[clang-format] Improve ObjC headers detection

[jolesiak]

Summary

Detect ObjC characteristic types when they start a line and add additional keywords.

[jolesiak]

Add NSBundle.

[benhamilton]

[jolesiak]

This comment was removed by jolesiak.

[jolesiak]

Added support for ObjC characteristic keywords starting a new line.

lib/Format/Format.cpp

private:
   static bool guessIsObjC(const SmallVectorImpl<AnnotatedLine *> &AnnotatedLines,
                           const AdditionalKeywords &Keywords) {
     // Keep this array sorted, since we are binary searching over it.
     static constexpr llvm::StringLiteral FoundationIdentifiers[] = {
         "CGFloat",
         "NSAffineTransform",
         "NSArray",
         "NSAttributedString",
+        "NSBundle",
         "NSCache",
+        "NSCalendar",
         "NSCharacterSet",
         "NSCountedSet",
         "NSData",
         "NSDataDetector",
         "NSDecimal",
         "NSDecimalNumber",
         "NSDictionary",
         "NSEdgeInsets",
static constexpr llvm::StringLiteral FoundationIdentifiers[] = {
         "NSMutableData",
         "NSMutableDictionary",
         "NSMutableIndexSet",
         "NSMutableOrderedSet",
         "NSMutableSet",
         "NSMutableString",
         "NSNumber",
         "NSNumberFormatter",
+        "NSObject",
         "NSOrderedSet",
         "NSPoint",
         "NSPointerArray",
         "NSRange",
         "NSRect",
         "NSRegularExpression",
         "NSSet",
         "NSSize",
         "NSString",
+        "NSTimeZone",
         "NSUInteger",
         "NSURL",
         "NSURLComponents",
         "NSURLQueryItem",
         "NSUUID",
+        "NSValue",
     };
 
     for (auto &Line : AnnotatedLines) {
-      for (FormatToken *FormatTok = Line->First->Next; FormatTok;
+      for (FormatToken *FormatTok = Line->First; FormatTok;
            FormatTok = FormatTok->Next) {
-        if ((FormatTok->Previous->is(tok::at) &&
+        if ((FormatTok->Previous && FormatTok->Previous->is(tok::at) &&
              (FormatTok->isObjCAtKeyword(tok::objc_interface) ||
               FormatTok->isObjCAtKeyword(tok::objc_implementation) ||
               FormatTok->isObjCAtKeyword(tok::objc_protocol) ||
               FormatTok->isObjCAtKeyword(tok::objc_end) ||
               FormatTok->isOneOf(tok::numeric_constant, tok::l_square,
                                  tok::l_brace))) ||
             (FormatTok->Tok.isAnyIdentifier() &&
              std::binary_search(std::begin(FoundationIdentifiers),

unittests/Format/FormatTestObjC.cpp

TEST(FormatTestObjCStyle, DetectsObjCInHeaders) {
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
 
   Style = getStyle("{}", "a.h", "none",
                    "const int protocol = 1;\nconst int end = 2;\n");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_Cpp, Style->Language);
 
-  Style = getStyle("{}", "a.h", "none", "extern NSString *kFoo;\n");
-  ASSERT_TRUE((bool)Style);
-  EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
-
   Style =
       getStyle("{}", "a.h", "none", "typedef NS_ENUM(NSInteger, Foo) {};\n");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
 
   Style = getStyle("{}", "a.h", "none", "enum Foo {};");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_Cpp, Style->Language);
 
-  Style = getStyle("{}", "a.h", "none", "extern NSInteger Foo();\n");
-  ASSERT_TRUE((bool)Style);
-  EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
-
   Style =
       getStyle("{}", "a.h", "none", "inline void Foo() { Log(@\"Foo\"); }\n");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
 
   Style =
       getStyle("{}", "a.h", "none", "inline void Foo() { Log(\"Foo\"); }\n");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_Cpp, Style->Language);
 
   Style =
       getStyle("{}", "a.h", "none", "inline void Foo() { id = @[1, 2, 3]; }\n");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
 
   Style = getStyle("{}", "a.h", "none",
                    "inline void Foo() { id foo = @{1: 2, 3: 4, 5: 6}; }\n");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
 
   Style = getStyle("{}", "a.h", "none",
                    "inline void Foo() { int foo[] = {1, 2, 3}; }\n");
   ASSERT_TRUE((bool)Style);
   EXPECT_EQ(FormatStyle::LK_Cpp, Style->Language);
+
+  // ObjC characteristic types.
+  Style = getStyle("{}", "a.h", "none", "extern NSString *kFoo;\n");
+  ASSERT_TRUE((bool)Style);
+  EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
+
+  Style = getStyle("{}", "a.h", "none", "extern NSInteger Foo();\n");
+  ASSERT_TRUE((bool)Style);
+  EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
+
+  Style = getStyle("{}", "a.h", "none", "NSObject *Foo();\n");
+  ASSERT_TRUE((bool)Style);
+  EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
+
+  Style = getStyle("{}", "a.h", "none", "NSSet *Foo();\n");
+  ASSERT_TRUE((bool)Style);
+  EXPECT_EQ(FormatStyle::LK_ObjC, Style->Language);
 }
 
 TEST_F(FormatTestObjC, FormatObjCTryCatch) {
   verifyFormat("@try {\n"
                "  f();\n"
                "} @catch (NSException e) {\n"
                "  @throw;\n"
                "} @finally {\n"