Fixed decoding of UTF-8

2 files changed, 18 insertions, 1 deletions

diff --git a/src/core/basetypes/ConvertUTF.c b/src/core/basetypes/ConvertUTF.c
index f5be6e79..2984f529 100644
--- a/src/core/basetypes/ConvertUTF.c
+++ b/src/core/basetypes/ConvertUTF.c
@@ -527,7 +527,19 @@ ConversionResult ConvertUTF8toUTF16 (
         /* Do this check whether lenient or strict */
         if (!isLegalUTF8(source, extraBytesToRead+1)) {
             result = sourceIllegal;
-            break;
+            if (flags == strictConversion) {
+                /* Abort conversion. */
+                break;
+            } else {
+                /*
+                 * Replace the maximal subpart of ill-formed sequence with
+                 * replacement character.
+                 */
+                source += findMaximalSubpartOfIllFormedUTF8Sequence(source,
+                                                                    sourceEnd);
+                *target++ = UNI_REPLACEMENT_CHAR;
+                continue;
+            }
         }
         /*
          * The cases all fall through. See "Note A" below.
diff --git a/src/core/basetypes/MCString.cc b/src/core/basetypes/MCString.cc
index 642fe6a0..cf71218b 100644
--- a/src/core/basetypes/MCString.cc
+++ b/src/core/basetypes/MCString.cc
@@ -1290,6 +1290,11 @@ void String::appendBytes(const char * bytes, unsigned int length, const char * c
         }
         CFRelease(encodingName);
     }
+    if (encoding == kCFStringEncodingUTF8) {
+        appendUTF8CharactersLength(bytes, length);
+        return;
+    }
+    
     CFStringRef cfStr = CFStringCreateWithBytes(NULL, (const UInt8 *) bytes, (CFIndex) length, encoding, false);
     if (cfStr != NULL) {
         CFDataRef data = CFStringCreateExternalRepresentation(NULL, cfStr, kCFStringEncodingUTF16LE, '_');