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>

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@174081 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Lex/Lexer.cpp b/lib/Lex/Lexer.cpp
index 4b5a3135c363cf342ce2e904d8367a0d6f1a78bc..1b064c88ff89402a10bee54cfba7c448ca644c54 100644 (file)
--- a/lib/Lex/Lexer.cpp
+++ b/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;

diff --git a/test/Lexer/unicode.c b/test/Lexer/unicode.c
index 26e77f61fdd092256932653429eafbdab80f59b8..de758f179a41ff42bf136d1f6ba364ba61dc4906 100644 (file)
--- a/test/Lexer/unicode.c
+++ b/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

diff --git a/test/Lexer/utf8-invalid.c b/test/Lexer/utf8-invalid.c
index a387ff776f43388edca6564ab43de567c7d19daf..2657b54c374efed28dd57719a556b35c65288b20 100644 (file)
--- a/test/Lexer/utf8-invalid.c
+++ b/test/Lexer/utf8-invalid.c
@@ -9,3 +9,7 @@ extern int 
 // Don't warn about bad UTF-8 in raw lexing mode.
 extern int \82x;
 #endif
+
+// Don't warn about bad UTF-8 in preprocessor directives.
+#define x82 \82
+#pragma mark \82