[clang-format]: Annotate colons found in inline assembly (#92617)

Short-circuit the parsing of tok::colon to label colons found within
lines starting with asm as InlineASMColon.

Fixes #92616.

---------

Co-authored-by: Owen Pan <[email protected]>

Author: gedare

clang/lib/Format/TokenAnnotator.cpp

@@ -1358,6 +1358,8 @@ class AnnotatingParser {
           Line.First->startsSequence(tok::kw_export, Keywords.kw_module) ||
           Line.First->startsSequence(tok::kw_export, Keywords.kw_import)) {
         Tok->setType(TT_ModulePartitionColon);
+      } else if (Line.First->is(tok::kw_asm)) {
+        Tok->setType(TT_InlineASMColon);
       } else if (Contexts.back().ColonIsDictLiteral || Style.isProto()) {
         Tok->setType(TT_DictLiteral);
         if (Style.Language == FormatStyle::LK_TextProto) {
@@ -1425,13 +1427,6 @@ class AnnotatingParser {
         // This handles a special macro in ObjC code where selectors including
         // the colon are passed as macro arguments.
         Tok->setType(TT_ObjCMethodExpr);
-      } else if (Contexts.back().ContextKind == tok::l_paren &&
-                 !Line.InPragmaDirective) {
-        if (Style.isTableGen() && Contexts.back().IsTableGenDAGArg) {
-          Tok->setType(TT_TableGenDAGArgListColon);
-          break;
-        }
-        Tok->setType(TT_InlineASMColon);
       }
       break;
     case tok::pipe:

clang/unittests/Format/TokenAnnotatorTest.cpp

@@ -1496,12 +1496,82 @@ TEST_F(TokenAnnotatorTest, RequiresDoesNotChangeParsingOfTheRest) {
 
 TEST_F(TokenAnnotatorTest, UnderstandsAsm) {
   auto Tokens = annotate("__asm{\n"
-                         "a:\n"
-                         "};");
-  ASSERT_EQ(Tokens.size(), 7u) << Tokens;
+                         "\"a\":\n"
+                         ": x\n"
+                         ":};");
+  ASSERT_EQ(Tokens.size(), 10u) << Tokens;
   EXPECT_TOKEN(Tokens[0], tok::kw_asm, TT_Unknown);
   EXPECT_TOKEN(Tokens[1], tok::l_brace, TT_InlineASMBrace);
-  EXPECT_TOKEN(Tokens[4], tok::r_brace, TT_InlineASMBrace);
+  EXPECT_TOKEN(Tokens[3], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[4], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[6], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[7], tok::r_brace, TT_InlineASMBrace);
+
+  Tokens = annotate("__asm(\n"
+                    "\"a\":\n"
+                    ": x\n"
+                    ":);");
+  ASSERT_EQ(Tokens.size(), 10u) << Tokens;
+  EXPECT_TOKEN(Tokens[0], tok::kw_asm, TT_Unknown);
+  EXPECT_TOKEN(Tokens[3], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[4], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[6], tok::colon, TT_InlineASMColon);
+
+  Tokens = annotate("asm volatile (\n"
+                    "\"a_label:\"\n"
+                    ":\n"
+                    ": x\n"
+                    ":);");
+  ASSERT_EQ(Tokens.size(), 11u) << Tokens;
+  EXPECT_TOKEN(Tokens[0], tok::kw_asm, TT_Unknown);
+  EXPECT_TOKEN(Tokens[4], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[5], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[7], tok::colon, TT_InlineASMColon);
+
+  Tokens = annotate("__asm__(\n"
+                    "\"a_label:\"\n"
+                    ": x\n"
+                    ":\n"
+                    ": y);");
+  ASSERT_EQ(Tokens.size(), 11u) << Tokens;
+  EXPECT_TOKEN(Tokens[0], tok::kw_asm, TT_Unknown);
+  EXPECT_TOKEN(Tokens[3], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[5], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[6], tok::colon, TT_InlineASMColon);
+
+  Tokens = annotate("__asm volatile (\n"
+                    "\"a_label:\"\n"
+                    "\"a b c(%%x)\"\n"
+                    ":\n"
+                    ": x\n"
+                    ":);");
+  ASSERT_EQ(Tokens.size(), 12u) << Tokens;
+  EXPECT_TOKEN(Tokens[0], tok::kw_asm, TT_Unknown);
+  EXPECT_TOKEN(Tokens[5], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[6], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[8], tok::colon, TT_InlineASMColon);
+
+  Tokens = annotate("asm(\n"
+                    "\"insn\"\n"
+                    ": \"=r\" (var1), \"=&r\" (value)\n"
+                    ":\n"
+                    ": \"memory\");");
+  ASSERT_EQ(Tokens.size(), 19u) << Tokens;
+  EXPECT_TOKEN(Tokens[0], tok::kw_asm, TT_Unknown);
+  EXPECT_TOKEN(Tokens[3], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[13], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[14], tok::colon, TT_InlineASMColon);
+
+  Tokens = annotate("__asm__ volatile (\n"
+                    "\"ldr r1, [r0, %%[sym]]\"\n"
+                    ":\n"
+                    ": [sym] \"J\" (aaaaa(aaaa, aaaa))\n"
+                    ");");
+  ASSERT_EQ(Tokens.size(), 21u) << Tokens;
+  EXPECT_TOKEN(Tokens[0], tok::kw_asm, TT_Unknown);
+  EXPECT_TOKEN(Tokens[4], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[5], tok::colon, TT_InlineASMColon);
+  EXPECT_TOKEN(Tokens[6], tok::l_square, TT_InlineASMSymbolicNameLSquare);
 }
 
 TEST_F(TokenAnnotatorTest, UnderstandsObjCBlock) {