When a bad UTF-8 encoding or bogus escape sequence is encountered in a

string literal, produce a diagnostic pointing at the erroneous character
range, not at the start of the literal.


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@163459 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 7 insertions, 3 deletions

diff --git a/include/clang/Basic/ConvertUTF.h b/include/clang/Basic/ConvertUTF.h
index 5be304b475..cdc42699e3 100644
--- a/include/clang/Basic/ConvertUTF.h
+++ b/include/clang/Basic/ConvertUTF.h
@@ -158,7 +158,9 @@ ConversionResult ConvertUTF32toUTF16 (
 
 Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
 
-Boolean isLegalUTF8String(const UTF8 *source, const UTF8 *sourceEnd);
+Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd);
+
+unsigned getNumBytesForUTF8(UTF8 firstByte);
 
 #ifdef __cplusplus
 }
@@ -174,11 +176,13 @@ namespace clang {
  * Convert an UTF8 StringRef to UTF8, UTF16, or UTF32 depending on
  * WideCharWidth. The converted data is written to ResultPtr, which needs to
  * point to at least WideCharWidth * (Source.Size() + 1) bytes. On success,
- * ResultPtr will point one after the end of the copied string.
+ * ResultPtr will point one after the end of the copied string. On failure,
+ * ResultPtr will not be changed, and ErrorPtr will be set to the location of
+ * the first character which could not be converted.
  * \return true on success.
  */
 bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
-                       char *&ResultPtr);
+                       char *&ResultPtr, const UTF8 *&ErrorPtr);
 
 /**
  * Convert an Unicode code point to UTF8 sequence.