Changes in the validation of UTF-8

All UTF-8 encoding functionality (including the escape
sequence '\u') accepts all values from the original UTF-8
specification (with sequences of up to six bytes).

By default, the decoding functions in the UTF-8 library do not
accept invalid Unicode code points, such as surrogates. A new
parameter 'nonstrict' makes them accept all code points up to
(2^31)-1, as in the original UTF-8 specification.

1 files changed, 3 insertions, 3 deletions

diff --git a/lobject.c b/lobject.c
index 3ce052c2..5d340de6 100644
--- a/lobject.c
+++ b/lobject.c
@@ -343,7 +343,7 @@ size_t luaO_str2num (const char *s, TValue *o) {
 
 int luaO_utf8esc (char *buff, unsigned long x) {
   int n = 1;  /* number of bytes put in buffer (backwards) */
-  lua_assert(x <= 0x10FFFF);
+  lua_assert(x <= 0x7FFFFFFFu);
   if (x < 0x80)  /* ascii? */
     buff[UTF8BUFFSZ - 1] = cast_char(x);
   else {  /* need continuation bytes */
@@ -435,9 +435,9 @@ const char *luaO_pushvfstring (lua_State *L, const char *fmt, va_list argp) {
         pushstr(L, buff, l);
         break;
       }
-      case 'U': {  /* an 'int' as a UTF-8 sequence */
+      case 'U': {  /* a 'long' as a UTF-8 sequence */
         char buff[UTF8BUFFSZ];
-        int l = luaO_utf8esc(buff, cast(long, va_arg(argp, long)));
+        int l = luaO_utf8esc(buff, va_arg(argp, long));
         pushstr(L, buff + UTF8BUFFSZ - l, l);
         break;
       }