[Sema] Handle UTF-8 invalid format string specifiers

Improve invalid format string specifier handling by printing out
invalid specifiers characters with \x, \u and \U. Previously clang
would print gargabe whenever the character is unprintable.

Example, before:
  NSLog(@"%\u25B9"); => warning: invalid conversion specifier ' [-Wformat-invalid-specifier]
after:
  NSLog(@"%\u25B9"); => warning: invalid conversion specifier '\u25b9' [-Wformat-invalid-specifier]

Differential Revision: http://reviews.llvm.org/D18296

rdar://problem/24672159

llvm-svn: 264752

1 files changed, 6 insertions, 1 deletions

diff --git a/clang/lib/Analysis/PrintfFormatString.cpp b/clang/lib/Analysis/PrintfFormatString.cpp
index f0976bce972..fb5df61c5ed 100644
--- a/clang/lib/Analysis/PrintfFormatString.cpp
+++ b/clang/lib/Analysis/PrintfFormatString.cpp
@@ -312,8 +312,13 @@ static PrintfSpecifierResult ParsePrintfSpecifier(FormatStringHandler &H,
     argIndex++;
 
   if (k == ConversionSpecifier::InvalidSpecifier) {
+    unsigned Len = I - Start;
+    if (ParseUTF8InvalidSpecifier(Start, E, Len)) {
+      CS.setEndScanList(Start + Len);
+      FS.setConversionSpecifier(CS);
+    }
     // Assume the conversion takes one argument.
-    return !H.HandleInvalidPrintfConversionSpecifier(FS, Start, I - Start);
+    return !H.HandleInvalidPrintfConversionSpecifier(FS, Start, Len);
   }
   return PrintfSpecifierResult(Start, FS);
 }