Support/ConvertUTF: implement U+FFFD insertion according to the recommendation

given in the Unicode spec

That is, replace every maximal subpart of an ill-formed subsequence with one
U+FFFD.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211015 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 13 insertions, 1 deletions

diff --git a/include/llvm/Support/ConvertUTF.h b/include/llvm/Support/ConvertUTF.h
index 282036619c..a184d0df21 100644
--- a/include/llvm/Support/ConvertUTF.h
+++ b/include/llvm/Support/ConvertUTF.h
@@ -136,7 +136,19 @@ ConversionResult ConvertUTF8toUTF16 (
   const UTF8** sourceStart, const UTF8* sourceEnd,
   UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
 
-ConversionResult ConvertUTF8toUTF32 (
+/**
+ * Convert a partial UTF8 sequence to UTF32.  If the sequence ends in an
+ * incomplete code unit sequence, returns \c sourceExhausted.
+ */
+ConversionResult ConvertUTF8toUTF32Partial(
+  const UTF8** sourceStart, const UTF8* sourceEnd,
+  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
+
+/**
+ * Convert a partial UTF8 sequence to UTF32.  If the sequence ends in an
+ * incomplete code unit sequence, returns \c sourceIllegal.
+ */
+ConversionResult ConvertUTF8toUTF32(
   const UTF8** sourceStart, const UTF8* sourceEnd,
   UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);