Author: sstwcw Date: 2025-04-10T12:52:02Z New Revision: f7617f7f909102080f1a0cee46f8ca75ec8d14ff
URL: https://github.com/llvm/llvm-project/commit/f7617f7f909102080f1a0cee46f8ca75ec8d14ff DIFF: https://github.com/llvm/llvm-project/commit/f7617f7f909102080f1a0cee46f8ca75ec8d14ff.diff LOG: [clang-format] Recognize TableGen paste operator on separate line (#133722) Formatting this piece of code made the program crash. ``` class TypedVecListRegOperand<RegisterClass Reg, int lanes, string eltsize> : RegisterOperand<Reg, "printTypedVectorList<" # lanes # ", '" # eltsize # "'>">; ``` The line starting with the `#` was treated as a separate preprocessor directive line. Then the code dereferenced a null pointer when it tried to continue parsing the first line that did not end in a semicolon. Now the 2 problems are fixed. Added: Modified: clang/lib/Format/TokenAnnotator.cpp clang/lib/Format/UnwrappedLineParser.cpp clang/unittests/Format/FormatTestTableGen.cpp clang/unittests/Format/TokenAnnotatorTest.cpp Removed: ################################################################################ diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp index 46cd009da281e..d184c23123c34 100644 --- a/clang/lib/Format/TokenAnnotator.cpp +++ b/clang/lib/Format/TokenAnnotator.cpp @@ -948,6 +948,8 @@ class AnnotatingParser { HashTok->setType(TT_Unknown); if (!parseTableGenValue(ParseNameMode)) return false; + if (!CurrentToken) + return true; } // In name mode, '{' is regarded as the end of the value. // See TGParser::ParseValue in TGParser.cpp diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp index b49e80b0b89c8..60f4f30623baa 100644 --- a/clang/lib/Format/UnwrappedLineParser.cpp +++ b/clang/lib/Format/UnwrappedLineParser.cpp @@ -4842,9 +4842,16 @@ void UnwrappedLineParser::readToken(int LevelDifference) { PreviousWasComment = FormatTok->is(tok::comment); while (!Line->InPPDirective && FormatTok->is(tok::hash) && - (!Style.isVerilog() || - Keywords.isVerilogPPDirective(*Tokens->peekNextToken())) && FirstNonCommentOnLine) { + // In Verilog, the backtick is used for macro invocations. In TableGen, + // the single hash is used for the paste operator. + const auto *Next = Tokens->peekNextToken(); + if ((Style.isVerilog() && !Keywords.isVerilogPPDirective(*Next)) || + (Style.isTableGen() && + !Next->isOneOf(tok::kw_else, tok::pp_define, tok::pp_ifdef, + tok::pp_ifndef, tok::pp_endif))) { + break; + } distributeComments(Comments, FormatTok); Comments.clear(); // If there is an unfinished unwrapped line, we flush the preprocessor diff --git a/clang/unittests/Format/FormatTestTableGen.cpp b/clang/unittests/Format/FormatTestTableGen.cpp index 92377c31f2e91..1c3d187de393c 100644 --- a/clang/unittests/Format/FormatTestTableGen.cpp +++ b/clang/unittests/Format/FormatTestTableGen.cpp @@ -218,6 +218,13 @@ TEST_F(FormatTestTableGen, PasteOperator) { " string Z = [\"Traring\", \"Paste\", \"Traring\", \"Paste\",\n" " \"Traring\", \"Paste\"]#;\n" "}"); + + verifyFormat("def x#x {}", "def x\n" + "#x {}"); + verifyFormat("def x#x {}", "def x\n" + "#\n" + "x {}"); + verifyFormat("def x#x"); } TEST_F(FormatTestTableGen, ClassDefinition) { diff --git a/clang/unittests/Format/TokenAnnotatorTest.cpp b/clang/unittests/Format/TokenAnnotatorTest.cpp index 38dc10a08f640..2c7319ccefec2 100644 --- a/clang/unittests/Format/TokenAnnotatorTest.cpp +++ b/clang/unittests/Format/TokenAnnotatorTest.cpp @@ -2836,6 +2836,28 @@ TEST_F(TokenAnnotatorTest, UnderstandTableGenTokens) { Tokens = Annotate("!cond"); EXPECT_TOKEN(Tokens[0], tok::identifier, TT_TableGenCondOperator); + // The paste operator should not be treated as a preprocessor directive even + // if it is on a separate line. + Tokens = Annotate("def x\n" + "#embed {}"); + ASSERT_EQ(Tokens.size(), 7u) << Tokens; + EXPECT_TOKEN(Tokens[1], tok::identifier, TT_StartOfName); + EXPECT_EQ(Tokens[1]->Next, Tokens[2]); + Tokens = Annotate("def x\n" + "#define x\n" + "#embed {}"); + ASSERT_EQ(Tokens.size(), 10u) << Tokens; + EXPECT_TOKEN(Tokens[1], tok::identifier, TT_StartOfName); + EXPECT_EQ(Tokens[1]->Next, Tokens[5]); + Tokens = Annotate("def x\n" + "#ifdef x\n" + "#else\n" + "#endif\n" + "#embed {}"); + ASSERT_EQ(Tokens.size(), 14u) << Tokens; + EXPECT_TOKEN(Tokens[1], tok::identifier, TT_StartOfName); + EXPECT_EQ(Tokens[1]->Next, Tokens[9]); + auto AnnotateValue = [this, &Style](StringRef Code) { // Values are annotated only in specific context. auto Result = annotate(("def X { let V = " + Code + "; }").str(), Style); _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
