[clang-format] Special handling of spaces for C# code

[jbcoe]

Summary

Ensure that there are spaces around braces '{', '}'.

Ensure that there is a space before and after '=>'.

Ensure that 'async' and 'when' are considered as keywords when inserting spaces.

[krasimir]

As a general comment, we should consider which of these special cases can already be simulated by a combination of existing style options:
https://clang.llvm.org/docs/ClangFormatStyleOptions.html
There are several Spaces* options there that can be used to independently control various spacing around parenthesis.

[krasimir]

clang/lib/Format/TokenAnnotator.cpp

2839

Move this to the already existing } else if (Style.isCSharp()) { on line 2902 below.

[jbcoe]

Treat async and when as keywords.

Consolidate C# space insertion logic.

[jbcoe]

remove commented out code

[krasimir]

clang/unittests/Format/FormatTestCSharp.cpp

584

If these values for these options make sense for Google style in general, consider updating the getGoogleStyle default style with a C#-specific section here:
https://github.com/llvm/llvm-project/blob/master/clang/lib/Format/Format.cpp#L992
I'd recommend doing this in a separate patch based on top of this one.

clang/lib/Format/FormatToken.h

AdditionalKeywords(IdentifierTable &IdentTable) {
     kw_stackalloc = &IdentTable.get("stackalloc");
     kw_sbyte = &IdentTable.get("sbyte");
     kw_sealed = &IdentTable.get("sealed");
     kw_uint = &IdentTable.get("uint");
     kw_ulong = &IdentTable.get("ulong");
     kw_unchecked = &IdentTable.get("unchecked");
     kw_unsafe = &IdentTable.get("unsafe");
     kw_ushort = &IdentTable.get("ushort");
+    kw_when = &IdentTable.get("when");
 
     // Keep this at the end of the constructor to make sure everything here
     // is
     // already initialized.
     JsExtraKeywords = std::unordered_set<IdentifierInfo *>(
         {kw_as, kw_async, kw_await, kw_declare, kw_finally, kw_from,
          kw_function, kw_get, kw_import, kw_is, kw_let, kw_module, kw_readonly,
          kw_set, kw_type, kw_typeof, kw_var, kw_yield,
          // Keywords from the Java section.
          kw_abstract, kw_extends, kw_implements, kw_instanceof, kw_interface});
 
     CSharpExtraKeywords = std::unordered_set<IdentifierInfo *>(
         {kw_base, kw_byte, kw_checked, kw_decimal, kw_delegate, kw_event,
          kw_fixed, kw_foreach, kw_implicit, kw_in, kw_interface, kw_internal,
          kw_is, kw_lock, kw_null, kw_object, kw_out, kw_override, kw_params,
          kw_readonly, kw_ref, kw_string, kw_stackalloc, kw_sbyte, kw_sealed,
-         kw_uint, kw_ulong, kw_unchecked, kw_unsafe, kw_ushort,
+         kw_uint, kw_ulong, kw_unchecked, kw_unsafe, kw_ushort, kw_when,
          // Keywords from the JavaScript section.
          kw_as, kw_async, kw_await, kw_declare, kw_finally, kw_from,
          kw_function, kw_get, kw_import, kw_is, kw_let, kw_module, kw_readonly,
          kw_set, kw_type, kw_typeof, kw_var, kw_yield,
          // Keywords from the Java section.
          kw_abstract, kw_extends, kw_implements, kw_instanceof, kw_interface});
   }
 
struct AdditionalKeywords {
   IdentifierInfo *kw_stackalloc;
   IdentifierInfo *kw_sbyte;
   IdentifierInfo *kw_sealed;
   IdentifierInfo *kw_uint;
   IdentifierInfo *kw_ulong;
   IdentifierInfo *kw_unchecked;
   IdentifierInfo *kw_unsafe;
   IdentifierInfo *kw_ushort;
+  IdentifierInfo *kw_when;
 
   /// Returns \c true if \p Tok is a true JavaScript identifier, returns
   /// \c false if it is a keyword or a pseudo keyword.
   bool IsJavaScriptIdentifier(const FormatToken &Tok) const {
     return Tok.is(tok::identifier) &&
            JsExtraKeywords.find(Tok.Tok.getIdentifierInfo()) ==
                JsExtraKeywords.end();
   }

clang/lib/Format/TokenAnnotator.cpp

if (Right.Type == TT_TrailingAnnotation &&
     // void Fn() const &;
     return Style.PointerAlignment != FormatStyle::PAS_Left;
   return true;
 }
 
 bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
                                          const FormatToken &Right) {
   const FormatToken &Left = *Right.Previous;
   if (Right.Tok.getIdentifierInfo() && Left.Tok.getIdentifierInfo())
     return true; // Never ever merge two identifiers.
   if (Style.isCpp()) {
     if (Left.is(tok::kw_operator))
       return Right.is(tok::coloncolon);
     if (Right.is(tok::l_brace) && Right.BlockKind == BK_BracedInit &&
         !Left.opensScope() && Style.SpaceBeforeCpp11BracedList)
       return true;
   } else if (Style.Language == FormatStyle::LK_Proto ||
if (Style.isCpp()) {
     // A percent is probably part of a formatting specification, such as %lld.
     if (Left.is(tok::percent))
       return false;
     // Preserve the existence of a space before a percent for cases like 0x%04x
     // and "%d %d"
     if (Left.is(tok::numeric_constant) && Right.is(tok::percent))
       return Right.WhitespaceRange.getEnd() != Right.WhitespaceRange.getBegin();
   } else if (Style.isCSharp()) {
+    // Require spaces around '{' and  before '}' unless they appear in
+    // interpolated strings. Interpolated strings are merged into a single token
+    // so cannot have spaces inserted by this function.
+
+    // Space before { (including space within '{ {').
+    if (Right.is(tok::l_brace))
+      return true;
+
+    // Spaces inside braces.
+    if (Left.is(tok::l_brace) && Right.isNot(tok::r_brace))
+      return true;
+
+    if (Left.isNot(tok::l_brace) && Right.is(tok::r_brace))
+      return true;
+
+    // Spaces around '=>'.
+    if (Left.is(TT_JsFatArrow) || Right.is(TT_JsFatArrow))
+      return true;
+
     // space between type and variable e.g. Dictionary<string,string> foo;
     if (Left.is(TT_TemplateCloser) && Right.is(TT_StartOfName))
       return true;
+
     // space between keywords and paren e.g. "using ("
     if (Right.is(tok::l_paren))
-      if (Left.is(tok::kw_using))
+      if (Left.isOneOf(tok::kw_using, Keywords.kw_async, Keywords.kw_when))
         return Style.SpaceBeforeParens == FormatStyle::SBPO_ControlStatements ||
                spaceRequiredBeforeParens(Right);
-    // space between ']' and '{'
-    if (Left.is(tok::r_square) && Right.is(tok::l_brace))
-      return true;
-    // space before '{' in "new MyType {"
-    if (Right.is(tok::l_brace) && Left.Previous &&
-        Left.Previous->is(tok::kw_new))
-      return true;
   } 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) &&

clang/unittests/Format/FormatTestCSharp.cpp

new Square {
         Side = 101.1,
         Colour = Colours.Yellow,
     },
 };)",
                Style);
 
   // Omitted final `,`s will change the formatting.
   verifyFormat(R"(//
-Shape[] shapes = new[] {new Circle {Radius = 2.7281, Colour = Colours.Red},
+Shape[] shapes = new[] { new Circle { Radius = 2.7281, Colour = Colours.Red },
                          new Square {
                              Side = 101.1,
                              Colour = Colours.Yellow,
-                        }};)",
+                         } };)",
                Style);
 }
 
 TEST_F(FormatTestCSharp, CSharpNamedArguments) {
   FormatStyle Style = getGoogleStyle(FormatStyle::LK_CSharp);
 
   verifyFormat(R"(//
 PrintOrderDetails(orderNum: 31, productName: "Red Mug",
TEST_F(FormatTestCSharp, CSharpPropertyAccessors) {
   verifyFormat(R"(//
 public string Name {
   get => _name;
   set => _name = value;
 })",
                Style);
 }
 
+TEST_F(FormatTestCSharp, CSharpSpaces) {
+  FormatStyle Style = getGoogleStyle(FormatStyle::LK_CSharp);
+  Style.SpaceBeforeSquareBrackets = false;
+  Style.SpacesInSquareBrackets = false;
+  Style.SpaceBeforeCpp11BracedList = true;
+  Style.Cpp11BracedListStyle = false;
+  Style.SpacesInContainerLiterals = false;
+
+  verifyFormat(R"(new Car { "Door", 0.1 })", Style);
+  verifyFormat(R"(new Car { 0.1, "Door" })", Style);
+  verifyFormat(R"(new string[] { "A" })", Style);
+  verifyFormat(R"(new string[] {})", Style);
+  verifyFormat(R"(new Car { someVariableName })", Style);
+  verifyFormat(R"(new Car { someVariableName })", Style);
+  verifyFormat(R"(new Dictionary<string, string> { ["Key"] = "Value" };)",
+               Style);
+  verifyFormat(R"(Apply(x => x.Name, x => () => x.ID);)", Style);
+  verifyFormat(R"(bool[] xs = { true, true };)", Style);
+  verifyFormat(R"(taskContext.Factory.Run(async () => doThing(args);)", Style);
+  verifyFormat(R"(catch (TestException) when (innerFinallyExecuted))", Style);
+}
+
 } // namespace format
 } // end namespace clang