[clang-format] Add basic support for formatting C# files

Summary:

This revision adds basic support for formatting C# files with clang-format, I know the barrier to entry is high here  so I'm sending this revision in to test the water as to whether this might be something we'd consider landing.

Tracking in Bugzilla as:
https://bugs.llvm.org/show_bug.cgi?id=40850

Justification:
C# code just looks ugly in comparison to the C++ code in our source tree which is clang-formatted.

I've struggled with Visual Studio reformatting to get a clean and consistent style, I want to format our C# code on saving like I do now for C++ and i want it to have the same style as defined in our .clang-format file, so it consistent as it can be with C++.  (Braces/Breaking/Spaces/Indent etc..)

Using clang format without this patch leaves the code in a bad state, sometimes when the BreakStringLiterals is set, it  fails to compile.

Mostly the C# is similar to Java, except instead of JavaAnnotations I try to reuse the TT_AttributeSquare.

Almost the most valuable portion is to have a new Language in order to partition the configuration for C# within a common .clang-format file, with the auto detection on the .cs extension. But there are other C# specific styles that could be added later if this is accepted. in particular how  `{ set;get }` is formatted.

Reviewers: djasper, klimek, krasimir, benhamilton, JonasToth

Reviewed By: klimek

Subscribers: llvm-commits, mgorny, jdoerfert, cfe-commits

Tags: #clang, #clang-tools-extra

Differential Revision: https://reviews.llvm.org/D58404

llvm-svn: 356662

8 files changed, 352 insertions, 13 deletions

diff --git a/clang/lib/Format/ContinuationIndenter.cpp b/clang/lib/Format/ContinuationIndenter.cpp
index a82c8ce5b57..a2a13d4d465 100644
--- a/clang/lib/Format/ContinuationIndenter.cpp
+++ b/clang/lib/Format/ContinuationIndenter.cpp
@@ -418,7 +418,8 @@ bool ContinuationIndenter::mustBreak(const LineState &State) {
   if (Style.AlwaysBreakBeforeMultilineStrings &&
       (NewLineColumn == State.FirstIndent + Style.ContinuationIndentWidth ||
        Previous.is(tok::comma) || Current.NestingLevel < 2) &&
-      !Previous.isOneOf(tok::kw_return, tok::lessless, tok::at) &&
+      !Previous.isOneOf(tok::kw_return, tok::lessless, tok::at,
+                        Keywords.kw_dollar) &&
       !Previous.isOneOf(TT_InlineASMColon, TT_ConditionalExpr) &&
       nextIsMultilineString(State))
     return true;
@@ -1158,6 +1159,8 @@ unsigned ContinuationIndenter::moveStateToNextToken(LineState &State,
 
   if (Current.is(TT_ObjCStringLiteral) && State.StartOfStringLiteral == 0)
     State.StartOfStringLiteral = State.Column + 1;
+  if (Current.is(TT_CSharpStringLiteral) && State.StartOfStringLiteral == 0)
+    State.StartOfStringLiteral = State.Column + 1;
   else if (Current.isStringLiteral() && State.StartOfStringLiteral == 0)
     State.StartOfStringLiteral = State.Column;
   else if (!Current.isOneOf(tok::comment, tok::identifier, tok::hash) &&
@@ -1711,10 +1714,11 @@ ContinuationIndenter::createBreakableToken(const FormatToken &Current,
                                            LineState &State, bool AllowBreak) {
   unsigned StartColumn = State.Column - Current.ColumnWidth;
   if (Current.isStringLiteral()) {
-    // FIXME: String literal breaking is currently disabled for Java and JS, as
-    // it requires strings to be merged using "+" which we don't support.
+    // FIXME: String literal breaking is currently disabled for C#,Java and
+    // JavaScript, as it requires strings to be merged using "+" which we
+    // don't support.
     if (Style.Language == FormatStyle::LK_Java ||
-        Style.Language == FormatStyle::LK_JavaScript ||
+        Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp() ||
         !Style.BreakStringLiterals || !AllowBreak)
       return nullptr;
 
diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index 5e8a2497fea..5fe118a7161 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -61,6 +61,7 @@ template <> struct ScalarEnumerationTraits<FormatStyle::LanguageKind> {
     IO.enumCase(Value, "Proto", FormatStyle::LK_Proto);
     IO.enumCase(Value, "TableGen", FormatStyle::LK_TableGen);
     IO.enumCase(Value, "TextProto", FormatStyle::LK_TextProto);
+    IO.enumCase(Value, "CSharp", FormatStyle::LK_CSharp);
   }
 };
 
@@ -287,8 +288,8 @@ template <> struct MappingTraits<FormatStyle> {
     IO.mapOptional("Language", Style.Language);
 
     if (IO.outputting()) {
-      StringRef StylesArray[] = {"LLVM",    "Google", "Chromium",
-                                 "Mozilla", "WebKit", "GNU"};
+      StringRef StylesArray[] = {"LLVM",   "Google", "Chromium", "Mozilla",
+                                 "WebKit", "GNU",    "Microsoft"};
       ArrayRef<StringRef> Styles(StylesArray);
       for (size_t i = 0, e = Styles.size(); i < e; ++i) {
         StringRef StyleName(Styles[i]);
@@ -951,6 +952,32 @@ FormatStyle getGNUStyle() {
   return Style;
 }
 
+FormatStyle getMicrosoftStyle(FormatStyle::LanguageKind Language) {
+  FormatStyle Style = getLLVMStyle();
+  Style.ColumnLimit = 120;
+  Style.TabWidth = 4;
+  Style.IndentWidth = 4;
+  Style.UseTab = FormatStyle::UT_Never;
+  Style.BreakBeforeBraces = FormatStyle::BS_Custom;
+  Style.BraceWrapping.AfterClass = true;
+  Style.BraceWrapping.AfterControlStatement = true;
+  Style.BraceWrapping.AfterEnum = true;
+  Style.BraceWrapping.AfterFunction = true;
+  Style.BraceWrapping.AfterNamespace = true;
+  Style.BraceWrapping.AfterObjCDeclaration = true;
+  Style.BraceWrapping.AfterStruct = true;
+  Style.BraceWrapping.AfterExternBlock = true;
+  Style.BraceWrapping.BeforeCatch = true;
+  Style.BraceWrapping.BeforeElse = true;
+  Style.PenaltyReturnTypeOnItsOwnLine = 1000;
+  Style.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_None;
+  Style.AllowShortBlocksOnASingleLine = false;
+  Style.AllowShortCaseLabelsOnASingleLine = false;
+  Style.AllowShortIfStatementsOnASingleLine = FormatStyle::SIS_Never;
+  Style.AllowShortLoopsOnASingleLine = false;
+  return Style;
+}
+
 FormatStyle getNoStyle() {
   FormatStyle NoStyle = getLLVMStyle();
   NoStyle.DisableFormat = true;
@@ -973,6 +1000,8 @@ bool getPredefinedStyle(StringRef Name, FormatStyle::LanguageKind Language,
     *Style = getWebKitStyle();
   } else if (Name.equals_lower("gnu")) {
     *Style = getGNUStyle();
+  } else if (Name.equals_lower("microsoft")) {
+    *Style = getMicrosoftStyle(Language);
   } else if (Name.equals_lower("none")) {
     *Style = getNoStyle();
   } else {
@@ -2323,6 +2352,8 @@ static FormatStyle::LanguageKind getLanguageByFileName(StringRef FileName) {
     return FormatStyle::LK_TextProto;
   if (FileName.endswith_lower(".td"))
     return FormatStyle::LK_TableGen;
+  if (FileName.endswith_lower(".cs"))
+    return FormatStyle::LK_CSharp;
   return FormatStyle::LK_Cpp;
 }
 
diff --git a/clang/lib/Format/FormatToken.h b/clang/lib/Format/FormatToken.h
index a5daf8aed46..461e0704a3f 100644
--- a/clang/lib/Format/FormatToken.h
+++ b/clang/lib/Format/FormatToken.h
@@ -96,6 +96,8 @@ namespace format {
   TYPE(TrailingReturnArrow)                                                    \
   TYPE(TrailingUnaryOperator)                                                  \
   TYPE(UnaryOperator)                                                          \
+  TYPE(CSharpStringLiteral)                                                    \
+  TYPE(CSharpNullCoalescing)                                                   \
   TYPE(Unknown)
 
 enum TokenType {
@@ -723,7 +725,36 @@ struct AdditionalKeywords {
     kw_slots = &IdentTable.get("slots");
     kw_qslots = &IdentTable.get("Q_SLOTS");
 
-    // Keep this at the end of the constructor to make sure everything here is
+    // C# keywords
+    kw_dollar = &IdentTable.get("dollar");
+    kw_base = &IdentTable.get("base");
+    kw_byte = &IdentTable.get("byte");
+    kw_checked = &IdentTable.get("checked");
+    kw_decimal = &IdentTable.get("decimal");
+    kw_delegate = &IdentTable.get("delegate");
+    kw_event = &IdentTable.get("event");
+    kw_fixed = &IdentTable.get("fixed");
+    kw_foreach = &IdentTable.get("foreach");
+    kw_implicit = &IdentTable.get("implicit");
+    kw_internal = &IdentTable.get("internal");
+    kw_lock = &IdentTable.get("lock");
+    kw_null = &IdentTable.get("null");
+    kw_object = &IdentTable.get("object");
+    kw_out = &IdentTable.get("out");
+    kw_params = &IdentTable.get("params");
+    kw_ref = &IdentTable.get("ref");
+    kw_string = &IdentTable.get("string");
+    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");
+
+    // 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,
@@ -731,6 +762,19 @@ struct AdditionalKeywords {
          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,
+         // 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});
   }
 
   // Context sensitive keywords.
@@ -796,6 +840,37 @@ struct AdditionalKeywords {
   IdentifierInfo *kw_slots;
   IdentifierInfo *kw_qslots;
 
+  // C# keywords
+  IdentifierInfo *kw_dollar;
+  IdentifierInfo *kw_base;
+  IdentifierInfo *kw_byte;
+  IdentifierInfo *kw_checked;
+  IdentifierInfo *kw_decimal;
+  IdentifierInfo *kw_delegate;
+  IdentifierInfo *kw_event;
+  IdentifierInfo *kw_fixed;
+  IdentifierInfo *kw_foreach;
+  IdentifierInfo *kw_implicit;
+  IdentifierInfo *kw_internal;
+
+  IdentifierInfo *kw_lock;
+  IdentifierInfo *kw_null;
+  IdentifierInfo *kw_object;
+  IdentifierInfo *kw_out;
+
+  IdentifierInfo *kw_params;
+
+  IdentifierInfo *kw_ref;
+  IdentifierInfo *kw_string;
+  IdentifierInfo *kw_stackalloc;
+  IdentifierInfo *kw_sbyte;
+  IdentifierInfo *kw_sealed;
+  IdentifierInfo *kw_uint;
+  IdentifierInfo *kw_ulong;
+  IdentifierInfo *kw_unchecked;
+  IdentifierInfo *kw_unsafe;
+  IdentifierInfo *kw_ushort;
+
   /// 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 {
@@ -804,9 +879,68 @@ struct AdditionalKeywords {
                JsExtraKeywords.end();
   }
 
+  /// Returns \c true if \p Tok is a C# keyword, returns
+  /// \c false if it is a anything else.
+  bool isCSharpKeyword(const FormatToken &Tok) const {
+    switch (Tok.Tok.getKind()) {
+    case tok::kw_bool:
+    case tok::kw_break:
+    case tok::kw_case:
+    case tok::kw_catch:
+    case tok::kw_char:
+    case tok::kw_class:
+    case tok::kw_const:
+    case tok::kw_continue:
+    case tok::kw_default:
+    case tok::kw_do:
+    case tok::kw_double:
+    case tok::kw_else:
+    case tok::kw_enum:
+    case tok::kw_explicit:
+    case tok::kw_extern:
+    case tok::kw_false:
+    case tok::kw_float:
+    case tok::kw_for:
+    case tok::kw_goto:
+    case tok::kw_if:
+    case tok::kw_int:
+    case tok::kw_long:
+    case tok::kw_namespace:
+    case tok::kw_new:
+    case tok::kw_operator:
+    case tok::kw_private:
+    case tok::kw_protected:
+    case tok::kw_public:
+    case tok::kw_return:
+    case tok::kw_short:
+    case tok::kw_sizeof:
+    case tok::kw_static:
+    case tok::kw_struct:
+    case tok::kw_switch:
+    case tok::kw_this:
+    case tok::kw_throw:
+    case tok::kw_true:
+    case tok::kw_try:
+    case tok::kw_typeof:
+    case tok::kw_using:
+    case tok::kw_virtual:
+    case tok::kw_void:
+    case tok::kw_volatile:
+    case tok::kw_while:
+      return true;
+    default:
+      return Tok.is(tok::identifier) &&
+             CSharpExtraKeywords.find(Tok.Tok.getIdentifierInfo()) ==
+                 CSharpExtraKeywords.end();
+    }
+  }
+
 private:
   /// The JavaScript keywords beyond the C++ keyword set.
   std::unordered_set<IdentifierInfo *> JsExtraKeywords;
+
+  /// The C# keywords beyond the C++ keyword set
+  std::unordered_set<IdentifierInfo *> CSharpExtraKeywords;
 };
 
 } // namespace format
diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp
index da755e36c15..3a1dcef7d43 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -66,6 +66,21 @@ void FormatTokenLexer::tryMergePreviousTokens() {
     return;
   if (tryMergeLessLess())
     return;
+
+  if (Style.isCSharp()) {
+    if (tryMergeCSharpKeywordVariables())
+      return;
+    if (tryMergeCSharpVerbatimStringLiteral())
+      return;
+    if (tryMergeCSharpDoubleQuestion())
+      return;
+    if (tryMergeCSharpNullConditionals())
+      return;
+    static const tok::TokenKind JSRightArrow[] = {tok::equal, tok::greater};
+    if (tryMergeTokens(JSRightArrow, TT_JsFatArrow))
+      return;
+  }
+
   if (tryMergeNSStringLiteral())
     return;
 
@@ -142,6 +157,100 @@ bool FormatTokenLexer::tryMergeJSPrivateIdentifier() {
   return true;
 }
 
+// Search for verbatim or interpolated string literals @"ABC" or
+// $"aaaaa{abc}aaaaa" i and mark the token as TT_CSharpStringLiteral, and to
+// prevent splitting of @, $ and ".
+bool FormatTokenLexer::tryMergeCSharpVerbatimStringLiteral() {
+  if (Tokens.size() < 2)
+    return false;
+  auto &At = *(Tokens.end() - 2);
+  auto &String = *(Tokens.end() - 1);
+
+  // Look for $"aaaaaa" @"aaaaaa".
+  if (!(At->is(tok::at) || At->TokenText == "$") ||
+      !String->is(tok::string_literal))
+    return false;
+
+  if (Tokens.size() >= 2 && At->is(tok::at)) {
+    auto &Dollar = *(Tokens.end() - 3);
+    if (Dollar->TokenText == "$") {
+      // This looks like $@"aaaaa" so we need to combine all 3 tokens.
+      Dollar->Tok.setKind(tok::string_literal);
+      Dollar->TokenText =
+          StringRef(Dollar->TokenText.begin(),
+                    String->TokenText.end() - Dollar->TokenText.begin());
+      Dollar->ColumnWidth += (At->ColumnWidth + String->ColumnWidth);
+      Dollar->Type = TT_CSharpStringLiteral;
+      Tokens.erase(Tokens.end() - 2);
+      Tokens.erase(Tokens.end() - 1);
+      return true;
+    }
+  }
+
+  // Convert back into just a string_literal.
+  At->Tok.setKind(tok::string_literal);
+  At->TokenText = StringRef(At->TokenText.begin(),
+                            String->TokenText.end() - At->TokenText.begin());
+  At->ColumnWidth += String->ColumnWidth;
+  At->Type = TT_CSharpStringLiteral;
+  Tokens.erase(Tokens.end() - 1);
+  return true;
+}
+
+bool FormatTokenLexer::tryMergeCSharpDoubleQuestion() {
+  if (Tokens.size() < 2)
+    return false;
+  auto &FirstQuestion = *(Tokens.end() - 2);
+  auto &SecondQuestion = *(Tokens.end() - 1);
+  if (!FirstQuestion->is(tok::question) || !SecondQuestion->is(tok::question))
+    return false;
+  FirstQuestion->Tok.setKind(tok::question);
+  FirstQuestion->TokenText = StringRef(FirstQuestion->TokenText.begin(),
+                                       SecondQuestion->TokenText.end() -
+                                           FirstQuestion->TokenText.begin());
+  FirstQuestion->ColumnWidth += SecondQuestion->ColumnWidth;
+  FirstQuestion->Type = TT_CSharpNullCoalescing;
+  Tokens.erase(Tokens.end() - 1);
+  return true;
+}
+
+bool FormatTokenLexer::tryMergeCSharpKeywordVariables() {
+  if (Tokens.size() < 2)
+    return false;
+  auto &At = *(Tokens.end() - 2);
+  auto &Keyword = *(Tokens.end() - 1);
+  if (!At->is(tok::at))
+    return false;
+  if (!Keywords.isCSharpKeyword(*Keyword))
+    return false;
+
+  At->Tok.setKind(tok::identifier);
+  At->TokenText = StringRef(At->TokenText.begin(),
+                            Keyword->TokenText.end() - At->TokenText.begin());
+  At->ColumnWidth += Keyword->ColumnWidth;
+  At->Type = Keyword->Type;
+  Tokens.erase(Tokens.end() - 1);
+  return true;
+}
+
+// In C# merge the Identifier and the ? together e.g. arg?.
+bool FormatTokenLexer::tryMergeCSharpNullConditionals() {
+  if (Tokens.size() < 2)
+    return false;
+  auto &Identifier = *(Tokens.end() - 2);
+  auto &Question = *(Tokens.end() - 1);
+  if (!Identifier->isOneOf(tok::r_square, tok::identifier) ||
+      !Question->is(tok::question))
+    return false;
+  Identifier->TokenText =
+      StringRef(Identifier->TokenText.begin(),
+                Question->TokenText.end() - Identifier->TokenText.begin());
+  Identifier->ColumnWidth += Question->ColumnWidth;
+  Identifier->Type = Identifier->Type;
+  Tokens.erase(Tokens.end() - 1);
+  return true;
+}
+
 bool FormatTokenLexer::tryMergeLessLess() {
   // Merge X,less,less,Y into X,lessless,Y unless X or Y is less.
   if (Tokens.size() < 3)
diff --git a/clang/lib/Format/FormatTokenLexer.h b/clang/lib/Format/FormatTokenLexer.h
index a9646261461..1e096fc5020 100644
--- a/clang/lib/Format/FormatTokenLexer.h
+++ b/clang/lib/Format/FormatTokenLexer.h
@@ -49,6 +49,10 @@ private:
   bool tryMergeLessLess();
   bool tryMergeNSStringLiteral();
   bool tryMergeJSPrivateIdentifier();
+  bool tryMergeCSharpVerbatimStringLiteral();
+  bool tryMergeCSharpKeywordVariables();
+  bool tryMergeCSharpNullConditionals();
+  bool tryMergeCSharpDoubleQuestion();
 
   bool tryMergeTokens(ArrayRef<tok::TokenKind> Kinds, TokenType NewType);
 
diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp
index eeaceb82f9f..ccf5e51576d 100644
--- a/clang/lib/Format/TokenAnnotator.cpp
+++ b/clang/lib/Format/TokenAnnotator.cpp
@@ -298,6 +298,8 @@ private:
           CurrentToken->Type = TT_JavaAnnotation;
         if (Left->Previous && Left->Previous->is(TT_LeadingJavaAnnotation))
           CurrentToken->Type = TT_LeadingJavaAnnotation;
+        if (Left->Previous && Left->Previous->is(TT_AttributeSquare))
+          CurrentToken->Type = TT_AttributeSquare;
 
         if (!HasMultipleLines)
           Left->PackingKind = PPK_Inconclusive;
@@ -348,6 +350,40 @@ private:
     return false;
   }
 
+  bool isCSharpAttributeSpecifier(const FormatToken &Tok) {
+    if (!Style.isCSharp())
+      return false;
+
+    const FormatToken *AttrTok = Tok.Next;
+    if (!AttrTok)
+      return false;
+
+    // Just an empty declaration e.g. string [].
+    if (AttrTok->is(tok::r_square))
+      return false;
+
+    // Move along the tokens inbetween the '[' and ']' e.g. [STAThread].
+    while (AttrTok && AttrTok->isNot(tok::r_square)) {
+      AttrTok = AttrTok->Next;
+    }
+
+    if (!AttrTok)
+      return false;
+
+    // Move past the end of ']'.
+    AttrTok = AttrTok->Next;
+    if (!AttrTok)
+      return false;
+
+    // Limit this to being an access modifier that follows.
+    if (AttrTok->isOneOf(tok::kw_public, tok::kw_private, tok::kw_protected,
+                         tok::kw_class, tok::kw_static, tok::l_square,
+                         Keywords.kw_internal)) {
+      return true;
+    }
+    return false;
+  }
+
   bool isCpp11AttributeSpecifier(const FormatToken &Tok) {
     if (!Style.isCpp() || !Tok.startsSequence(tok::l_square, tok::l_square))
       return false;
@@ -398,6 +434,11 @@ private:
     bool IsCpp11AttributeSpecifier = isCpp11AttributeSpecifier(*Left) ||
                                      Contexts.back().InCpp11AttributeSpecifier;
 
+    // Treat C# Attributes [STAThread] much like C++ attributes [[...]].
+    bool IsCSharp11AttributeSpecifier =
+        isCSharpAttributeSpecifier(*Left) ||
+        Contexts.back().InCSharpAttributeSpecifier;
+
     bool InsideInlineASM = Line.startsWith(tok::kw_asm);
     bool StartsObjCMethodExpr =
         !InsideInlineASM && !CppArrayTemplates && Style.isCpp() &&
@@ -478,6 +519,8 @@ private:
                                  // Should only be relevant to JavaScript:
                                  tok::kw_default)) {
         Left->Type = TT_ArrayInitializerLSquare;
+      } else if (IsCSharp11AttributeSpecifier) {
+        Left->Type = TT_AttributeSquare;
       } else {
         BindingIncrease = 10;
         Left->Type = TT_ArraySubscriptLSquare;
@@ -492,11 +535,14 @@ private:
 
     Contexts.back().ColonIsObjCMethodExpr = StartsObjCMethodExpr;
     Contexts.back().InCpp11AttributeSpecifier = IsCpp11AttributeSpecifier;
+    Contexts.back().InCSharpAttributeSpecifier = IsCSharp11AttributeSpecifier;
 
     while (CurrentToken) {
       if (CurrentToken->is(tok::r_square)) {
         if (IsCpp11AttributeSpecifier)
           CurrentToken->Type = TT_AttributeSquare;
+        if (IsCSharp11AttributeSpecifier)
+          CurrentToken->Type = TT_AttributeSquare;
         else if (((CurrentToken->Next &&
                    CurrentToken->Next->is(tok::l_paren)) ||
                   (CurrentToken->Previous &&
@@ -1193,6 +1239,7 @@ private:
     bool CaretFound = false;
     bool IsForEachMacro = false;
     bool InCpp11AttributeSpecifier = false;
+    bool InCSharpAttributeSpecifier = false;
   };
 
   /// Puts a new \c Context onto the stack \c Contexts for the lifetime
@@ -2630,7 +2677,7 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
     // and "%d %d"
     if (Left.is(tok::numeric_constant) && Right.is(tok::percent))
       return Right.WhitespaceRange.getEnd() != Right.WhitespaceRange.getBegin();
-  } else if (Style.Language == FormatStyle::LK_JavaScript) {
+  } else if (Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp()) {
     if (Left.is(TT_JsFatArrow))
       return true;
     // for await ( ...
@@ -2977,6 +3024,14 @@ bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line,
   if (Left.is(TT_ObjCBlockLBrace) && !Style.AllowShortBlocksOnASingleLine)
     return true;
 
+  // Put multiple C# attributes on a new line.
+  if (Style.isCSharp() &&
+      ((Left.is(TT_AttributeSquare) && Left.is(tok::r_square)) ||
+       (Left.is(tok::r_square) && Right.is(TT_AttributeSquare) &&
+        Right.is(tok::l_square))))
+    return true;
+
+  // Put multiple Java annotation on a new line.
   if ((Style.Language == FormatStyle::LK_Java ||
        Style.Language == FormatStyle::LK_JavaScript) &&
       Left.is(TT_LeadingJavaAnnotation) &&
diff --git a/clang/lib/Format/UnwrappedLineFormatter.cpp b/clang/lib/Format/UnwrappedLineFormatter.cpp
index 5d8142a1cfb..4e633c203c1 100644
--- a/clang/lib/Format/UnwrappedLineFormatter.cpp
+++ b/clang/lib/Format/UnwrappedLineFormatter.cpp
@@ -94,7 +94,7 @@ private:
   /// characters to the left from their level.
   int getIndentOffset(const FormatToken &RootToken) {
     if (Style.Language == FormatStyle::LK_Java ||
-        Style.Language == FormatStyle::LK_JavaScript)
+        Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp())
       return 0;
     if (RootToken.isAccessSpecifier(false) ||
         RootToken.isObjCAccessSpecifier() ||
@@ -1073,7 +1073,9 @@ unsigned UnwrappedLineFormatter::format(
           TheLine.Last->TotalLength + Indent <= ColumnLimit ||
           (TheLine.Type == LT_ImportStatement &&
            (Style.Language != FormatStyle::LK_JavaScript ||
-            !Style.JavaScriptWrapImports));
+            !Style.JavaScriptWrapImports)) ||
+          (Style.isCSharp() &&
+           TheLine.InPPDirective); // don't split #regions in C#
       if (Style.ColumnLimit == 0)
         NoColumnLimitLineFormatter(Indenter, Whitespaces, Style, this)
             .formatLine(TheLine, NextStartColumn + Indent,
diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp
index 4bd71aa26d5..814e8143e17 100644
--- a/clang/lib/Format/UnwrappedLineParser.cpp
+++ b/clang/lib/Format/UnwrappedLineParser.cpp
@@ -1000,7 +1000,7 @@ void UnwrappedLineParser::parseStructuralElement() {
   case tok::kw_protected:
   case tok::kw_private:
     if (Style.Language == FormatStyle::LK_Java ||
-        Style.Language == FormatStyle::LK_JavaScript)
+        Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp())
       nextToken();
     else
       parseAccessSpecifier();
@@ -1214,9 +1214,9 @@ void UnwrappedLineParser::parseStructuralElement() {
       // parseRecord falls through and does not yet add an unwrapped line as a
       // record declaration or definition can start a structural element.
       parseRecord();
-      // This does not apply for Java and JavaScript.
+      // This does not apply for Java, JavaScript and C#.
       if (Style.Language == FormatStyle::LK_Java ||
-          Style.Language == FormatStyle::LK_JavaScript) {
+          Style.Language == FormatStyle::LK_JavaScript || Style.isCSharp()) {
         if (FormatTok->is(tok::semi))
           nextToken();
         addUnwrappedLine();