Mercurial > hg > xemacs-beta
diff src/charset.h @ 4096:1abf84db2c7f
[xemacs-hg @ 2007-08-04 20:00:10 by aidan]
Preserve invalid UTF-8, UTF-16 sequences on encoding, decoding.
| author | aidan |
|---|---|
| date | Sat, 04 Aug 2007 20:00:24 +0000 |
| parents | 3ef0aaf3dc34 |
| children | d7cc9553d3eb e0db3c197671 |
line wrap: on
line diff
--- a/src/charset.h Fri Aug 03 21:51:12 2007 +0000 +++ b/src/charset.h Sat Aug 04 20:00:24 2007 +0000 @@ -567,12 +567,20 @@ UNICODE_UTF_16, UNICODE_UTF_8, UNICODE_UTF_7, - UNICODE_UCS_4 + UNICODE_UCS_4, + UNICODE_UTF_32 }; void encode_unicode_char (Lisp_Object USED_IF_MULE (charset), int h, int USED_IF_MULE (l), unsigned_char_dynarr *dst, - enum unicode_type type, unsigned int little_endian); + enum unicode_type type, unsigned int little_endian, + int write_error_characters_as_such); + +#define UNICODE_ERROR_OCTET_RANGE_START 0x200000 + +#define valid_utf_16_first_surrogate(ch) (((ch) & 0xFC00) == 0xD800) +#define valid_utf_16_last_surrogate(ch) (((ch) & 0xFC00) == 0xDC00) +#define valid_utf_16_surrogate(ch) (((ch) & 0xF800) == 0xD800) void set_charset_registries(Lisp_Object charset, Lisp_Object registries);