[clang-format] Support of TableGen statements in unwrapped line parser (#78846)

Make TableGen's statements to be parsed considering their structure.
- Avoid to parse label
- Avoid class from being parsed as c++'s class
- Support if statement of the form `if <cond> then { ... }` 
- Support defset statement of the form `defset <type> <name> {}`

---------

Co-authored-by: Björn Schäpers <[email protected]>

Author: hnakamura5

clang/lib/Format/UnwrappedLineParser.cpp

@@ -1661,7 +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;
@@ -1790,6 +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:
@@ -2028,6 +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 &&
@@ -2743,6 +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();

clang/unittests/Format/TokenAnnotatorTest.cpp

@@ -2232,6 +2232,18 @@ TEST_F(TokenAnnotatorTest, UnderstandTableGenTokens) {
   EXPECT_TOKEN(Tokens[0], tok::identifier, TT_Unknown);
   Tokens = Annotate("01234Vector");
   EXPECT_TOKEN(Tokens[0], tok::identifier, TT_Unknown);
+
+  // Structured statements.
+  Tokens = Annotate("class Foo {}");
+  EXPECT_TOKEN(Tokens[2], tok::l_brace, TT_FunctionLBrace);
+  Tokens = Annotate("def Def: Foo {}");
+  EXPECT_TOKEN(Tokens[2], tok::colon, TT_InheritanceColon);
+  EXPECT_TOKEN(Tokens[4], tok::l_brace, TT_FunctionLBrace);
+  Tokens = Annotate("if cond then {} else {}");
+  EXPECT_TOKEN(Tokens[3], tok::l_brace, TT_ControlStatementLBrace);
+  EXPECT_TOKEN(Tokens[6], tok::l_brace, TT_ElseLBrace);
+  Tokens = Annotate("defset Foo Def2 = {}");
+  EXPECT_TOKEN(Tokens[4], tok::l_brace, TT_FunctionLBrace);
 }
 
 TEST_F(TokenAnnotatorTest, UnderstandConstructors) {