[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
diff --git a/clang/lib/Analysis/FormatStringParsing.h b/clang/lib/Analysis/FormatStringParsing.h
index e165296..8463fce 100644
--- a/clang/lib/Analysis/FormatStringParsing.h
+++ b/clang/lib/Analysis/FormatStringParsing.h
@@ -46,7 +46,13 @@
/// FormatSpecifier& argument, and false otherwise.
bool ParseLengthModifier(FormatSpecifier &FS, const char *&Beg, const char *E,
const LangOptions &LO, bool IsScanf = false);
-
+
+/// Returns true if the invalid specifier in \p SpecifierBegin is a UTF-8
+/// string; check that it won't go further than \p FmtStrEnd and write
+/// up the total size in \p Len.
+bool ParseUTF8InvalidSpecifier(const char *SpecifierBegin,
+ const char *FmtStrEnd, unsigned &Len);
+
template <typename T> class SpecifierResult {
T FS;
const char *Start;