r343040 - Don't emit "will be treated as an identifier character" warning for

[Richard Smith via cfe-commits]

Author: rsmith
Date: Tue Sep 25 15:34:45 2018
New Revision: 343040

URL: http://llvm.org/viewvc/llvm-project?rev=343040&view=rev
Log:
Don't emit "will be treated as an identifier character" warning for
UTF-8 characters that aren't identifier characters in the current
language mode.

Modified:
    cfe/trunk/lib/Lex/Lexer.cpp
    cfe/trunk/test/Lexer/unicode.c

Modified: cfe/trunk/lib/Lex/Lexer.cpp
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Lex/Lexer.cpp?rev=343040&r1=343039&r2=343040&view=diff
==============================================================================
--- cfe/trunk/lib/Lex/Lexer.cpp (original)
+++ cfe/trunk/lib/Lex/Lexer.cpp Tue Sep 25 15:34:45 2018
@@ -3085,6 +3085,8 @@ bool Lexer::LexUnicode(Token &Result, ui
       maybeDiagnoseIDCharCompat(PP->getDiagnostics(), C,
                                 makeCharRange(*this, BufferPtr, CurPtr),
                                 /*IsFirst=*/true);
+      maybeDiagnoseUTF8Homoglyph(PP->getDiagnostics(), C,
+                                 makeCharRange(*this, BufferPtr, CurPtr));
     }
 
     MIOpt.ReadToken();
@@ -3879,7 +3881,6 @@ LexNextToken:
     // We can't just reset CurPtr to BufferPtr because BufferPtr may point to
     // an escaped newline.
     --CurPtr;
-    const char *UTF8StartPtr = CurPtr;
     llvm::ConversionResult Status =
         llvm::convertUTF8Sequence((const llvm::UTF8 **)&CurPtr,
                                   (const llvm::UTF8 *)BufferEnd,
@@ -3894,9 +3895,6 @@ LexNextToken:
         // (We manually eliminate the tail call to avoid recursion.)
         goto LexNextToken;
       }
-      if (!isLexingRawMode())
-        maybeDiagnoseUTF8Homoglyph(PP->getDiagnostics(), CodePoint,
-                                   makeCharRange(*this, UTF8StartPtr, CurPtr));
       return LexUnicode(Result, CodePoint, CurPtr);
     }
 

Modified: cfe/trunk/test/Lexer/unicode.c
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Lexer/unicode.c?rev=343040&r1=343039&r2=343040&view=diff
==============================================================================
--- cfe/trunk/test/Lexer/unicode.c (original)
+++ cfe/trunk/test/Lexer/unicode.c Tue Sep 25 15:34:45 2018
@@ -45,3 +45,8 @@ int ⁠xx‍;
 // expected-warning at -3 {{identifier contains Unicode character <U+200D> that is invisible in some environments}}
 int foo​bar = 0; // expected-warning {{identifier contains Unicode character <U+200B> that is invisible in some environments}}
 int x = foobar; // expected-error {{undeclared identifier}}
+
+int ∣foo; // expected-error {{non-ASCII character}}
+#ifndef PP_ONLY
+#define ∶ x // expected-error {{macro name must be an identifier}}
+#endif