[clang-format] Fix preprocessor nesting after commit 529aa4b011c4ae808d658022ef643c44...

In https://github.com/llvm/llvm-project/commit/529aa4b011c4ae808d658022ef643c44dd9b2c9c
by setting the identifier info to nullptr, we started to subtly
interfere with the parts in the beginning of the function,
https://github.com/llvm/llvm-project/blob/529aa4b011c4ae808d658022ef643c44dd9b2c9c/clang/lib/Format/UnwrappedLineParser.cpp#L991
causing the preprocessor nesting to change in some cases. E.g., for the
added regression test, clang-format started incorrectly guessing the
language as C++.

This tries to address this by introducing an internal identifier info
element to use instead.

Reviewed By: curdeius, MyDeveloperDay

Differential Revision: https://reviews.llvm.org/D120315

diff --git a/clang/lib/Format/FormatToken.h b/clang/lib/Format/FormatToken.h
index 5f05986..bd1d447 100644 (file)
--- a/clang/lib/Format/FormatToken.h
+++ b/clang/lib/Format/FormatToken.h
@@ -949,6 +949,10 @@ struct AdditionalKeywords {
     kw_slots = &IdentTable.get("slots");
     kw_qslots = &IdentTable.get("Q_SLOTS");
 
+    // For internal clang-format use.
+    kw_internal_ident_after_define =
+        &IdentTable.get("__CLANG_FORMAT_INTERNAL_IDENT_AFTER_DEFINE__");
+
     // C# keywords
     kw_dollar = &IdentTable.get("dollar");
     kw_base = &IdentTable.get("base");
@@ -1069,6 +1073,9 @@ struct AdditionalKeywords {
   IdentifierInfo *kw_slots;
   IdentifierInfo *kw_qslots;
 
+  // For internal use by clang-format.
+  IdentifierInfo *kw_internal_ident_after_define;
+
   // C# keywords
   IdentifierInfo *kw_dollar;
   IdentifierInfo *kw_base;

diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp
index 7d29afb..09e209e 100644 (file)
--- a/clang/lib/Format/UnwrappedLineParser.cpp
+++ b/clang/lib/Format/UnwrappedLineParser.cpp
@@ -1089,9 +1089,10 @@ void UnwrappedLineParser::parsePPDefine() {
   // In the context of a define, even keywords should be treated as normal
   // identifiers. Setting the kind to identifier is not enough, because we need
   // to treat additional keywords like __except as well, which are already
-  // identifiers.
+  // identifiers. Setting the identifier info to null interferes with include
+  // guard processing above, and changes preprocessing nesting.
   FormatTok->Tok.setKind(tok::identifier);
-  FormatTok->Tok.setIdentifierInfo(nullptr);
+  FormatTok->Tok.setIdentifierInfo(Keywords.kw_internal_ident_after_define);
   nextToken();
   if (FormatTok->Tok.getKind() == tok::l_paren &&
       !FormatTok->hasWhitespaceBefore())

diff --git a/clang/unittests/Format/FormatTest.cpp b/clang/unittests/Format/FormatTest.cpp
index 51f6239..7d8b74c 100644 (file)
--- a/clang/unittests/Format/FormatTest.cpp
+++ b/clang/unittests/Format/FormatTest.cpp
@@ -22724,6 +22724,13 @@ TEST_F(FormatTest, FileAndCode) {
   EXPECT_EQ(
       FormatStyle::LK_Cpp,
       guessLanguage("foo.h", "#define FOO(...) auto bar = [] __VA_ARGS__;"));
+  // Only one of the two preprocessor regions has ObjC-like code.
+  EXPECT_EQ(FormatStyle::LK_ObjC,
+            guessLanguage("foo.h", "#if A\n"
+                                   "#define B() C\n"
+                                   "#else\n"
+                                   "#define B() [NSString a:@\"\"]\n"
+                                   "#endif\n"));
 }
 
 TEST_F(FormatTest, GuessLanguageWithCpp11AttributeSpecifiers) {