Merge branch 'dbus-1.6'

Conflicts:
	NEWS

NEWS

@@ -10,6 +10,10 @@ Configuration changes:
 
 Fixes:
 
+• Following Unicode Corrigendum #9, the noncharacters U+nFFFE, U+nFFFF,
+  U+FDD0..U+FDEF are allowed in UTF-8 strings again.
+  (fd.o #63072, Simon McVittie)
+
 • Diagnose incorrect use of dbus_connection_get_data() with negative slot
   (i.e. before allocating the slot) rather than returning junk
   (fd.o #63127, Dan Williams)

dbus/dbus-string.c

@@ -1577,19 +1577,11 @@ _dbus_string_split_on_byte (DBusString        *source,
  *
  * The second check covers surrogate pairs (category Cs).
  *
- * The last two checks cover "Noncharacter": defined as:
- *   "A code point that is permanently reserved for
- *    internal use, and that should never be interchanged. In
- *    Unicode 3.1, these consist of the values U+nFFFE and U+nFFFF
- *    (where n is from 0 to 10_16) and the values U+FDD0..U+FDEF."
- *
  * @param Char the character
  */
 #define UNICODE_VALID(Char)                   \
     ((Char) < 0x110000 &&                     \
-     (((Char) & 0xFFFFF800) != 0xD800) &&     \
-     ((Char) < 0xFDD0 || (Char) > 0xFDEF) &&  \
-     ((Char) & 0xFFFE) != 0xFFFE)
+     (((Char) & 0xFFFFF800) != 0xD800))
 
 /**
  * Finds the given substring in the string,

test/syntax.c

@@ -178,12 +178,14 @@ const char * const invalid_single_signatures[] = {
 
 const char * const valid_strings[] = {
     "",
-    "\xc2\xa9",
+    "\xc2\xa9",       /* UTF-8 (c) symbol */
+    "\xef\xbf\xbe",   /* U+FFFE is reserved but Corrigendum 9 says it's OK */
     NULL
 };
 
 const char * const invalid_strings[] = {
-    "\xa9",
+    "\xa9",           /* Latin-1 (c) symbol */
+    "\xed\xa0\x80",   /* UTF-16 surrogates are not valid in UTF-8 */
     NULL
 };