Lexer: Don't warn about Unicode in preprocessor directives.

This allows people to use Unicode in their #pragma mark and in macros
that exist only to be string-ized.

<rdar://problem/13107323&13121362>

llvm-svn: 174081

clang/lib/Lex/Lexer.cpp

@@ -2832,7 +2832,8 @@ void Lexer::LexUnicode(Token &Result, uint32_t C, const char *CurPtr) {
     return LexIdentifier(Result, CurPtr);
   }
 
-  if (!isLexingRawMode() && !PP->isPreprocessedOutput() &&
+  if (!isLexingRawMode() && !ParsingPreprocessorDirective &&
+      !PP->isPreprocessedOutput() &&
       !isASCII(*BufferPtr) && !isAllowedIDChar(C)) {
     // Non-ASCII characters tend to creep into source code unintentionally.
     // Instead of letting the parser complain about the unknown token,
@@ -3537,7 +3538,8 @@ LexNextToken:
     if (Status == conversionOK)
       return LexUnicode(Result, CodePoint, CurPtr);
     
-    if (isLexingRawMode() || PP->isPreprocessedOutput()) {
+    if (isLexingRawMode() || ParsingPreprocessorDirective ||
+        PP->isPreprocessedOutput()) {
       ++CurPtr;
       Kind = tok::unknown;
       break;

clang/test/Lexer/unicode.c

@@ -10,6 +10,17 @@ extern int　x; // expected-warning {{treating Unicode character as whitespace}}
 // CHECK: extern int {{x}}
 // CHECK: extern int　{{x}}
 
+#pragma mark ¡Unicode!
+
+#define COPYRIGHT Copyright © 2012
+#define XSTR(X) #X
+#define STR(X) XSTR(X)
+
+static const char *copyright = STR(COPYRIGHT); // no-warning
+// CHECK: static const char *copyright = "Copyright © {{2012}}";
+
 #if PP_ONLY
+COPYRIGHT
+// CHECK: Copyright © {{2012}}
 CHECK: The preprocessor should not complain about Unicode characters like ©.
 #endif

clang/test/Lexer/utf8-invalid.c

@@ -9,3 +9,7 @@ extern int
 // Don't warn about bad UTF-8 in raw lexing mode.
 extern int ‚x;
 #endif
+
+// Don't warn about bad UTF-8 in preprocessor directives.
+#define x82 ‚
+#pragma mark ‚