]>
git.saurik.com Git - apple/libc.git/blob - locale/utf2-fbsd.c
2 * Copyright (c) 2002-2004 Tim J. Robbins
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 #include <sys/param.h>
28 /* dumb down UTF-8 to do UTF2 */
29 __FBSDID("$FreeBSD: src/lib/libc/locale/utf8.c,v 1.11 2004/07/27 06:29:48 tjr Exp $");
31 #include "xlocale_private.h"
41 #define UTF2_MB_CUR_MAX 3
43 static size_t _UTF2_mbrtowc(wchar_t * __restrict
, const char * __restrict
, size_t,
44 mbstate_t * __restrict
, locale_t
);
45 static int _UTF2_mbsinit(const mbstate_t *, locale_t
);
46 static size_t _UTF2_mbsnrtowcs(wchar_t * __restrict
, const char ** __restrict
,
47 size_t, size_t, mbstate_t * __restrict
, locale_t
);
48 static size_t _UTF2_wcrtomb(char * __restrict
, wchar_t, mbstate_t * __restrict
, locale_t
);
49 static size_t _UTF2_wcsnrtombs(char * __restrict
, const wchar_t ** __restrict
,
50 size_t, size_t, mbstate_t * __restrict
, locale_t
);
58 __private_extern__
int
59 _UTF2_init(struct __xlocale_st_runelocale
*xrl
)
62 xrl
->__mbrtowc
= _UTF2_mbrtowc
;
63 xrl
->__wcrtomb
= _UTF2_wcrtomb
;
64 xrl
->__mbsinit
= _UTF2_mbsinit
;
65 xrl
->__mbsnrtowcs
= _UTF2_mbsnrtowcs
;
66 xrl
->__wcsnrtombs
= _UTF2_wcsnrtombs
;
67 xrl
->__mb_cur_max
= UTF2_MB_CUR_MAX
;
73 _UTF2_mbsinit(const mbstate_t *ps
, locale_t loc
)
76 return (ps
== NULL
|| ((const _UTF2State
*)ps
)->want
== 0);
80 _UTF2_mbrtowc(wchar_t * __restrict pwc
, const char * __restrict s
, size_t n
,
81 mbstate_t * __restrict ps
, locale_t loc
)
84 int ch
, i
, mask
, want
;
87 us
= (_UTF2State
*)ps
;
89 if (us
->want
< 0 || us
->want
> 3) {
101 /* Incomplete multibyte sequence */
104 if (us
->want
== 0 && ((ch
= (unsigned char)*s
) & ~0x7f) == 0) {
105 /* Fast path for plain ASCII characters. */
108 return (ch
!= '\0' ? 1 : 0);
113 * Determine the number of octets that make up this character
114 * from the first octet, and a mask that extracts the
115 * interesting bits of the first octet. We already know
116 * the character is at least two bytes long.
118 * We also specify a lower bound for the character code to
119 * detect redundant, non-"shortest form" encodings. For
120 * example, the sequence C0 80 is _not_ a legal representation
121 * of the null character. This enforces a 1-to-1 mapping
122 * between character codes and their multibyte representations.
124 ch
= (unsigned char)*s
;
125 if ((ch
& 0x80) == 0) {
129 } else if ((ch
& 0xe0) == 0xc0) {
133 } else if ((ch
& 0xf0) == 0xe0) {
139 * Malformed input; input is not UTF2.
150 * Decode the octet sequence representing the character in chunks
151 * of 6 bits, most significant first.
154 wch
= (unsigned char)*s
++ & mask
;
157 for (i
= (us
->want
== 0) ? 1 : 0; i
< MIN(want
, n
); i
++) {
158 if ((*s
& 0xc0) != 0x80) {
160 * Malformed input; bad characters in the middle
170 /* Incomplete multibyte sequence. */
178 * Malformed input; redundant encoding.
186 return (wch
== L
'\0' ? 0 : want
);
190 _UTF2_mbsnrtowcs(wchar_t * __restrict dst
, const char ** __restrict src
,
191 size_t nms
, size_t len
, mbstate_t * __restrict ps
, locale_t loc
)
199 us
= (_UTF2State
*)ps
;
206 * The fast path in the loop below is not safe if an ASCII
207 * character appears as anything but the first byte of a
208 * multibyte sequence. Check now to avoid doing it in the loop.
210 if (nms
> 0 && us
->want
> 0 && (signed char)*s
> 0) {
215 if (nms
> 0 && (signed char)*s
> 0)
217 * Fast path for plain ASCII characters
221 else if ((nb
= _UTF2_mbrtowc(&wc
, s
, nms
, ps
, loc
)) ==
223 /* Invalid sequence - mbrtowc() sets errno. */
225 else if (nb
== 0 || nb
== (size_t)-2)
235 * The fast path in the loop below is not safe if an ASCII
236 * character appears as anything but the first byte of a
237 * multibyte sequence. Check now to avoid doing it in the loop.
239 if (nms
> 0 && len
> 0 && us
->want
> 0 && (signed char)*s
> 0) {
244 if (nms
> 0 && (signed char)*s
> 0) {
246 * Fast path for plain ASCII characters
251 } else if ((nb
= _UTF2_mbrtowc(dst
, s
, nms
, ps
, loc
)) ==
255 } else if (nb
== (size_t)-2) {
258 } else if (nb
== 0) {
272 _UTF2_wcrtomb(char * __restrict s
, wchar_t wc
, mbstate_t * __restrict ps
, locale_t loc
)
278 us
= (_UTF2State
*)ps
;
286 /* Reset to initial shift state (no-op) */
289 if ((wc
& ~0x7f) == 0) {
290 /* Fast path for plain ASCII characters. */
296 * Determine the number of octets needed to represent this character.
297 * We always output the shortest sequence possible. Also specify the
298 * first few bits of the first octet, which contains the information
299 * about the sequence length.
301 if ((wc
& ~0x7f) == 0) {
304 } else if ((wc
& ~0x7ff) == 0) {
307 } else if ((wc
& ~0xffff) == 0) {
316 * Output the octets representing the character in chunks
317 * of 6 bits, least significant last. The first octet is
318 * a special case because it contains the sequence length
321 for (i
= len
- 1; i
> 0; i
--) {
322 s
[i
] = (wc
& 0x3f) | 0x80;
325 *s
= (wc
& 0xff) | lead
;
331 _UTF2_wcsnrtombs(char * __restrict dst
, const wchar_t ** __restrict src
,
332 size_t nwc
, size_t len
, mbstate_t * __restrict ps
, locale_t loc
)
335 char buf
[MB_LEN_MAX
];
340 us
= (_UTF2State
*)ps
;
352 if (0 <= *s
&& *s
< 0x80)
353 /* Fast path for plain ASCII characters. */
355 else if ((nb
= _UTF2_wcrtomb(buf
, *s
, ps
, loc
)) ==
357 /* Invalid character - wcrtomb() sets errno. */
360 return (nbytes
+ nb
- 1);
367 while (len
> 0 && nwc
-- > 0) {
368 if (0 <= *s
&& *s
< 0x80) {
369 /* Fast path for plain ASCII characters. */
372 } else if (len
> (size_t)UTF2_MB_CUR_MAX
) {
373 /* Enough space to translate in-place. */
374 if ((nb
= (int)_UTF2_wcrtomb(dst
, *s
, ps
, loc
)) < 0) {
380 * May not be enough space; use temp. buffer.
382 if ((nb
= (int)_UTF2_wcrtomb(buf
, *s
, ps
, loc
)) < 0) {
387 /* MB sequence for character won't fit. */
389 memcpy(dst
, buf
, nb
);
393 return (nbytes
+ nb
- 1);