clang-format: Separate out a language kind for ObjC.

While C(++) and ObjC are generally formatted the same way and can be
mixed, people might want to choose different styles based on the
language. This patch recognizes .m and .mm files as ObjC and also
implements a very crude detection of whether or not a .h file contains
ObjC code. This can be improved over time.

Also move most of the ObjC tests into their own test file to keep file
size maintainable.

llvm-svn: 289428

4 files changed, 23 insertions, 4 deletions

diff --git a/clang/lib/Format/ContinuationIndenter.cpp b/clang/lib/Format/ContinuationIndenter.cpp
index 404e3a3b4ad..aa6f37bd199 100644
--- a/clang/lib/Format/ContinuationIndenter.cpp
+++ b/clang/lib/Format/ContinuationIndenter.cpp
@@ -560,6 +560,7 @@ unsigned ContinuationIndenter::addTokenOnNewLine(LineState &State,
   // and we need to avoid bin packing there.
   bool NestedBlockSpecialCase =
       Style.Language != FormatStyle::LK_Cpp &&
+      Style.Language != FormatStyle::LK_ObjC &&
       Current.is(tok::r_brace) && State.Stack.size() > 1 &&
       State.Stack[State.Stack.size() - 2].NestedBlockInlined;
   if (!NestedBlockSpecialCase)
diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index bcea5ac411a..4879d1e818c 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -52,6 +52,7 @@ template <> struct ScalarEnumerationTraits<FormatStyle::LanguageKind> {
     IO.enumCase(Value, "Cpp", FormatStyle::LK_Cpp);
     IO.enumCase(Value, "Java", FormatStyle::LK_Java);
     IO.enumCase(Value, "JavaScript", FormatStyle::LK_JavaScript);
+    IO.enumCase(Value, "ObjC", FormatStyle::LK_ObjC);
     IO.enumCase(Value, "Proto", FormatStyle::LK_Proto);
     IO.enumCase(Value, "TableGen", FormatStyle::LK_TableGen);
   }
@@ -623,6 +624,8 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) {
   } else if (Language == FormatStyle::LK_Proto) {
     GoogleStyle.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_None;
     GoogleStyle.SpacesInContainerLiterals = false;
+  } else if (Language == FormatStyle::LK_ObjC) {
+    GoogleStyle.ColumnLimit = 100;
   }
 
   return GoogleStyle;
@@ -1861,6 +1864,8 @@ static FormatStyle::LanguageKind getLanguageByFileName(StringRef FileName) {
     return FormatStyle::LK_Java;
   if (FileName.endswith_lower(".js") || FileName.endswith_lower(".ts"))
     return FormatStyle::LK_JavaScript; // JavaScript or TypeScript.
+  if (FileName.endswith(".m") || FileName.endswith(".mm"))
+    return FormatStyle::LK_ObjC;
   if (FileName.endswith_lower(".proto") ||
       FileName.endswith_lower(".protodevel"))
     return FormatStyle::LK_Proto;
@@ -1870,12 +1875,21 @@ static FormatStyle::LanguageKind getLanguageByFileName(StringRef FileName) {
 }
 
 FormatStyle getStyle(StringRef StyleName, StringRef FileName,
-                     StringRef FallbackStyle, vfs::FileSystem *FS) {
+                     StringRef FallbackStyle, StringRef Code,
+                     vfs::FileSystem *FS) {
   if (!FS) {
     FS = vfs::getRealFileSystem().get();
   }
   FormatStyle Style = getLLVMStyle();
   Style.Language = getLanguageByFileName(FileName);
+
+  // This is a very crude detection of whether a header contains ObjC code that
+  // should be improved over time and probably be done on tokens, not one the
+  // bare content of the file.
+  if (Style.Language == FormatStyle::LK_Cpp && FileName.endswith(".h") &&
+      (Code.contains("\n- (") || Code.contains("\n+ (")))
+    Style.Language = FormatStyle::LK_ObjC;
+
   if (!getPredefinedStyle(FallbackStyle, Style.Language, &Style)) {
     llvm::errs() << "Invalid fallback style \"" << FallbackStyle
                  << "\" using LLVM style\n";
diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp
index 2aa48e3f491..46a32a917dd 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -558,7 +558,8 @@ FormatToken *FormatTokenLexer::getNextToken() {
     Column = FormatTok->LastLineColumnWidth;
   }
 
-  if (Style.Language == FormatStyle::LK_Cpp) {
+  if (Style.Language == FormatStyle::LK_Cpp ||
+      Style.Language == FormatStyle::LK_ObjC) {
     if (!(Tokens.size() > 0 && Tokens.back()->Tok.getIdentifierInfo() &&
           Tokens.back()->Tok.getIdentifierInfo()->getPPKeywordID() ==
               tok::pp_define) &&
diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp
index 57f30276b36..4db0e937afc 100644
--- a/clang/lib/Format/TokenAnnotator.cpp
+++ b/clang/lib/Format/TokenAnnotator.cpp
@@ -317,7 +317,8 @@ private:
          Contexts.back().InTemplateArgument);
 
     bool StartsObjCMethodExpr =
-        !CppArrayTemplates && Style.Language == FormatStyle::LK_Cpp &&
+        !CppArrayTemplates && (Style.Language == FormatStyle::LK_Cpp ||
+                               Style.Language == FormatStyle::LK_ObjC) &&
         Contexts.back().CanBeExpression && Left->isNot(TT_LambdaLSquare) &&
         CurrentToken->isNot(tok::l_brace) &&
         (!Parent ||
@@ -433,7 +434,8 @@ private:
           FormatToken *Previous = CurrentToken->getPreviousNonComment();
           if (((CurrentToken->is(tok::colon) &&
                 (!Contexts.back().ColonIsDictLiteral ||
-                 Style.Language != FormatStyle::LK_Cpp)) ||
+                 (Style.Language != FormatStyle::LK_Cpp &&
+                  Style.Language != FormatStyle::LK_ObjC))) ||
                Style.Language == FormatStyle::LK_Proto) &&
               (Previous->Tok.getIdentifierInfo() ||
                Previous->is(tok::string_literal)))
@@ -1174,6 +1176,7 @@ private:
   bool rParenEndsCast(const FormatToken &Tok) {
     // C-style casts are only used in C++ and Java.
     if (Style.Language != FormatStyle::LK_Cpp &&
+        Style.Language != FormatStyle::LK_ObjC &&
         Style.Language != FormatStyle::LK_Java)
       return false;