Fix r173881 to properly skip invalid UTF-8 characters in raw lexing and -E.

This caused hangs as we processed the same invalid byte over and over.

<rdar://problem/13115651>

llvm-svn: 173959

2 files changed, 7 insertions, 0 deletions

diff --git a/clang/lib/Lex/Lexer.cpp b/clang/lib/Lex/Lexer.cpp
index 6a918d6a3ad..4b5a3135c36 100644
--- a/clang/lib/Lex/Lexer.cpp
+++ b/clang/lib/Lex/Lexer.cpp
@@ -3538,6 +3538,7 @@ LexNextToken:
       return LexUnicode(Result, CodePoint, CurPtr);
     
     if (isLexingRawMode() || PP->isPreprocessedOutput()) {
+      ++CurPtr;
       Kind = tok::unknown;
       break;
     }
diff --git a/clang/test/Lexer/utf8-invalid.c b/clang/test/Lexer/utf8-invalid.c
index c4dd318e786..f9d2b59a6bd 100644
--- a/clang/test/Lexer/utf8-invalid.c
+++ b/clang/test/Lexer/utf8-invalid.c
@@ -1,6 +1,12 @@
 // RUN: %clang_cc1 -fsyntax-only -verify %s
+// RUN: %clang_cc1 -E %s -o /dev/null
 
 // Note: this file contains invalid UTF-8 before the variable name in the
 // next line. Please do not fix!
 
 extern int ‚x; // expected-error{{source file is not valid UTF-8}}
+
+#if 0
+// Don't warn about bad UTF-8 in raw lexing mode.
+extern int ‚x;
+#endif