diff options
| -rw-r--r-- | utf8.h | 7 | ||||
| -rw-r--r-- | utfebcdic.h | 8 |
2 files changed, 15 insertions, 0 deletions
@@ -227,6 +227,13 @@ Perl's extended UTF-8 means we can have start bytes up to FF. */ +/* Anything larger than this will overflow the word if it were converted into a UV */ +#if defined(UV_IS_QUAD) +# define HIGHEST_REPRESENTABLE_UTF8 "\xFF\x80\x8F\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF" +#else +# define HIGHEST_REPRESENTABLE_UTF8 "\xFE\x83\xBF\xBF\xBF\xBF\xBF" +#endif + /* Is the representation of the Unicode code point 'cp' the same regardless of * being encoded in UTF-8 or not? */ #define OFFUNI_IS_INVARIANT(cp) isASCII(cp) diff --git a/utfebcdic.h b/utfebcdic.h index a6ba4fa6a3..227e0eb3db 100644 --- a/utfebcdic.h +++ b/utfebcdic.h @@ -268,6 +268,14 @@ explicitly forbidden, and the shortest possible encoding should always be used * for more */ #define QUESTION_MARK_CTRL LATIN1_TO_NATIVE(0x9F) +/* Any I8 string larger than this will overflow the word if it were converted into a UV */ +#if defined(UV_IS_QUAD) +# define HIGHEST_REPRESENTABLE_UTF8 "\xFF\xAF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF" +#else +# define HIGHEST_REPRESENTABLE_UTF8 "\xFF\xA0\xA0\xA0\xA0\xA0\xA0\xA3\xBF\xBF\xBF\xBF\xBF\xBF" +#endif + + /* * ex: set ts=8 sts=4 sw=4 et: */ |