[clang-format/ObjC] Use getIdentifierInfo() instead of tok::identifier

Summary:
Previously, we checked tokens for `tok::identifier` to see if they
were identifiers inside an Objective-C selector.

However, this missed C++ keywords like `new` and `delete`.

To fix this, this diff uses `getIdentifierInfo()` to find
identifiers or keywords inside Objective-C selectors.

Test Plan: New tests added. Ran tests with:
  % make -j16 FormatTests && ./tools/clang/unittests/Format/FormatTests

Reviewers: djasper, jolesiak

Reviewed By: djasper

Subscribers: klimek, cfe-commits

Differential Revision: https://reviews.llvm.org/D46143

llvm-svn: 331067

1 files changed, 21 insertions, 4 deletions

diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp
index 49e21520b70..475eadd9f4c 100644
--- a/clang/lib/Format/TokenAnnotator.cpp
+++ b/clang/lib/Format/TokenAnnotator.cpp
@@ -25,6 +25,21 @@ namespace format {
 
 namespace {
 
+/// \brief Returns \c true if the token can be used as an identifier in
+/// an Objective-C \c @selector, \c false otherwise.
+///
+/// Because getFormattingLangOpts() always lexes source code as
+/// Objective-C++, C++ keywords like \c new and \c delete are
+/// lexed as tok::kw_*, not tok::identifier, even for Objective-C.
+///
+/// For Objective-C and Objective-C++, both identifiers and keywords
+/// are valid inside @selector(...) (or a macro which
+/// invokes @selector(...)). So, we allow treat any identifier or
+/// keyword as a potential Objective-C selector component.
+static bool canBeObjCSelectorComponent(const FormatToken &Tok) {
+  return Tok.Tok.getIdentifierInfo() != nullptr;
+}
+
 /// \brief A parser that gathers additional information about tokens.
 ///
 /// The \c TokenAnnotator tries to match parenthesis and square brakets and
@@ -703,9 +718,10 @@ private:
           Tok->Type = TT_CtorInitializerColon;
         else
           Tok->Type = TT_InheritanceColon;
-      } else if (Tok->Previous->is(tok::identifier) && Tok->Next &&
+      } else if (canBeObjCSelectorComponent(*Tok->Previous) && Tok->Next &&
                  (Tok->Next->isOneOf(tok::r_paren, tok::comma) ||
-                  Tok->Next->startsSequence(tok::identifier, tok::colon))) {
+                  (canBeObjCSelectorComponent(*Tok->Next) && Tok->Next->Next &&
+                   Tok->Next->Next->is(tok::colon)))) {
         // This handles a special macro in ObjC code where selectors including
         // the colon are passed as macro arguments.
         Tok->Type = TT_ObjCMethodExpr;
@@ -1346,7 +1362,7 @@ private:
                                          TT_LeadingJavaAnnotation)) {
         Current.Type = Current.Previous->Type;
       }
-    } else if (Current.isOneOf(tok::identifier, tok::kw_new) &&
+    } else if (canBeObjCSelectorComponent(Current) &&
                // FIXME(bug 36976): ObjC return types shouldn't use TT_CastRParen.
                Current.Previous && Current.Previous->is(TT_CastRParen) &&
                Current.Previous->MatchingParen &&
@@ -2650,7 +2666,7 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
   if (Line.Type == LT_ObjCMethodDecl) {
     if (Left.is(TT_ObjCMethodSpecifier))
       return true;
-    if (Left.is(tok::r_paren) && Right.isOneOf(tok::identifier, tok::kw_new))
+    if (Left.is(tok::r_paren) && canBeObjCSelectorComponent(Right))
       // Don't space between ')' and <id> or ')' and 'new'. 'new' is not a
       // keyword in Objective-C, and '+ (instancetype)new;' is a standard class
       // method declaration.
@@ -3128,6 +3144,7 @@ void TokenAnnotator::printDebugInfo(const AnnotatedLine &Line) {
     for (unsigned i = 0, e = Tok->FakeLParens.size(); i != e; ++i)
       llvm::errs() << Tok->FakeLParens[i] << "/";
     llvm::errs() << " FakeRParens=" << Tok->FakeRParens;
+    llvm::errs() << " II=" << Tok->Tok.getIdentifierInfo();
     llvm::errs() << " Text='" << Tok->TokenText << "'\n";
     if (!Tok->Next)
       assert(Tok == Line.Last);