1 files changed, 51 insertions, 15 deletions

diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp
index 50d41c9f57a6..b904e0e56d9e 100644
--- a/clang/lib/Format/UnwrappedLineParser.cpp
+++ b/clang/lib/Format/UnwrappedLineParser.cpp
@@ -1170,6 +1170,15 @@ void UnwrappedLineParser::parsePPDefine() {
   assert((int)Line->PPLevel >= 0);
   Line->InMacroBody = true;
 
+  if (Style.SkipMacroDefinitionBody) {
+    do {
+      FormatTok->Finalized = true;
+      nextToken();
+    } while (!eof());
+    addUnwrappedLine();
+    return;
+  }
+
   if (FormatTok->is(tok::identifier) &&
       Tokens->peekNextToken()->is(tok::colon)) {
     nextToken();
@@ -1652,7 +1661,8 @@ void UnwrappedLineParser::parseStructuralElement(
     // In Verilog labels can be any expression, so we don't do them here.
     // JS doesn't have macros, and within classes colons indicate fields, not
     // labels.
-    if (!Style.isJavaScript() && !Style.isVerilog() &&
+    // TableGen doesn't have labels.
+    if (!Style.isJavaScript() && !Style.isVerilog() && !Style.isTableGen() &&
         Tokens->peekNextToken()->is(tok::colon) && !Line->MustBeDeclaration) {
       nextToken();
       Line->Tokens.begin()->Tok->MustBreakBefore = true;
@@ -1781,6 +1791,12 @@ void UnwrappedLineParser::parseStructuralElement(
         addUnwrappedLine();
         return;
       }
+      if (Style.isTableGen()) {
+        // Do nothing special. In this case the l_brace becomes FunctionLBrace.
+        // This is same as def and so on.
+        nextToken();
+        break;
+      }
       [[fallthrough]];
     case tok::kw_struct:
     case tok::kw_union:
@@ -2019,6 +2035,16 @@ void UnwrappedLineParser::parseStructuralElement(
         // initialisers are indented the same way.
         if (Style.isCSharp())
           FormatTok->setBlockKind(BK_BracedInit);
+        // TableGen's defset statement has syntax of the form,
+        // `defset <type> <name> = { <statement>... }`
+        if (Style.isTableGen() &&
+            Line->Tokens.begin()->Tok->is(Keywords.kw_defset)) {
+          FormatTok->setFinalizedType(TT_FunctionLBrace);
+          parseBlock(/*MustBeDeclaration=*/false, /*AddLevels=*/1u,
+                     /*MunchSemi=*/false);
+          addUnwrappedLine();
+          break;
+        }
         nextToken();
         parseBracedList();
       } else if (Style.Language == FormatStyle::LK_Proto &&
@@ -2734,6 +2760,14 @@ FormatToken *UnwrappedLineParser::parseIfThenElse(IfStmtKind *IfKind,
     }
   }
 
+  // TableGen's if statement has the form of `if <cond> then { ... }`.
+  if (Style.isTableGen()) {
+    while (!eof() && FormatTok->isNot(Keywords.kw_then)) {
+      // Simply skip until then. This range only contains a value.
+      nextToken();
+    }
+  }
+
   // Handle `if !consteval`.
   if (FormatTok->is(tok::exclaim))
     nextToken();
@@ -3873,6 +3907,9 @@ void UnwrappedLineParser::parseRecord(bool ParseAsExpr) {
   const FormatToken &InitialToken = *FormatTok;
   nextToken();
 
+  auto IsNonMacroIdentifier = [](const FormatToken *Tok) {
+    return Tok->is(tok::identifier) && Tok->TokenText != Tok->TokenText.upper();
+  };
   // The actual identifier can be a nested name specifier, and in macros
   // it is often token-pasted.
   // An [[attribute]] can be before the identifier.
@@ -3894,27 +3931,26 @@ void UnwrappedLineParser::parseRecord(bool ParseAsExpr) {
     }
     if (FormatTok->is(tok::l_square) && handleCppAttributes())
       continue;
-    bool IsNonMacroIdentifier =
-        FormatTok->is(tok::identifier) &&
-        FormatTok->TokenText != FormatTok->TokenText.upper();
     nextToken();
     // We can have macros in between 'class' and the class name.
-    if (!IsNonMacroIdentifier && FormatTok->is(tok::l_paren))
+    if (!IsNonMacroIdentifier(FormatTok->Previous) &&
+        FormatTok->is(tok::l_paren)) {
       parseParens();
+    }
   }
 
-  // Note that parsing away template declarations here leads to incorrectly
-  // accepting function declarations as record declarations.
-  // In general, we cannot solve this problem. Consider:
-  // class A<int> B() {}
-  // which can be a function definition or a class definition when B() is a
-  // macro. If we find enough real-world cases where this is a problem, we
-  // can parse for the 'template' keyword in the beginning of the statement,
-  // and thus rule out the record production in case there is no template
-  // (this would still leave us with an ambiguity between template function
-  // and class declarations).
   if (FormatTok->isOneOf(tok::colon, tok::less)) {
+    int AngleNestingLevel = 0;
     do {
+      if (FormatTok->is(tok::less))
+        ++AngleNestingLevel;
+      else if (FormatTok->is(tok::greater))
+        --AngleNestingLevel;
+
+      if (AngleNestingLevel == 0 && FormatTok->is(tok::l_paren) &&
+          IsNonMacroIdentifier(FormatTok->Previous)) {
+        break;
+      }
       if (FormatTok->is(tok::l_brace)) {
         calculateBraceTypes(/*ExpectClassBody=*/true);
         if (!tryToParseBracedList())