Author: sstwcw Date: 2025-03-31T13:54:49Z New Revision: ab7cee8a0ecf29fdb47c64c8d431a694d63390d2
URL: https://github.com/llvm/llvm-project/commit/ab7cee8a0ecf29fdb47c64c8d431a694d63390d2 DIFF: https://github.com/llvm/llvm-project/commit/ab7cee8a0ecf29fdb47c64c8d431a694d63390d2.diff LOG: [clang-format] Handle C++ keywords in other languages better (#132941) There is some code to make sure that C++ keywords that are identifiers in the other languages are not treated as keywords. Right now, the kind is set to identifier, and the identifier info is cleared. The latter is probably so that the code for identifying C++ structures does not recognize those structures by mistake when formatting a language that does not have those structures. But we did not find an instance where the language can have the sequence of tokens, the code tries to parse the structure as if it is C++ using the identifier info instead of the token kind, but without checking for the language setting. However, there are places where the code checks whether the identifier info field is null or not. They are places where an identifier and a keyword are treated the same way. For example, the name of a function in JavaScript. This patch removes the lines that clear the identifier info. This way, a C++ keyword gets treated in the same way as an identifier in those places. JavaScript New ```JavaScript async function union( myparamnameiswaytooloooong) { } ``` Old ```JavaScript async function union( myparamnameiswaytooloooong) { } ``` Java New ```Java enum union { ABC, CDE } ``` Old ```Java enum union { ABC, CDE } ``` Added: Modified: clang/lib/Format/FormatTokenLexer.cpp clang/unittests/Format/FormatTestJS.cpp clang/unittests/Format/FormatTestJava.cpp Removed: ################################################################################ diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp index eed54a11684b5..014b10b206d90 100644 --- a/clang/lib/Format/FormatTokenLexer.cpp +++ b/clang/lib/Format/FormatTokenLexer.cpp @@ -1306,15 +1306,12 @@ FormatToken *FormatTokenLexer::getNextToken() { FormatTok->isOneOf(tok::kw_struct, tok::kw_union, tok::kw_delete, tok::kw_operator)) { FormatTok->Tok.setKind(tok::identifier); - FormatTok->Tok.setIdentifierInfo(nullptr); } else if (Style.isJavaScript() && FormatTok->isOneOf(tok::kw_struct, tok::kw_union, tok::kw_operator)) { FormatTok->Tok.setKind(tok::identifier); - FormatTok->Tok.setIdentifierInfo(nullptr); } else if (Style.isTableGen() && !Keywords.isTableGenKeyword(*FormatTok)) { FormatTok->Tok.setKind(tok::identifier); - FormatTok->Tok.setIdentifierInfo(nullptr); } } else if (FormatTok->is(tok::greatergreater)) { FormatTok->Tok.setKind(tok::greater); diff --git a/clang/unittests/Format/FormatTestJS.cpp b/clang/unittests/Format/FormatTestJS.cpp index 78c9f887a159b..3dae67fbcdfcb 100644 --- a/clang/unittests/Format/FormatTestJS.cpp +++ b/clang/unittests/Format/FormatTestJS.cpp @@ -828,12 +828,18 @@ TEST_F(FormatTestJS, AsyncFunctions) { "} "); // clang-format must not insert breaks between async and function, otherwise // automatic semicolon insertion may trigger (in particular in a class body). + auto Style = getGoogleJSStyleWithColumns(10); verifyFormat("async function\n" "hello(\n" " myparamnameiswaytooloooong) {\n" "}", "async function hello(myparamnameiswaytooloooong) {}", - getGoogleJSStyleWithColumns(10)); + Style); + verifyFormat("async function\n" + "union(\n" + " myparamnameiswaytooloooong) {\n" + "}", + Style); verifyFormat("class C {\n" " async hello(\n" " myparamnameiswaytooloooong) {\n" @@ -841,7 +847,7 @@ TEST_F(FormatTestJS, AsyncFunctions) { "}", "class C {\n" " async hello(myparamnameiswaytooloooong) {} }", - getGoogleJSStyleWithColumns(10)); + Style); verifyFormat("async function* f() {\n" " yield fetch(x);\n" "}"); @@ -1338,15 +1344,16 @@ TEST_F(FormatTestJS, WrapRespectsAutomaticSemicolonInsertion) { // The following statements must not wrap, as otherwise the program meaning // would change due to automatic semicolon insertion. // See http://www.ecma-international.org/ecma-262/5.1/#sec-7.9.1. - verifyFormat("return aaaaa;", getGoogleJSStyleWithColumns(10)); - verifyFormat("yield aaaaa;", getGoogleJSStyleWithColumns(10)); - verifyFormat("return /* hello! */ aaaaa;", getGoogleJSStyleWithColumns(10)); - verifyFormat("continue aaaaa;", getGoogleJSStyleWithColumns(10)); - verifyFormat("continue /* hello! */ aaaaa;", getGoogleJSStyleWithColumns(10)); - verifyFormat("break aaaaa;", getGoogleJSStyleWithColumns(10)); - verifyFormat("throw aaaaa;", getGoogleJSStyleWithColumns(10)); - verifyFormat("aaaaaaaaa++;", getGoogleJSStyleWithColumns(10)); - verifyFormat("aaaaaaaaa--;", getGoogleJSStyleWithColumns(10)); + auto Style =getGoogleJSStyleWithColumns(10); + verifyFormat("return aaaaa;", Style); + verifyFormat("yield aaaaa;", Style); + verifyFormat("return /* hello! */ aaaaa;", Style); + verifyFormat("continue aaaaa;", Style); + verifyFormat("continue /* hello! */ aaaaa;", Style); + verifyFormat("break aaaaa;", Style); + verifyFormat("throw aaaaa;", Style); + verifyFormat("aaaaaaaaa++;", Style); + verifyFormat("aaaaaaaaa--;", Style); verifyFormat("return [\n" " aaa\n" "];", @@ -1366,12 +1373,13 @@ TEST_F(FormatTestJS, WrapRespectsAutomaticSemicolonInsertion) { // Ideally the foo() bit should be indented relative to the async function(). verifyFormat("async function\n" "foo() {}", - getGoogleJSStyleWithColumns(10)); - verifyFormat("await theReckoning;", getGoogleJSStyleWithColumns(10)); - verifyFormat("some['a']['b']", getGoogleJSStyleWithColumns(10)); + Style); + verifyFormat("await theReckoning;", Style); + verifyFormat("some['a']['b']", Style); + verifyFormat("union['a']['b']", Style); verifyFormat("x = (a['a']\n" " ['b']);", - getGoogleJSStyleWithColumns(10)); + Style); verifyFormat("function f() {\n" " return foo.bar(\n" " (param): param is {\n" @@ -2500,6 +2508,10 @@ TEST_F(FormatTestJS, NonNullAssertionOperator) { TEST_F(FormatTestJS, CppKeywords) { // Make sure we don't mess stuff up because of C++ keywords. verifyFormat("return operator && (aa);"); + verifyFormat("enum operator {\n" + " A = 1,\n" + " B\n" + "}"); // .. or QT ones. verifyFormat("const slots: Slot[];"); // use the "!" assertion operator to validate that clang-format understands diff --git a/clang/unittests/Format/FormatTestJava.cpp b/clang/unittests/Format/FormatTestJava.cpp index 33998bc7ff858..e01c1d6d7e684 100644 --- a/clang/unittests/Format/FormatTestJava.cpp +++ b/clang/unittests/Format/FormatTestJava.cpp @@ -158,6 +158,8 @@ TEST_F(FormatTestJava, AnonymousClasses) { TEST_F(FormatTestJava, EnumDeclarations) { verifyFormat("enum SomeThing { ABC, CDE }"); + // A C++ keyword should not mess things up. + verifyFormat("enum union { ABC, CDE }"); verifyFormat("enum SomeThing {\n" " ABC,\n" " CDE,\n" _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
