[clang-format] Support text proto extensions

[krasimir]

Summary

This adds support for text proto extensions, like:

msg {
  [type.type/ext] {
    key: value
  }
}

[djasper]

unittests/Format/FormatTestTextProto.cpp

317

It might be useful to attach a test case for what happens if the "[...]" does not fit on one line. I don't even know how I would format that, but it seems important to know and not accidentally modify the behavior.

[krasimir]

• Add tests with long [...]

[krasimir]

unittests/Format/FormatTestTextProto.cpp

317

I added some tests. The current behavior seems reasonable.

[djasper]

Cool, thanks.

lib/Format/ContinuationIndenter.cpp

if (PreviousNonComment && PreviousNonComment->is(TT_CtorInitializerColon) &&
       Style.BreakConstructorInitializers == FormatStyle::BCIS_AfterColon)
     return State.Stack.back().Indent;
   if (NextNonComment->isOneOf(TT_CtorInitializerColon, TT_InheritanceColon,
                               TT_InheritanceComma))
     return State.FirstIndent + Style.ConstructorInitializerIndentWidth;
   if (Previous.is(tok::r_paren) && !Current.isBinaryOperator() &&
       !Current.isOneOf(tok::colon, tok::comment))
     return ContinuationIndent;
+  if (Current.is(TT_ProtoExtensionLSquare))
+    return State.Stack.back().Indent;
   if (State.Stack.back().Indent == State.FirstIndent && PreviousNonComment &&
       PreviousNonComment->isNot(tok::r_brace))
     // Ensure that we fall back to the continuation indent width instead of
     // just flushing continuations left.
     return State.Stack.back().Indent + Style.ContinuationIndentWidth;
   return State.Stack.back().Indent;
 }
 

lib/Format/FormatToken.h

#define LIST_TOKEN_TYPES                                                       \
   TYPE(RangeBasedForLoopColon)                                                 \
   TYPE(RegexLiteral)                                                           \
   TYPE(SelectorName)                                                           \
   TYPE(StartOfName)                                                            \
   TYPE(StructuredBindingLSquare)                                               \
   TYPE(TemplateCloser)                                                         \
   TYPE(TemplateOpener)                                                         \
   TYPE(TemplateString)                                                         \
+  TYPE(ProtoExtensionLSquare)                                                  \
   TYPE(TrailingAnnotation)                                                     \
   TYPE(TrailingReturnArrow)                                                    \
   TYPE(TrailingUnaryOperator)                                                  \
   TYPE(UnaryOperator)                                                          \
   TYPE(Unknown)
 
 enum TokenType {
 #define TYPE(X) TT_##X,

lib/Format/TokenAnnotator.cpp

if (Left->isCppStructuredBinding(Style)) {
         Left->Type = TT_JsComputedPropertyName;
       } else if (Style.isCpp() && Contexts.back().ContextKind == tok::l_brace &&
                  Parent && Parent->isOneOf(tok::l_brace, tok::comma)) {
         Left->Type = TT_DesignatedInitializerLSquare;
       } else if (CurrentToken->is(tok::r_square) && Parent &&
                  Parent->is(TT_TemplateCloser)) {
         Left->Type = TT_ArraySubscriptLSquare;
       } else if (Style.Language == FormatStyle::LK_Proto ||
-                 (!CppArrayTemplates && Parent &&
-                  Parent->isOneOf(TT_BinaryOperator, TT_TemplateCloser, tok::at,
-                                  tok::comma, tok::l_paren, tok::l_square,
-                                  tok::question, tok::colon, tok::kw_return,
-                                  // Should only be relevant to JavaScript:
-                                  tok::kw_default))) {
+                 Style.Language == FormatStyle::LK_TextProto) {
+        // Square braces in LK_Proto can either be message field attributes:
+        //
+        // optional Aaa aaa = 1 [
+        //   (aaa) = aaa
+        // ];
+        //
+        // or text proto extensions (in options):
+        //
+        // option (Aaa.options) = {
+        //   [type.type/type] {
+        //     key: value
+        //   }
+        // }
+        //
+        // In the first case we want to spread the contents inside the square
+        // braces; in the second we want to keep them inline.
+        Left->Type = TT_ArrayInitializerLSquare;
+        if (!Left->endsSequence(tok::l_square, tok::numeric_constant,
+                                tok::equal)) {
+          Left->Type = TT_ProtoExtensionLSquare;
+          BindingIncrease = 10;
+        }
+      } else if (!CppArrayTemplates && Parent &&
+                                 tok::kw_default)) {
         Left->Type = TT_ArrayInitializerLSquare;
       } else {
         BindingIncrease = 10;
         Left->Type = TT_ArraySubscriptLSquare;
       }
     }
 
     ScopedContextCreator ContextCreator(*this, tok::l_square, BindingIncrease);
if (Right.is(tok::period) &&
         Left.isOneOf(Keywords.kw_optional, Keywords.kw_required,
                      Keywords.kw_repeated, Keywords.kw_extend))
       return true;
     if (Right.is(tok::l_paren) &&
         Left.isOneOf(Keywords.kw_returns, Keywords.kw_option))
       return true;
     if (Right.isOneOf(tok::l_brace, tok::less) && Left.is(TT_SelectorName))
       return true;
+    // Slashes occur in text protocol extension syntax: [type/type] { ... }.
+    if (Left.is(tok::slash) || Right.is(tok::slash))
+      return false;
+    if (Left.MatchingParen && Left.MatchingParen->is(TT_ProtoExtensionLSquare) &&
+        Right.isOneOf(tok::l_brace, tok::less))
+      return !Style.Cpp11BracedListStyle;
   } else if (Style.Language == FormatStyle::LK_JavaScript) {
     if (Left.is(TT_JsFatArrow))
       return true;
     // for await ( ...
     if (Right.is(tok::l_paren) && Left.is(Keywords.kw_await) && Left.Previous &&
         Left.Previous->is(tok::kw_for))
       return true;
     if (Left.is(Keywords.kw_async) && Right.is(tok::l_paren) &&
bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line,
 
   if ((Style.Language == FormatStyle::LK_Java ||
        Style.Language == FormatStyle::LK_JavaScript) &&
       Left.is(TT_LeadingJavaAnnotation) &&
       Right.isNot(TT_LeadingJavaAnnotation) && Right.isNot(tok::l_paren) &&
       (Line.Last->is(tok::l_brace) || Style.BreakAfterJavaFieldAnnotations))
     return true;
 
+  if (Right.is(TT_ProtoExtensionLSquare))
+    return true;
+
   return false;
 }
 
 bool TokenAnnotator::canBreakBefore(const AnnotatedLine &Line,
                                     const FormatToken &Right) {
   const FormatToken &Left = *Right.Previous;
 
   // Language-specific stuff.

unittests/Format/FormatTestProto.cpp

TEST_F(FormatTestProto, KeepsLongStringLiteralsOnSameLine) {
   verifyFormat(
       "option (MyProto.options) = {\n"
       "  foo: {\n"
       "    text: \"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaasaaaaaaaa\"\n"
       "  }\n"
       "}");
 }
 
+TEST_F(FormatTestProto, FormatsOptionsExtensions) {
+  verifyFormat("option (MyProto.options) = {\n"
+               "  msg_field: { field_d: 123 }\n"
+               "  [ext.t/u] { key: value }\n"
+               "  key: value\n"
+               "  [t.u/v] <\n"
+               "    [ext] { key: value }\n"
+               "  >\n"
+               "};");
+}
+
 } // end namespace tooling
 } // end namespace clang

unittests/Format/FormatTestTextProto.cpp

 }
 
 TEST_F(FormatTestTextProto, KeepsLongStringLiteralsOnSameLine) {
   verifyFormat(
       "foo: {\n"
       "  text: \"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaasaaaaaaaaaa\"\n"
       "}");
 }
+
+TEST_F(FormatTestTextProto, FormatsExtensions) {
+  verifyFormat("[type] { key: value }");
+  verifyFormat("[type] {\n"
+               "  keyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy: value\n"
+               "}");
+  verifyFormat("[type.type] { key: value }");
+  verifyFormat("[type.type] < key: value >");
+  verifyFormat("[type.type/type.type] { key: value }");
+  verifyFormat("msg {\n"
+               "  [type.type] { key: value }\n"
+               "}");
+  verifyFormat("msg {\n"
+               "  [type.type] {\n"
+               "    keyyyyyyyyyyyyyy: valuuuuuuuuuuuuuuuuuuuuuuuuue\n"
+               "  }\n"
+               "}");
+  verifyFormat("key: value\n"
+               "[a.b] { key: value }");
+  verifyFormat("msg: <\n"
+               "  key: value\n"
+               "  [a.b.c/d.e]: < key: value >\n"
+               "  [f.g]: <\n"
+               "    key: valueeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee\n"
+               "    key: {}\n"
+               "  >\n"
+               "  key {}\n"
+               "  [h.i.j] < key: value >\n"
+               "  [a]: {\n"
+               "    [b.c]: {}\n"
+               "    [d] <>\n"
+               "    [e/f]: 1\n"
+               "  }\n"
+               ">");
+}
 } // end namespace tooling
 } // end namespace clang