[clang-format] Handle NSString literals by merging tokens.

Summary:
This fixes a few outstanding bugs:
  * incorrect breaking of NSString literals containing double-width characters;
  * inconsistent formatting of ObjC dictionary literals containing NSString
    literals;
  * AlwaysBreakBeforeMultilineStrings ignoring implicitly-concatenated NSString
    literals.

Reviewers: djasper

Reviewed By: djasper

Subscribers: klimek, cfe-commits

Differential Revision: https://reviews.llvm.org/D31706

llvm-svn: 299927

1 files changed, 18 insertions, 0 deletions

diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp
index 91c9af005a2..9415dbe9ab3 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -64,6 +64,8 @@ void FormatTokenLexer::tryMergePreviousTokens() {
     return;
   if (tryMergeLessLess())
     return;
+  if (tryMergeNSStringLiteral())
+    return;
 
   if (Style.Language == FormatStyle::LK_JavaScript) {
     static const tok::TokenKind JSIdentity[] = {tok::equalequal, tok::equal};
@@ -84,6 +86,22 @@ void FormatTokenLexer::tryMergePreviousTokens() {
   }
 }
 
+bool FormatTokenLexer::tryMergeNSStringLiteral() {
+  if (Tokens.size() < 2)
+    return false;
+  auto &At = *(Tokens.end() - 2);
+  auto &String = *(Tokens.end() - 1);
+  if (!At->is(tok::at) || !String->is(tok::string_literal))
+    return false;
+  At->Tok.setKind(tok::string_literal);
+  At->TokenText = StringRef(At->TokenText.begin(),
+                            String->TokenText.end() - At->TokenText.begin());
+  At->ColumnWidth += String->ColumnWidth;
+  At->Type = TT_ObjCStringLiteral;
+  Tokens.erase(Tokens.end() - 1);
+  return true;
+}
+
 bool FormatTokenLexer::tryMergeLessLess() {
   // Merge X,less,less,Y into X,lessless,Y unless X or Y is less.
   if (Tokens.size() < 3)