDecl) const {
   const FormatToken &Left = *Tok.Previous;
   const FormatToken &Right = Tok;
 
   if (Left.is(tok::semi))
     return 0;
 
+  // Language specific handling.
   if (Style.Language == FormatStyle::LK_Java) {
     if (Right.isOneOf(Keywords.kw_extends, Keywords.kw_throws))
       return 1;
     if (Right.is(Keywords.kw_implements))
       return 2;
     if (Left.is(tok::comma) && Left.NestingLevel == 0)
       return 3;
   } else if (Style.isJavaScript()) {
     if (Right.is(Keywords.kw_function) && Left.isNot(tok::comma))
       return 100;
     if (Left.is(TT_JsTypeColon))
       return 35;
     if ((Left.is(TT_TemplateString) && Left.TokenText.endswith("${")) ||
         (Right.is(TT_TemplateString) && Right.TokenText.startswith("}"))) {
       return 100;
     }
     // Prefer breaking call chains (".foo") over empty "{}", "[]" or "()".
     if (Left.opensScope() && Right.closesScope())
       return 200;
+  } else if (Style.isProto()) {
+    if (Right.is(tok::l_square))
+      return 1;
+    if (Right.is(tok::period))
+      return 500;
   }
 
   if (Right.is(tok::identifier) && Right.Next && Right.Next->is(TT_DictLiteral))
     return 1;
   if (Right.is(tok::l_square)) {
-    if (Style.Language == FormatStyle::LK_Proto)
-      return 1;
     if (Left.is(tok::r_square))
       return 200;
     // Slightly prefer formatting local lambda definitions like functions.
     if (Right.is(TT_LambdaLSquare) && Left.is(tok::equal))
       return 35;
     if (!Right.isOneOf(TT_ObjCMethodExpr, TT_LambdaLSquare,
                        TT_ArrayInitializerLSquare,
                        TT_DesignatedInitializerLSquare, TT_AttributeSquare)) {
       return 500;
     }
   }
 
-  if (Left.is(tok::coloncolon) ||
-      (Right.is(tok::period) && Style.Language == FormatStyle::LK_Proto)) {
+  if (Left.is(tok::coloncolon))
     return 500;
-  }
   if (Right.isOneOf(TT_StartOfName, TT_FunctionDeclarationName) ||
       Right.is(tok::kw_operator)) {
     if (Line.startsWith(tok::kw_for) && Right.PartOfMultiVariableDeclStmt)
       return 3;
     if (Left.is(TT_StartOfName))
       return 110;
     if (InFunctionDecl && Right.NestingLevel == 0)
       return Style.PenaltyReturnTypeOnItsOwnLine;