mbrtocXX_iconv.h revision 282275 
1/*-
2 * Copyright (c) 2013 Ed Schouten <ed@FreeBSD.org>
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
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.
13 *
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
24 * SUCH DAMAGE.
25 */
26
27#include <sys/cdefs.h>
28__FBSDID("$FreeBSD: stable/10/lib/libc/locale/mbrtocXX_iconv.h 282275 2015-04-30 16:08:47Z tijl $");
29
30#include <sys/queue.h>
31
32#include <assert.h>
33#include <errno.h>
34#include <langinfo.h>
35#include <limits.h>
36#include <string.h>
37#include <uchar.h>
38
39#include "../iconv/citrus_hash.h"
40#include "../iconv/citrus_module.h"
41#include "../iconv/citrus_iconv.h"
42#include "xlocale_private.h"
43
44typedef struct {
45	bool			initialized;
46	struct _citrus_iconv	iconv;
47	char			srcbuf[MB_LEN_MAX];
48	size_t			srcbuf_len;
49	union {
50		charXX_t	widechar[DSTBUF_LEN];
51		char		bytes[sizeof(charXX_t) * DSTBUF_LEN];
52	} dstbuf;
53	size_t			dstbuf_len;
54} _ConversionState;
55_Static_assert(sizeof(_ConversionState) <= sizeof(mbstate_t),
56    "Size of _ConversionState must not exceed mbstate_t's size.");
57
58size_t
59mbrtocXX_l(charXX_t * __restrict pc, const char * __restrict s, size_t n,
60    mbstate_t * __restrict ps, locale_t locale)
61{
62	_ConversionState *cs;
63	struct _citrus_iconv *handle;
64	size_t i, retval;
65	charXX_t retchar;
66
67	FIX_LOCALE(locale);
68	if (ps == NULL)
69		ps = &locale->mbrtocXX;
70	cs = (_ConversionState *)ps;
71	handle = &cs->iconv;
72
73	/* Reinitialize mbstate_t. */
74	if (s == NULL || !cs->initialized) {
75		if (_citrus_iconv_open(&handle,
76		    nl_langinfo_l(CODESET, locale), UTF_XX_INTERNAL) != 0) {
77			cs->initialized = false;
78			errno = EINVAL;
79			return (-1);
80		}
81		handle->cv_shared->ci_discard_ilseq = true;
82		handle->cv_shared->ci_hooks = NULL;
83		cs->srcbuf_len = cs->dstbuf_len = 0;
84		cs->initialized = true;
85		if (s == NULL)
86			return (0);
87	}
88
89	/* See if we still have characters left from the previous invocation. */
90	if (cs->dstbuf_len > 0) {
91		retval = (size_t)-3;
92		goto return_char;
93	}
94
95	/* Fill up the read buffer as far as possible. */
96	if (n > sizeof(cs->srcbuf) - cs->srcbuf_len)
97		n = sizeof(cs->srcbuf) - cs->srcbuf_len;
98	memcpy(cs->srcbuf + cs->srcbuf_len, s, n);
99
100	/* Convert as few characters to the dst buffer as possible. */
101	for (i = 0; ; i++) {
102		char *src, *dst;
103		size_t srcleft, dstleft, invlen;
104		int err;
105
106		src = cs->srcbuf;
107		srcleft = cs->srcbuf_len + n;
108		dst = cs->dstbuf.bytes;
109		dstleft = i * sizeof(charXX_t);
110		assert(srcleft <= sizeof(cs->srcbuf) &&
111		    dstleft <= sizeof(cs->dstbuf.bytes));
112		err = _citrus_iconv_convert(handle, &src, &srcleft,
113		    &dst, &dstleft, 0, &invlen);
114		cs->dstbuf_len = (dst - cs->dstbuf.bytes) / sizeof(charXX_t);
115
116		/* Got new character(s). Return the first. */
117		if (cs->dstbuf_len > 0) {
118			assert(src - cs->srcbuf > cs->srcbuf_len);
119			retval = src - cs->srcbuf - cs->srcbuf_len;
120			cs->srcbuf_len = 0;
121			goto return_char;
122		}
123
124		/* Increase dst buffer size, to obtain the surrogate pair. */
125		if (err == E2BIG)
126			continue;
127
128		/* Illegal sequence. */
129		if (invlen > 0) {
130			cs->srcbuf_len = 0;
131			errno = EILSEQ;
132			return ((size_t)-1);
133		}
134
135		/* Save unprocessed remainder for the next invocation. */
136		memmove(cs->srcbuf, src, srcleft);
137		cs->srcbuf_len = srcleft;
138		return ((size_t)-2);
139	}
140
141return_char:
142	retchar = cs->dstbuf.widechar[0];
143	memmove(&cs->dstbuf.widechar[0], &cs->dstbuf.widechar[1],
144	    --cs->dstbuf_len * sizeof(charXX_t));
145	if (pc != NULL)
146		*pc = retchar;
147	if (retchar == 0)
148		return (0);
149	return (retval);
150}
151
152size_t
153mbrtocXX(charXX_t * __restrict pc, const char * __restrict s, size_t n,
154    mbstate_t * __restrict ps)
155{
156
157	return (mbrtocXX_l(pc, s, n, ps, __get_locale()));
158}
159