[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

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@264752 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 8 insertions, 3 deletions

diff --git a/lib/Analysis/ScanfFormatString.cpp b/lib/Analysis/ScanfFormatString.cpp
index d484d8e828..82b038864c 100644
--- a/lib/Analysis/ScanfFormatString.cpp
+++ b/lib/Analysis/ScanfFormatString.cpp
@@ -79,7 +79,7 @@ static ScanfSpecifierResult ParseScanfSpecifier(FormatStringHandler &H,
                                                 unsigned &argIndex,
                                                 const LangOptions &LO,
                                                 const TargetInfo &Target) {
-  
+  using namespace clang::analyze_format_string;
   using namespace clang::analyze_scanf;
   const char *I = Beg;
   const char *Start = nullptr;
@@ -210,10 +210,15 @@ static ScanfSpecifierResult ParseScanfSpecifier(FormatStringHandler &H,
   
   // FIXME: '%' and '*' doesn't make sense.  Issue a warning.
   // FIXME: 'ConsumedSoFar' and '*' doesn't make sense.
-  
+
   if (k == ScanfConversionSpecifier::InvalidSpecifier) {
+    unsigned Len = I - Beg;
+    if (ParseUTF8InvalidSpecifier(Beg, E, Len)) {
+      CS.setEndScanList(Beg + Len);
+      FS.setConversionSpecifier(CS);
+    }
     // Assume the conversion takes one argument.
-    return !H.HandleInvalidScanfConversionSpecifier(FS, Beg, I - Beg);
+    return !H.HandleInvalidScanfConversionSpecifier(FS, Beg, Len);
   }
   return ScanfSpecifierResult(Start, FS);
 }