1 /*-
2 * SPDX-License-Identifier: BSD-2-Clause
3 *
4 * Copyright (c) 2013 Ed Schouten <ed@FreeBSD.org>
5 * All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 */
28
29 #include <sys/queue.h>
30
31 #include <assert.h>
32 #include <errno.h>
33 #include <langinfo.h>
34 #include <limits.h>
35 #include <string.h>
36 #include <uchar.h>
37
38 #include "../iconv/citrus_hash.h"
39 #include "../iconv/citrus_module.h"
40 #include "../iconv/citrus_iconv.h"
41 #include "mblocal.h"
42
43 typedef struct {
44 bool initialized;
45 struct _citrus_iconv iconv;
46 char srcbuf[MB_LEN_MAX];
47 size_t srcbuf_len;
48 union {
49 charXX_t widechar[DSTBUF_LEN];
50 char bytes[sizeof(charXX_t) * DSTBUF_LEN];
51 } dstbuf;
52 size_t dstbuf_len;
53 } _ConversionState;
54 _Static_assert(sizeof(_ConversionState) <= sizeof(mbstate_t),
55 "Size of _ConversionState must not exceed mbstate_t's size.");
56
57 size_t
mbrtocXX_l(charXX_t * __restrict pc,const char * __restrict s,size_t n,mbstate_t * __restrict ps,locale_t locale)58 mbrtocXX_l(charXX_t * __restrict pc, const char * __restrict s, size_t n,
59 mbstate_t * __restrict ps, locale_t locale)
60 {
61 _ConversionState *cs;
62 struct _citrus_iconv *handle;
63 size_t i, retval;
64 charXX_t retchar;
65
66 FIX_LOCALE(locale);
67 if (ps == NULL)
68 ps = &(XLOCALE_CTYPE(locale)->mbrtocXX);
69 cs = (_ConversionState *)ps;
70 handle = &cs->iconv;
71
72 /* Reinitialize mbstate_t. */
73 if (s == NULL || !cs->initialized) {
74 if (_citrus_iconv_open(&handle,
75 nl_langinfo_l(CODESET, locale), UTF_XX_INTERNAL) != 0) {
76 cs->initialized = false;
77 errno = EINVAL;
78 return (-1);
79 }
80 cs->srcbuf_len = cs->dstbuf_len = 0;
81 cs->initialized = true;
82 if (s == NULL)
83 return (0);
84 }
85
86 /* See if we still have characters left from the previous invocation. */
87 if (cs->dstbuf_len > 0) {
88 retval = (size_t)-3;
89 goto return_char;
90 }
91
92 /* Fill up the read buffer as far as possible. */
93 if (n > sizeof(cs->srcbuf) - cs->srcbuf_len)
94 n = sizeof(cs->srcbuf) - cs->srcbuf_len;
95 memcpy(cs->srcbuf + cs->srcbuf_len, s, n);
96
97 /* Convert as few characters to the dst buffer as possible. */
98 for (i = 0; ; i++) {
99 char *src, *dst;
100 size_t srcleft, dstleft, invlen;
101 int err;
102
103 src = cs->srcbuf;
104 srcleft = cs->srcbuf_len + n;
105 dst = cs->dstbuf.bytes;
106 dstleft = i * sizeof(charXX_t);
107 assert(srcleft <= sizeof(cs->srcbuf) &&
108 dstleft <= sizeof(cs->dstbuf.bytes));
109 err = _citrus_iconv_convert(handle, &src, &srcleft,
110 &dst, &dstleft, _CITRUS_ICONV_F_HIDE_INVALID, &invlen);
111 cs->dstbuf_len = (dst - cs->dstbuf.bytes) / sizeof(charXX_t);
112
113 /* Got new character(s). Return the first. */
114 if (cs->dstbuf_len > 0) {
115 assert(src - cs->srcbuf > cs->srcbuf_len);
116 retval = src - cs->srcbuf - cs->srcbuf_len;
117 cs->srcbuf_len = 0;
118 goto return_char;
119 }
120
121 /* Increase dst buffer size, to obtain the surrogate pair. */
122 if (err == E2BIG)
123 continue;
124
125 /* Illegal sequence. */
126 if (invlen > 0) {
127 cs->srcbuf_len = 0;
128 errno = EILSEQ;
129 return ((size_t)-1);
130 }
131
132 /* Save unprocessed remainder for the next invocation. */
133 memmove(cs->srcbuf, src, srcleft);
134 cs->srcbuf_len = srcleft;
135 return ((size_t)-2);
136 }
137
138 return_char:
139 retchar = cs->dstbuf.widechar[0];
140 memmove(&cs->dstbuf.widechar[0], &cs->dstbuf.widechar[1],
141 --cs->dstbuf_len * sizeof(charXX_t));
142 if (pc != NULL)
143 *pc = retchar;
144 if (retchar == 0)
145 return (0);
146 return (retval);
147 }
148
149 size_t
mbrtocXX(charXX_t * __restrict pc,const char * __restrict s,size_t n,mbstate_t * __restrict ps)150 mbrtocXX(charXX_t * __restrict pc, const char * __restrict s, size_t n,
151 mbstate_t * __restrict ps)
152 {
153
154 return (mbrtocXX_l(pc, s, n, ps, __get_locale()));
155 }
156