2008-12-22 12:02:22 +00:00
|
|
|
/* $Id$
|
|
|
|
|
|
|
|
Part of SWI-Prolog
|
|
|
|
|
|
|
|
Author: Jan Wielemaker and Anjo Anjewierden
|
|
|
|
E-mail: jan@swi.psy.uva.nl
|
|
|
|
WWW: http://www.swi-prolog.org
|
|
|
|
Copyright (C): 1985-2002, University of Amsterdam
|
|
|
|
|
|
|
|
This library is free software; you can redistribute it and/or
|
|
|
|
modify it under the terms of the GNU Lesser General Public
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
|
|
|
|
This library is distributed in the hope that it will be useful,
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
Lesser General Public License for more details.
|
|
|
|
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
|
|
License along with this library; if not, write to the Free Software
|
2013-01-16 00:19:07 +00:00
|
|
|
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
2008-12-22 12:02:22 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
#ifndef UTF8_H_INCLUDED
|
|
|
|
#define UTF8_H_INCLUDED
|
|
|
|
|
2013-01-16 00:19:07 +00:00
|
|
|
#define PL_MB_LEN_MAX 16
|
|
|
|
|
2008-12-22 12:02:22 +00:00
|
|
|
#define UTF8_MALFORMED_REPLACEMENT 0xfffd
|
|
|
|
|
|
|
|
#define ISUTF8_MB(c) ((unsigned)(c) >= 0xc0 && (unsigned)(c) <= 0xfd)
|
|
|
|
|
|
|
|
#define ISUTF8_CB(c) (((c)&0xc0) == 0x80) /* Is continuation byte */
|
|
|
|
#define ISUTF8_FB2(c) (((c)&0xe0) == 0xc0)
|
|
|
|
#define ISUTF8_FB3(c) (((c)&0xf0) == 0xe0)
|
|
|
|
#define ISUTF8_FB4(c) (((c)&0xf8) == 0xf0)
|
|
|
|
#define ISUTF8_FB5(c) (((c)&0xfc) == 0xf8)
|
|
|
|
#define ISUTF8_FB6(c) (((c)&0xfe) == 0xfc)
|
|
|
|
|
|
|
|
#define UTF8_FBN(c) (!(c&0x80) ? 0 : \
|
|
|
|
ISUTF8_FB2(c) ? 1 : \
|
|
|
|
ISUTF8_FB3(c) ? 2 : \
|
|
|
|
ISUTF8_FB4(c) ? 3 : \
|
|
|
|
ISUTF8_FB5(c) ? 4 : \
|
|
|
|
ISUTF8_FB6(c) ? 5 : -1)
|
|
|
|
#define UTF8_FBV(c,n) ( n == 0 ? c : (c & ((0x01<<(6-n))-1)) )
|
|
|
|
|
|
|
|
#define utf8_get_char(in, chr) \
|
|
|
|
(*(in) & 0x80 ? _PL__utf8_get_char(in, chr) \
|
|
|
|
: (*(chr) = *(in), (char *)(in)+1))
|
2013-12-06 23:22:42 +00:00
|
|
|
#define utf8_skip_char(in) \
|
|
|
|
(*(in) & 0x80 ? _PL__utf8_skip_char(in) \
|
|
|
|
: (char *)(in)+1)
|
2008-12-22 12:02:22 +00:00
|
|
|
#define utf8_put_char(out, chr) \
|
|
|
|
((chr) < 0x80 ? out[0]=(char)(chr), out+1 \
|
|
|
|
: _PL__utf8_put_char(out, (chr)))
|
|
|
|
|
|
|
|
extern char *_PL__utf8_get_char(const char *in, int *chr);
|
|
|
|
extern char *_PL__utf8_put_char(char *out, int chr);
|
2013-12-06 23:22:42 +00:00
|
|
|
extern char *_PL__utf8_skip_char(const char *out);
|
2008-12-22 12:02:22 +00:00
|
|
|
|
|
|
|
extern size_t utf8_strlen(const char *s, size_t len);
|
2013-12-04 23:01:30 +00:00
|
|
|
extern size_t utf8_strlen1(const char *s);
|
2013-12-06 23:22:42 +00:00
|
|
|
extern const char * utf8_skip(const char *s, int n);
|
2013-12-04 23:01:30 +00:00
|
|
|
extern int utf8_strncmp(const char *s1, const char *s2, size_t n);
|
|
|
|
extern int utf8_strprefix(const char *s1, const char *s2);
|
2008-12-22 12:02:22 +00:00
|
|
|
|
2013-12-02 14:49:41 +00:00
|
|
|
typedef enum {
|
|
|
|
S_ASCII,
|
|
|
|
S_LATIN,
|
|
|
|
S_WIDE
|
|
|
|
} unicode_type_t;
|
|
|
|
|
|
|
|
extern unicode_type_t _PL__utf8_type(const char *in0, size_t len);
|
|
|
|
|
2008-12-22 12:02:22 +00:00
|
|
|
#endif /*UTF8_H_INCLUDED*/
|