use the full spelling of a string literal token so that trigraphs

and escaped newlines don't throw off the offset computation.

On this testcase:
  printf("abc\
def"
         "%*d", (unsigned) 1, 1);

Before:
t.m:5:5: warning: field width should have type 'int', but argument has type 'unsigned int'
def"
    ^

after:
t.m:6:12: warning: field width should have type 'int', but argument has type 'unsigned int'
         "%*d", (unsigned) 1, 1);
           ^    ~~~~~~~~~~~~

llvm-svn: 64930

1 files changed, 8 insertions, 1 deletions

diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index f469684e503..6ffca1b7b87 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -31,6 +31,8 @@ SourceLocation Sema::getLocationOfStringLiteralByte(const StringLiteral *SL,
                                                     unsigned ByteNo) const {
   assert(!SL->isWide() && "This doesn't work for wide strings yet");
   
+  llvm::SmallString<32> SpellingBuffer;
+  
   // Loop over all of the tokens in this string until we find the one that
   // contains the byte we're looking for.
   unsigned TokNo = 0;
@@ -61,8 +63,13 @@ SourceLocation Sema::getLocationOfStringLiteralByte(const StringLiteral *SL,
     Token TheTok;
     TheLexer.LexFromRawLexer(TheTok);
     
+    // Get the spelling of the token to remove trigraphs and escaped newlines.
+    SpellingBuffer.resize(TheTok.getLength());
+    const char *SpellingPtr = &SpellingBuffer[0];
+    unsigned TokLen = PP.getSpelling(TheTok, SpellingPtr);
+    
     // The length of the string is the token length minus the two quotes.
-    unsigned TokNumBytes = TheTok.getLength()-2;
+    unsigned TokNumBytes = TokLen-2;
     
     // If we found the token we're looking for, return the location.
     // FIXME: This should consider character escapes!